DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 09/23/2025 has been entered.
Response to Amendment
The amendment filed 09/02/2025 has been entered. Claims 1-2, 4-7, 9-11, 21-28 and 31-33 remain pending in the application.
Response to Arguments
Applicant's arguments, filed 09/02/2025, with respect to the rejections of the claims under 101 have been fully considered and are persuasive, therefore, the rejection has been withdrawn.
Applicant’s arguments, filed 09/02/2025, with respect to the rejections of claims 1, 23 and 27 under 103 have been fully considered and are persuasive because of the amendments. Therefore, the rejections have been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Meeker et al. (US Pub. 2019/0036340) and further in view of Woldeyohannes et al. (NPL: Sustainable renewable energy resources utilization in rural areas).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4, 6-7, 9, 11, 21-27 and 32-33 are rejected under 35 U.S.C. 103 as being unpatentable over Meeker et al. (US Pub. 2019/0036340) in view of Woldeyohannes et al. (NPL: Sustainable renewable energy resources utilization in rural areas).
As per claim 1, Meeker teaches a computer-implemented method of network topology prediction [abstract, “methods of allocating distributed energy resources (DERs) to loads connected to a microgrid”], the method comprising:
receiving, by one or more computing devices, network data comprising information associated with a network comprising, a plurality of nodes associated with a resource availability and a resource usage, wherein the resource availability is associated with an amount of a resource dispatched in association with at least a portion of the plurality of nodes at an initial time interval, and wherein the resource usage is associated with an amount of the resource used at the initial time interval [Fig. 1, paragraph 0004, disclose a network comprising a plurality of energy resource and loads; paragraph 0027, “controller 105 may receive electric power data from one or more loads indicating the amount of electricity being consumed (demand) and may also receive electric power data from one or more renewable energy resources indicating the amount of electricity being generated (supply) … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source. Accordingly, controller 105 may allocate the solar PV resources to supply power to meet the demand for power by the load”; the examiner interprets “energy resources and loads” as a plurality of nodes, and “the amount of electricity being generated (supply) to supply power to meet the demand” as the resource available; Also, paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using … availability of solar PV resources, wind, or DER”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; Fig. 6, paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; the examiner interprets the PV Power and Load power of day prior as the resource availability and resource usage at the initial time interval];
processing, by the one or more computing devices, the amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the amount of the resource used, with a machine-learned model to determine a next amount of the resource dispatched in association with at least the portion of the plurality of nodes at a time interval subsequent to the initial time interval, and a next amount of the resource used at the time interval subsequent to the initial time interval [paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using, for example, forecasts of the price of energy (e.g., real time pricing (RTP)), availability of solar PV resources, wind, or DER. A neural network may be used to forecast the energy consumed based on the current price of energy and usage data, and the forecasted energy and usage data may then be used to regulate loads accordingly”; paragraph 0028, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; paragraphs 0053 and 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605 PV forecasting neural network 604, load forecasting neural network 605, and utility peak day pricing TOU profiles 606 may transmit PV forecast signals, load forecast signals, and price profile signals for a period of 24 hours to the future AORA … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile”];
processing, by the one or more computing devices, the next amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the next amount of the resource used, with the machine-learned model using representations of a structure of the network indicative of statuses of at least the portion of the nodes, to determine data indicative of a network topology for activating or deactivating individual nodes of at least the portion of the plurality of nodes of the network [paragraphs 0028-0030, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources … controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”];
generating, by the one or more computing devices, based at least in part on the data indicative of the network topology, one or more predictions for at least one of the plurality of nodes at a future time interval [paragraph 0053, “FIG. 4 depicts a resource allocation scheme (e.g., advanced optimal resource allocation (AORA) 409) … AORA 409 may consider various power sources (e.g., solar, battery and grid) to meet the demand for power at the one or more loads while minimizing the total cost of energy. In order to select the combination of these power sources, in an optimal way (select the power sources costing the least amount of power), a forecasted load profile, the forecasted PV power profile, and a real-time grid pricing (RTP) signal are used … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile. AORA 409 may forecasts the PV profile and the load profile using, for example, a feedforward neural network”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs]; and
controlling, by the one or more computing devices, and as the at least one of the plurality of nodes, at least one of i) one or more points in the network, or ii) one or more connections in the network between the points, based at least in part on the one or more predictions for the at least one of the plurality of nodes [paragraph 0030, “controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”].
Meeker does not teach
a network comprising, in a plurality of regions, a plurality of nodes associated with a resource availability and a resource usage (emphasis added);
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions (emphasis added);
the next amount of the resource used in the portion of the plurality of geographic regions (emphasis added);
Woldeyohannes teaches
a network comprising, in a plurality of regions, a plurality of nodes associated with a resource availability and a resource usage [Fig. 1 “geographical area with potential energy sources distribution”; page 3, section 2.2, 1st paragraph, “Depending on the geographic location, different subdivisions of the case study have various demand and renewable energy potential. As depicted in Fig. 1, some subdivision (Region 10) contains RE potential of all types considered in this study, while others are limited to only one type of renewable energy resource (Region 1, Region 3, Region 5, Region 7 and Region 9)”; page 3, Col. 1, 2nd paragraph, “Each region might experience various demand and supply scenarios depending on season and environmental conditions. In order to come up with detailed energy demand profile for each region, it is important to take into consideration several factors such as type of appliances used, number of occupants in each house, lifestyle pattern, culture, and house occupation period”; section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”];
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region];
the next amount of the resource used in the portion of the plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region; Since Meeker in paragraph 0060 teaches using a feedforward neural network designed to forecast both the future available PV power and the future load demand for the next 24 hours (the next amount of the resource used), while Woldeyohannes teaches the resource used in the portion of the plurality of geographic regions, therefore, the combination of Meeker and Woldeyohannes teaches the above claim limitation];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include a network comprising, in a plurality of regions, a plurality of nodes associated with a resource availability and a resource usage, and the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions of Woldeyohannes. Doing so would help determining the regions for allocating and/or developing the renewable energy resources (Woldeyohannes, abstract).
As per claim 2, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
the network data comprises resource availability data indicative of a total resource supply dispatched in association with the plurality of nodes during the initial time interval [Fig. 6, paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; the examiner interprets the PV Power and Load power of week/day prior as the resource availability and resource usage at the initial time interval];
Woldeyohannes teaches
the network data comprises resource usage data indicative of a plurality of resource usages associated with the plurality of geographic regions during the initial time interval [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region; Since Meeker in paragraph 0064 teaches the resource usage data during the initial time interval, while Woldeyohannes teaches the resource usage data indicative of a plurality of resource usages associated with the plurality of geographic regions, therefore, the combination of Meeker and Woldeyohannes teaches the above claim limitation];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the network data comprises resource usage data indicative of a plurality of resource usages associated with the plurality of geographic regions of Woldeyohannes. Doing so would help determining the regions for allocating the renewable energy resources (Woldeyohannes, abstract).
As per claim 4, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
wherein the resource availability comprises power dispatched in association with at least the portion of the plurality of nodes [abstract, “The devices and methods may determine an allocation of the renewable sources to one or more loads in the microgrid.”; paragraph 0025, “methods, and systems disclosed herein may control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using … availability of solar PV resources, wind, or DER”]; and
the resource usage comprises power demand of the at least the portion of the plurality of nodes [paragraph 0027, “controller 105 may receive electric power data from one or more loads indicating the amount of electricity being consumed (demand) … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load].
As per claim 6, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
individual nodes of the plurality of nodes are associated with corresponding ones of a plurality of energy distribution locations of an electrical power grid, and wherein the resource comprises electrical power [paragraph 0004, “FIG. 1 depicts a logical interaction between a controller and utilization of resources, including solar energy and local loads”; paragraph 0018, “one or more distributed energy resources (DERs) (e.g., battery storage, solar PV resources, and/or wind energy resources) are allocated, or turned on or turned off, to match the demand for power at one or more loads based on the cost associated with the DERs … The microgrid comprises the DERs and power lines that connect the DERs to the one or more loads within the residential, industrial, and/or commercial neighborhood”].
As per claim 7, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
generating, by the one or more computing devices, data indicative of at least one network optimization based at least in part on the one or more predictions [paragraph 0025, “systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises … A neural network may be used to forecast the energy consumed based on the current price of energy and usage data, and the forecasted energy and usage data may then be used to regulate loads accordingly … provides a control framework and solution for optimal allocation of solar PV resources in combination with other distributed energy resources (DER) including energy storage and variable load, in coordination with utility system operation and control”; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”; paragraph 0053, “FIG. 4 depicts a resource allocation scheme (e.g., advanced optimal resource allocation (AORA) 409) … AORA 409 may consider various power sources (e.g., solar, battery and grid) to meet the demand for power at the one or more loads while minimizing the total cost of energy. In order to select the combination of these power sources, in an optimal way (select the power sources costing the least amount of power), a forecasted load profile, the forecasted PV power profile, and a real-time grid pricing (RTP) signal are used”; It can be seen that the system, based on the forecast/predicted amount of power produced, the predicted amount of power to be consumed by a load, the cost associated with the one or more DERs, determines a control framework and solution for optimal allocation of solar PV resources and DER to the loads].
controlling, by the one or more computing devices, one or more of the plurality of nodes based at least in part on the network optimization [paragraph 0027, “Controller 105 may optimize the allocation of renewable energy resources to match the demand of loads in a microgrid, with respect to cost of energy to consumers … controller 105 may determine that the cost associated with allocating a solar PY resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source. Accordingly, controller 105 may allocate the solar PV resources to supply power to meet the demand for power by the load”; paragraph 0030, “controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”].
As per claim 9, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
receiving, by the one or more computing devices, historical training data comprising historical resource availability, historical resource usage, and a ground-truth resource cost for a resource provided in association with at least the portion of the plurality of nodes over a plurality of time intervals preceding the initial time interval, wherein the portion of the plurality of nodes comprises two or more nodes [Fig. 6, paragraph 0064, disclose historical data are transmitted to the neural network including time (month, day, hour), historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile. “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; examiner interprets the time of “month, week prior” as the time intervals preceding the initial time interval; paragraph 0034, “Local forecasting server 103 may generate forecasts for the power demand of the one or more loads and the power supply of DERs or solar PV resources. The forecasts may be based on historical data of the demand of the one or more loads and the supply of power by the DERs or solar PV resources”]; and
training, by the one or more computing devices, the machine-learned model using the historical training data [Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile to generate the output (load and PV forecast)].
As per claim 11, Meeker and Woldeyohannes teach the computer-implemented method of claim 9.
Woldeyohannes further teaches
each of the plurality of nodes is associated with one or more resource generation types of a plurality of resource generation types, and wherein the resource generation type is based at least in part on a way that each of the plurality of nodes generates the resource [Fig. 1, “geographical area with potential energy sources distribution”; page 3, section 2.2, 1st paragraph, “Depending on the geographic location, different subdivisions of the case study have various demand and renewable energy potential. As depicted in Fig. 1, some subdivision (Region 10) contains RE potential of all types considered in this study, while others are limited to only one type of renewable energy resource (Region 1, Region 3, Region 5, Region 7 and Region 9)”].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include each of the plurality of nodes is associated with one or more resource generation types of a plurality of resource generation types, and wherein the resource generation type is based at least in part on a way that each of the plurality of nodes generates the resource of Woldeyohannes. Doing so would help determining the regions for allocating the renewable energy resources (Woldeyohannes, abstract).
As per claim 21, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
the one or more predictions comprise a set of resource costs for the resource available for distribution from each of the plurality of nodes at the time interval subsequent to the initial time interval [paragraph 0018, “uses a predictive model in order to predict the cost of energy in real time. In addition, it can predict the cost of energy in the future”; paragraph 0027, “Controller 105 may optimize the allocation of renewable energy resources to match the demand of loads in a microgrid, with respect to cost of energy to consumers … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source”; It can be seen that the controller determines the cost associated with the one or more energy resource each time to supply power to meet demand of power consumed by the loads; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”; Model 503, may generate a cost associated with providing power to the load from the one or more DERs and send a signal to search procedure 509 indicating what the cost will be to provide power to the load from the one or more DERs at a next time increment (next state)], and wherein generating, by the one or more computing devices, based at least in part on the network data, the one or more predictions for at least one of the plurality of nodes comprises:
determining, by the one or more computing devices, the set of resource costs based at least in part on a set of constraints comprising transmission constraints associated with one or more connections between the plurality of nodes or resource generation constraints associated with an amount of the resource that can be distributed from each of the plurality of nodes [paragraph 0020, “An advanced optimal resource allocation (AORA) controller is provided for solar and DERs, to address the complexities of optimizing and matching resources in real-time, based on the cost of the resources and any intermittent generation issues of the resources, with the load at consumers' premises”; paragraphs 0053-0054, “FIG. 4 depicts a resource allocation scheme (e.g., advanced optimal resource allocation (AORA) 409) … AORA 409 may consider various power sources (e.g., solar, battery and grid) to meet the demand for power at the one or more loads while minimizing the total cost of energy. In order to select the combination of these power sources, in an optimal way (select the power sources costing the least amount of power), a forecasted load profile, the forecasted PV power profile, and a real-time grid pricing (RTP) signal are used. AORA 409 may input the amount of power forecasted to be consumed by a load (forecasted load profile), the forecast of the amount of power generated by solar PV resources (forecasted PV power profile), and the RTP signal for power generated by the utility distribution system. These inputs may be received from the utility DMS/ADMS 203 via DOCS 211. AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile” … if solar PV resources are the cheapest of the power sources, AORA409 will send a signal to SEEMS-to-Device-Controller Interface 219 with instructions that may cause SEEMS-to-Device-Controller Interface 219 to send one or more signals to PV Cntrl 230 to supply power to the bus bar to meet the power demands of the load. If the supply of power provided by solar PV resources connected to PV Cntrl 230 does not meet the demand of the load, SEEMS-to-Device-Controller Interface 219, may send one or more signals to a controller associated with the next cheapest power source (e.g., battery storage)].
As per claim 22, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
the one or more predictions comprise a resource cost for the resource available for distribution from each node of at least the portion of the plurality of nodes at the time interval subsequent to the initial time interval, and wherein the portion of the plurality of nodes comprises two or more nodes [paragraph 0018, “uses a predictive model in order to predict the cost of energy in real time. In addition, it can predict the cost of energy in the future”; paragraph 0027, “Controller 105 may optimize the allocation of renewable energy resources to match the demand of loads in a microgrid, with respect to cost of energy to consumers … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source”; It can be seen that the controller determines the cost associated with the one or more energy resource each time to supply power to meet demand of power consumed by the loads; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”; Model 503, may generate a cost associated with providing power to the load from the one or more DERs and send a signal to search procedure 509 indicating what the cost will be to provide power to the load from the one or more DERs at a next time increment (next state)]].
As per claim 23, Meeker teaches a computing system comprising:
one or more processors [paragraph 0053, “one or more processors”];
a machine-learned model trained to receive input data comprising information associated with a plurality of nodes in a network associated with a resource availability and a resource usage, and based at least in part on the input data, generate output data comprising one or more predictions associated with at least a portion of the plurality of nodes [Fig. 6, paragraph 0064, disclose historical data are transmitted to the neural network including time (month, day, hour), historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile. “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile to generate the output (load and PV forecast); Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”; the examiner interprets “energy resources and loads” as a plurality of nodes]; and
a memory comprising one or more computer-readable media, the memory storing computer-readable instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising [paragraph 0086, “the memory 1430 can comprise computer-accessible instructions and information … instruction(s) 1442 and the system information storage 1446 can be accessible or can be operated on by at least one of the processor(s)”]:
receiving the input data comprising information associated with the plurality of nodes respectively associated with the resource availability and the resource usage, wherein the resource availability is associated with an amount of a resource dispatched in association with at least the portion of the plurality of nodes at an initial time interval, and wherein the resource usage is associated with an amount of the resource used at the initial time interval [Fig. 1, paragraph 0004, disclose a network comprising a plurality of energy resource and loads; paragraph 0027, “controller 105 may receive electric power data from one or more loads indicating the amount of electricity being consumed (demand) and may also receive electric power data from one or more renewable energy resources indicating the amount of electricity being generated (supply) … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source. Accordingly, controller 105 may allocate the solar PV resources to supply power to meet the demand for power by the load”; the examiner interprets “energy resources and loads” as a plurality of nodes, and “the amount of electricity being generated (supply) to supply power to meet the demand” as the resource available; Also, paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using … availability of solar PV resources, wind, or DER”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; Fig. 6, paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; the examiner interprets the PV Power and Load power of day prior as the resource availability and resource usage at the initial time interval];
sending the input data to the machine-learned model, wherein the machine learned model is configured to process the amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the amount of the resource used, to determine a next amount of the resource dispatched in association with at least the portion of the plurality of nodes at a time interval subsequent to the initial time interval, and a next amount of the resource used at the time interval subsequent to the initial time interval [paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using, for example, forecasts of the price of energy (e.g., real time pricing (RTP)), availability of solar PV resources, wind, or DER. A neural network may be used to forecast the energy consumed based on the current price of energy and usage data, and the forecasted energy and usage data may then be used to regulate loads accordingly”; paragraph 0028, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; paragraphs 0053 and 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605 PV forecasting neural network 604, load forecasting neural network 605, and utility peak day pricing TOU profiles 606 may transmit PV forecast signals, load forecast signals, and price profile signals for a period of 24 hours to the future AORA … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile”];
processing the next amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the next amount of the resource used, with the machine- learned model using representations of a structure of the network indicative of statuses of at least the portion of the nodes, to determine data indicative of a network topology for activating or deactivating individual nodes of at least the portion of the plurality of nodes of the network [paragraphs 0028-0030, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources … controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”];
generating, based at least in part on the data indicative of the network topology, one or more predictions for at least one of the plurality of nodes at a future time interval [paragraph 0053, “FIG. 4 depicts a resource allocation scheme (e.g., advanced optimal resource allocation (AORA) 409) … AORA 409 may consider various power sources (e.g., solar, battery and grid) to meet the demand for power at the one or more loads while minimizing the total cost of energy. In order to select the combination of these power sources, in an optimal way (select the power sources costing the least amount of power), a forecasted load profile, the forecasted PV power profile, and a real-time grid pricing (RTP) signal are used … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile. AORA 409 may forecasts the PV profile and the load profile using, for example, a feedforward neural network”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs]; and
controlling, as the at least one of the plurality of nodes, at least one of i) one or more points in the network, or ii) one or more connections in the network between the points, based at least in part on the one or more predictions for the at least one of the plurality of nodes [paragraph 0030, “controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”].
Meeker does not teach
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions (emphasis added);
the next amount of the resource used in the portion of the plurality of geographic regions (emphasis added);
Woldeyohannes teaches
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region];
the next amount of the resource used in the portion of the plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region; Since Meeker in paragraph 0060 teaches using a feedforward neural network designed to forecast both the future available PV power and the future load demand for the next 24 hours (the next amount of the resource used), while Woldeyohannes teaches the resource used in the portion of the plurality of geographic regions, therefore, the combination of Meeker and Woldeyohannes teaches the above claim limitation];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions of Woldeyohannes. Doing so would help determining the regions for allocating and/or developing the renewable energy resources (Woldeyohannes, abstract).
As per claim 24, Meeker and Woldeyohannes teach the system of claim 23.
Meeker further teaches
generating, based at least in part on the output data from the machine-learned model, the one or more predictions comprises [Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile to generate the output (load and PV forecast), and the 24 hour forecast of PV, load and price profile is transmitted to AORA (advanced optimal resource allocation); paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605 PV forecasting neural network 604, load forecasting neural network 605, and utility peak day pricing TOU profiles 606 may transmit PV forecast signals, load forecast signals, and price profile signals for a period of 24 hours to the future AORA … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile”]:
determining the one or more predictions based at least in part on optimization of a cost function associated with optimal power flow for at least the portion of the plurality of nodes [paragraph 0058, “provide power to the load based on the optimization of the cost function. For example, if SBMPC optimizes J at a time tk and the cheapest costing power source is a solar PV resource, then AORA 218 may send a signal to SEEMS-to-Device Controller Interface 219 that will cause SEEMS-to-Device Controller Interface 219 to send a signal to PV Cntrl 230 to transfer power Ppv 227 to the load”; Model 503, may generate a cost associated with providing power to the load from the one or more DERs and send a signal to search procedure 509 indicating what the cost will be to provide power to the load from the one or more DERs at a next time increment (next state)].
As per claim 25, Meeker and Woldeyohannes teach the system of claim 23.
Meeker further teaches
the machine-learned model comprises a convolutional neural network or a support vector machine [paragraph 0060, “forecasting models, such as recurrent neural networks (RNN), support vector regressors (SVR), etc. can be used and integrated with the proposed SBMPC model”; paragraph 0058, “provide power to the load based on the optimization of the cost function. For example, if SBMPC (sampling-based model predictive control) optimizes J at a time tk and the cheapest costing power source is a solar PV resource, then AORA 218 may send a signal to SEEMS-to-Device Controller Interface 219 that will cause SEEMS-to-Device Controller Interface 219 to send a signal to PV Cntrl 230 to transfer power Ppv 227 to the load”].
As per claim 26, Meeker and Woldeyohannes teach the system of claim 23.
Meeker further teaches
control one or more of the plurality of nodes in dependence on the one or more predictions [paragraph 0026, “controller 105 may control the duty cycle of the pool pump or HVAC throughout a day to reduce or shed load during times when demand for electricity by loads in the distribution system exceeds the supply of electricity for the loads”; paragraph 0033, “the one or more loads may reduce power consumption in response to a price signal exceeding a certain price”].
As per claim 27, Meeker teaches one or more tangible non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations [paragraph 0086, “the memory 1430 can comprise computer-accessible instructions and information … instruction(s) 1442 and the system information storage 1446 can be accessible or can be operated on by at least one of the processors”], the operations comprising:
receiving network data comprising information associated with a network comprising a plurality of nodes associated with a resource availability and a resource usage, wherein the resource availability is associated with an amount of a resource dispatched in association with at least a portion of the plurality of nodes at an initial time interval, and wherein the resource usage is associated with an amount of the resource used at the initial time interval [Fig. 1, paragraph 0004, disclose a network comprising a plurality of energy resource and loads; paragraph 0027, “controller 105 may receive electric power data from one or more loads indicating the amount of electricity being consumed (demand) and may also receive electric power data from one or more renewable energy resources indicating the amount of electricity being generated (supply) … controller 105 may determine that the cost associated with allocating a solar PV resource to supply power to meet the demand of power consumed by a load at a certain time, is more affordable than allocating a traditional backup generator, or discharging a battery source. Accordingly, controller 105 may allocate the solar PV resources to supply power to meet the demand for power by the load”; the examiner interprets “energy resources and loads” as a plurality of nodes, and “the amount of electricity being generated (supply) to supply power to meet the demand” as the resource available; Also, paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using … availability of solar PV resources, wind, or DER”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; Fig. 6, paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605”; the examiner interprets the PV Power and Load power of day prior as the resource availability and resource usage at the initial time interval];
processing the amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the amount of the resource used, with a machine- learned model, to determine a next amount of the resource dispatched in association with at least the portion of the plurality of nodes, and a next amount of the resource used at a time interval subsequent to the initial time interval [paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and the matching of the dispatched solar PV resources and DER to load at consumer premises, using, for example, forecasts of the price of energy (e.g., real time pricing (RTP)), availability of solar PV resources, wind, or DER. A neural network may be used to forecast the energy consumed based on the current price of energy and usage data, and the forecasted energy and usage data may then be used to regulate loads accordingly”; paragraph 0028, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources”; paragraph 0048, “Forecasting 217 may forecast demand for power by one or more loads and/or the supply of power available in one or more DERs, PV solar resources”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; paragraphs 0053 and 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605 PV forecasting neural network 604, load forecasting neural network 605, and utility peak day pricing TOU profiles 606 may transmit PV forecast signals, load forecast signals, and price profile signals for a period of 24 hours to the future AORA … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile”];
processing the next amount of the resource dispatched in association with at least the portion of the plurality of nodes, and the next amount of the resource used, with the machine-learned model using representations of a structure of the network indicative of statuses of at least the portion of the nodes, to determine data indicative of a network topology for activating or deactivating individual nodes of at least the portion of the plurality of nodes of the network [paragraphs 0028-0030, “Historical and Real-Time Data Server 109 may receive a forecast of future power consumption, of the one or more loads from one or more loads attached to the microgrid … receive a forecast of future availability of one or more renewable energy resources, and the amount of power that may be produced by the one or more renewable energy resources from one or more renewable energy resources such as solar PV resources … receive signals from each of the one or more renewable energy resources about the amount of power that can be reliably supplied to meet the amount of power consumed by the one or more loads … determine a forecast that can be used by the controller 105 to determine the allocation of renewable energy resources … controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”];
generating, based at least in part on data indicative of the network topology, one or more predictions for at least one of the plurality of nodes at a future time interval [paragraph 0053, “FIG. 4 depicts a resource allocation scheme (e.g., advanced optimal resource allocation (AORA) 409) … AORA 409 may consider various power sources (e.g., solar, battery and grid) to meet the demand for power at the one or more loads while minimizing the total cost of energy. In order to select the combination of these power sources, in an optimal way (select the power sources costing the least amount of power), a forecasted load profile, the forecasted PV power profile, and a real-time grid pricing (RTP) signal are used … AORA 409 may allocate the DERs or solar PV resources that should be assigned to supply the power to cover the demand for power at the load, based on the cost RTP, forecasted load profile, and forecasted PV power profile. AORA 409 may forecasts the PV profile and the load profile using, for example, a feedforward neural network”; paragraph 0060, “use a feedforward neural network designed to forecast both the future available PV power and the future load demand for the required prediction horizon of the system. In this case, the feedforward neural network forecasts the needed values for the next 24 hours”; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs]; and
controlling, as the at least one of the plurality of nodes, at least one of i) one or more points in the network, or ii) one or more connections in the network between the points, based at least in part on the one or more predictions for the at least one of the plurality of nodes [paragraph 0030, “controller 105 may supply power to the hospital but may disable power intermittently to the residential apartment building, when the demand for power by the one or more loads exceeds the available supply of power … controller 105 to send control signals to local loads 113, with instructions that cause local loads 113 to operate within certain limits. For instance, a heating ventilation and air conditioning (HVAC) may be programmed to operate within certain voltage, real power, and reactive power limits, and these limits may correspond to a load profile”].
Meeker does not teach
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions (emphasis added);
the next amount of the resource used in the portion of the plurality of geographic regions (emphasis added);
Woldeyohannes teaches
the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region];
the next amount of the resource used in the portion of the plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region; Since Meeker in paragraph 0060 teaches using a feedforward neural network designed to forecast both the future available PV power and the future load demand for the next 24 hours (the next amount of the resource used), while Woldeyohannes teaches the resource used in the portion of the plurality of geographic regions, therefore, the combination of Meeker and Woldeyohannes teaches the above claim limitation];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the resource usage is associated with an amount of the resource used in a portion of a plurality of geographic regions of Woldeyohannes. Doing so would help determining the regions for allocating and/or developing the renewable energy resources (Woldeyohannes, abstract).
As per claim 32, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
the network data comprises resource availability data indicative of a total resource supply comprising resource supplies dispatched in association with corresponding ones of all of the plurality of nodes [abstract, “methods of allocating distributed energy resources (DERs) to loads connected to a microgrid”; paragraph 0054, “Optimal source dispatch 408 may allocate the power sources (solar PV resources, battery storage, or power from the utility distribution network) by sending a signal to SEEMS-to-Device Controller Interface 219, instructing SEEMS-to- device Controller Interface 219 to send signals to Bat Cntrl 229, PV Cntrl 230, or the PCC to transfer power to the bus bar that the load is connected to … send one or more signals to PV Cntrl 230 to supply power to the bus bar to meet the power demands of the load. If the supply of power provided by solar PV resources connected to PV Cntrl 230 does not meet the demand of the load … battery storage is the next cheapest option, SEEMS-to Device-Controller Interface 219 may send a control signal to Bat Cntrl 229 to supply power to the bus bar to meet the remaining power demands of the load”; It can be seen that the network data comprising the power supply to the load from the power sources (solar PV resources, battery storage, or power from the utility distribution network), and the total resource supply from the power sources corresponding to the power demands from the loads].
Woldeyohannes teaches
individual nodes of the plurality of nodes are associated with energy distribution to corresponding locations of a plurality of different locations [Fig. 1, “geographical area with potential energy sources distribution”; page 3, section 2.2, 1st paragraph, “Depending on the geographic location, different subdivisions of the case study have various demand and renewable energy potential. As depicted in Fig. 1, some subdivision (Region 10) contains RE potential of all types considered in this study, while others are limited to only one type of renewable energy resource (Region 1, Region 3, Region 5, Region 7 and Region 9)”; Tables 1-3 show the energy potential and demand for each region].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include individual nodes of the plurality of nodes are associated with energy distribution to corresponding locations of a plurality of different locations of Woldeyohannes. Doing so would help determining the regions for allocating the renewable energy resources (Woldeyohannes, abstract).
As per claim 33, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Woldeyohannes further teaches
the plurality of geographic regions are different from one another [Fig. 1 shows 10 different geographic regions].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the plurality of geographic regions are different from one another of Woldeyohannes. Doing so would help determining the regions for allocating the renewable energy resources (Woldeyohannes, abstract).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Meeker et al. in view of Woldeyohannes et al. and further in view of Ali et al. (US Pub. 2018/0048533).
As per claim 5, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker and Woldeyohannes do not teach
the resource availability comprises bandwidth availability associated with at least the plurality of nodes; and
the resource usage comprises bandwidth demand of at least the portion of the plurality of nodes.
Ali teaches
the resource availability comprises bandwidth availability associated with at least the plurality of nodes; and the resource usage comprises bandwidth demand of at least the portion of the plurality of nodes [paragraph 0040, “information related to resources consumed by the application 303. The resource information may identify consumption information and availability of the resources. An example may include bandwidth consumption and availability … productivity service 302 may detect high bandwidth usage by the component 305”].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the resource availability comprises bandwidth availability associated with at least the plurality of nodes, and the resource usage comprises bandwidth demand of at least the portion of the plurality of nodes of Suman. Doing so would help reducing resource consumption of the load upon detecting availability of a resource such as a network bandwidth is less an availability threshold (Ali, 0040).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Meeker et al. in view of Woldeyohannes et al. and further in view of Li et al. (US Pub. 2019/0312457).
As per claim 10, Meeker and Woldeyohannes teach the computer-implemented method of claim 9.
Meeker (as modified) further teaches
training, by the one or more computing devices, the machine-learned model using the historical training data comprises [Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile to generate the output (load and PV forecast)]:
sending, by the one or more computing devices, a portion of the historical training data to the machine-learned model, wherein the portion of the historical training data comprises the historical resource availability of at least the portion of the plurality of nodes, wherein the portion of the historical training data comprises the historical resource usage [Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, price profile to generate the output (load and PV forecast), paragraph 0064, “Load/PV Historical database 602 may transmit load power signals corresponding to the power consumed by the one or more load, or power supplied signals by the one or more solar PV sources, for the week or day prior to the time at which the load power signals and/or power supplied signals are sent to Load Forecasting Neural Network 605. Load/PV Historical database 602 may also transmit these signals to PV Forecasting Neural Network 604”; Since Meeker teaches historical data of power supply and power usage associated with a plurality of nodes are processed, while Nomura in fig. 1 and paragraphs 0020-0029 teaches the plurality of nodes are included in the regions such as building 21 and the residences 22 and 23, therefore, the combination of Meeker and Nomura teaches the above claim limitation]; and
responsive to sending the historical training data to the machine-learned model, obtaining, by the one or more computing devices, an output of the machine-learned model comprising a predicted resource cost of the resource provided at each of the plurality of nodes [Fig. 6 shows the neural networks processes the inputs which comprising historical power consumption data associated with one or more loads or historical power supply data associated with one or more solar PV sources, profile selection to generate the output which including the price profile; paragraph 0025, “methods, and systems disclosed herein may improve coordination and control of the dispatch of solar PV resources and DER, and forecasts of the price of energy (e.g., real time pricing (RTP)), availability of solar PV resources, wind, or DER. A neural network may be used to forecast the energy consumed based on the current price of energy and usage data, and the forecasted energy and usage data may then be used to regulate loads accordingly”; Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power produced by the one or more DERs … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”];
determining, by the one or more computing devices, at each of the plurality of iterations, one or more differences between the predicted resource cost and the ground-truth resource cost at each of the plurality of nodes [Fig. 11, paragraph 0074, “a process of optimizing a control scheme for resource allocation … determine a predicted amount of power to be consumed by a load connected to the one or more DERs … determine a cost associated with the one or more DERs to provide the predicted amount of power to the load from the one or more DERs … transfer the predicted amount of power to the load from the one or more DERs”; paragraph 0025, “A neural network may be used to forecast the energy consumed based on the current price of energy and usage data; paragraphs 0032-0033, “Model reference server 107 may receive price signals associated with the price of power provided by the utility distribution system via electric utility server … in response to a price signal exceeding a certain price”]; and
adjusting, by the one or more computing devices, one or more parameters of the machine-learned model to minimize the one or more differences between the predicted resource cost and the ground-truth resource cost at each of the plurality of nodes [paragraph 0033, “cause the one or more loads to make short-term reductions in power consumption in response to a price signal from the electricity hourly market … For example, the one or more loads may reduce power consumption in response to a price signal exceeding a certain price … power consumption may be reduced or curtailed to within 1 to 4 hours, and may include turning off or dimming banks of lighting, adjusting HVAC levels, or shutting down a portion of a manufacturing process”].
Woldeyohannes teaches
the resource used in the portion of the plurality of geographic regions [section 3.1, “As depicted in Fig. 1, the study area considers 10 sub-regions (regions R1–R10). Each region has various renewable energy potential. The daily energy consumption for individual household is estimated taking into consideration the various facilities such as lumps, refrigerators, ceiling fans, TV, and microwaves. The total demand for the energy was estimated taking into considerations the number of population in the region, the availability of public facilities such as schools, hospitals, police stations and other public infrastructures”; Tables 1-3 show the energy potential and demand for each region];
Meeker and Woldeyohannes do not explicitly teach
sending, by the one or more computing devices, over a plurality of iterations, a portion of the historical training data to the machine-learned model … (emphasis added);
responsive to sending the historical training data to the machine-learned model, obtaining, by the one or more computing devices, at each of the plurality of iterations, an output … (emphasis added);
determining, by the one or more computing devices, at each of the plurality of iterations, one or more differences … (emphasis added);
adjusting, by the one or more computing devices, at each of the plurality of iterations, one or more parameters of the machine-learned model … (emphasis added);
Li teaches
sending, by the one or more computing devices, over a plurality of iterations, a portion of the historical training data to the machine-learned model; responsive to sending the historical training data to the machine-learned model, obtaining, by the one or more computing devices, at each of the plurality of iterations, an output …; determining, by the one or more computing devices, at each of the plurality of iterations, one or more differences …; and adjusting, by the one or more computing devices, at each of the plurality of iterations one or more parameters of the machine-learned model [paragraph 0025, “machine learning modules to automate and enable self-learning abilities to improve existing short and long term utility load forecasts using historical load data”; paragraph 0054, “The machine learning unit is preferably implemented by a deep neural network (DNN) 701. The DNN takes as input a set of energy variables, including features extracted from energy data sets in real-time or from historical data, and produces an output intended to forecast utility load; paragraph 0088, “During training … The neural network parameters θ are updated to minimize the error between the predicted value and actual value. The new parameters are used in the next iteration of self-learning”]”.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include iteratively training the machine learning model using historical data to produce output of Li. Doing so would help accurately predicting both demand and supply so that the proper scheduling, dispatch and pricing signals can be sent (Li, 0023).
Claim 28 is rejected under 35 U.S.C. 103 as being unpatentable over Meeker et al. in view of Woldeyohannes et al. and further in view of Peljto et al. (US Pub. 2004/0146425).
As per claim 28, Meeker and Woldeyohannes teach the one or more tangible non-transitory computer-readable media of claim 27.
Meeker and Woldeyohannes do not teach
at least one of: each of the plurality of nodes is associated with a resource loss value corresponding to an amount of the resource that is lost in a predetermined time interval before being distributed from a respective node of the plurality of nodes; or
each of the plurality of nodes is associated with a congestion value corresponding to a reduction in the rate at which the resource can be distributed from a respective node of the plurality of nodes.
Peljto teaches
each of the plurality of nodes is associated with a resource loss value corresponding to an amount of the resource that is lost in a predetermined time interval before being distributed from a respective node of the plurality of nodes [paragraph 0042, “Any load (for example, a consumer of electrical energy) can also participate in a similar manner as generators to the extent that they meet the same metering requirements and can reliably vary the load. The load will participate on an equal basis with market generators sources after some consideration for transmission losses”; paragraph 0107, “the energy balance constraint takes into account the transmission network losses by normalizing generation and load MW values with the corresponding loss sensitivity factors, LossFac. The transmission network losses differentiate balancing energy prices for generators and loads to provide financial covering for network losses”; paragraph 0123, “The above condition must be satisfied for each market participant. The market clearing price will increase because of network losses. There is an influence of network losses on locational marginal prices that is dependent on corresponding loss sensitivity factors representing transmission network losses. Each portfolio or single bid has its own loss sensitivity factor with respect to the reference node in the RTO”; Fig. 8, paragraph 0141, “Ramping will start 1 minute before the start of the operational 5-minute interval. This ramping rule will provide balancing energy service as it is dispatched by the imbalance market. These effects are illustrated in the time diagram of FIG. 8”].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include each of the plurality of nodes is associated with a resource loss value corresponding to an amount of the resource that is lost in a predetermined time interval before being distributed from a respective node of the plurality of nodes of Peljto. Doing so would help determining the imbalance prices for each market participant (Peljto, 0047).
Claim 31 is rejected under 35 U.S.C. 103 as being unpatentable over Meeker et al. in view of Woldeyohannes et al. and further in view of Mammone (US Pub. 2012/0265586).
As per claim 31, Meeker and Woldeyohannes teach the computer-implemented method of claim 1.
Meeker further teaches
the resource usage comprises first resource usage [paragraph 0026, “load may be a pool pump or heating and ventilation and air conditioning (HVAC) unit], the resource comprises a first resource [paragraph 0029, “the renewable energy resources may include, but are not limited to, solar PV sources, wind, piezoelectric energy scavenging devices, or other renewable energy resources, or traditional backup generation”];
Woldeyohannes further teaches
the portion of the plurality of nodes comprises a first portion of the plurality of nodes [Fig. 1 shows a network with a plurality of nodes (renewable energy potential), each associated with different regions; page 3, section 2.2, 1st paragraph, “Depending on the geographic location, different subdivisions of the case study have various demand and renewable energy potential. As depicted in Fig. 1, some subdivision (Region 10) contains RE potential of all types considered in this study, while others are limited to only one type of renewable energy resource (Region 1, Region 3, Region 5, Region 7 and Region 9)”], and the portion of the plurality of geographic regions comprises a first portion of the plurality of geographic regions [Fig. 1 shows a network comprising 10 regions, wherein, some of the regions (first portion) contain one type of renewable energy resource, and other regions contain other type of renewable energy resource].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include the portion of the plurality of nodes comprises a first portion of the plurality of nodes, and the portion of the plurality of geographic regions comprises a first portion of the plurality of geographic regions of Woldeyohannes. Doing so would help determining the regions for allocating and/or developing the renewable energy resources (Woldeyohannes, abstract).
Meeker and Woldeyohannes teach
generating, by the one or more computing devices, the one or more predictions comprises generating, by the one or more computing devices, based at least in part on the network data and a second resource usage associated with usage of a second resource in associated with at least a second portion of the plurality of nodes at the time interval subsequent to the initial time interval, the one or more predictions for the at least one of the plurality of nodes.
Mammone teaches
generating, by the one or more computing devices, the one or more predictions comprises generating, by the one or more computing devices, based at least in part on the network data and a second resource usage associated with usage of a second resource in associated with at least a second portion of the plurality of nodes at the time interval subsequent to the initial time interval, the one or more predictions for the at least one of the plurality of nodes [abstract, “method to measure and control power usage within a residential or commercial building plurality having of electrical circuits electrically connected to an over-current protection device to ensure optimum energy usage”; paragraph 0034, “monitoring electrical power use in a residence of building of the user over a first time period via an energy monitoring system to yield a baseline energy use of the first time period; paragraph 0035, “comparing the electrical power use for the residence or building of the second time period to a plurality of other individuals in a geographic area that is different than the geographic area of the user to yield comparison data … The comparison data may include an indication to the user that a total energy usage amount of the user during a usage from the first period has decreased relative to individuals in a geographic area that is different than a geographic area of the user””; paragraph 0134, “determine how installing geothermal power sources, such as solar panels or wind turbines, could save a customer money. The determination may be customized based on geographic location of the customer”].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the method of allocating distributed energy resources to loads of Meeker to include generating, based at least in part on the network data and a second resource usage associated with usage of a second resource in associated with at least a second portion of the plurality of nodes in at least the second portion of the plurality of regions at the time interval subsequent to the initial time interval, the one or more predictions for the at least one of the plurality of nodes of Mammone. Doing so would help suggesting corrective action to the users such as using the solar panels to save energy cost based on geographic location of the users (Mammone, 0134).
Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
HAGHIGHAT-KASHANI et al. (US Pub. 2014/0336960) describes a method for modeling power usage within a macro grid.
SANDERS et al. (US Patent 9,807,099) describes a method for distributed energy services management.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TRI T NGUYEN whose telephone number is 571-272-0103. The examiner can normally be reached M-F, 8 AM-5 PM, (CT).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, OMAR FERNANDEZ can be reached at 571-272-2589. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/TRI T NGUYEN/Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128