DETAILED ACTION
1. Claims 1-20 have been presented for examination.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statement (IDS) submitted on 11/22/2022 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
4. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. abstract idea) without anything significantly more.
i) In view of Step 1 of analysis, Claim(s) 1 is directed to a statutory category as a process, and claim 10 is directed to a statutory category as a machine which each represent a statutory category of invention. Therefore, claims 1-20 are directed to a patent eligible category of invention.
ii) In view of Step 2A, Prong 1 of analysis, claims 1, and 10 recite an abstract idea that falls within at least two of the judicial exception categories: Mathematical Concepts and Mental Processes.
The limitation of Claim 1 of “generating a long term day ahead schedule for battery charge and discharge, controllable power generation and load dispatch using a scheduler neural network model and a short-term near real-time schedule using the scheduler neural network model for forecasted power generation from renewable sources, demand, price, and costs for the aggregation of the plurality of the microgrids connected to the electrical grid;” recites the mathematical concept of generating a schedule. The claim limitation is also analogous to mentally making a schedule, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation in Claim 1 of “performing a cost optimization calculation using a gradient descent algorithm to develop a schedule for the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid;”, recites the mathematical concept of performing mathematical optimization as well as constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation in Claim 1 of “comparing the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation”, recites the mathematical concept of performing numerical comparisons. The claim limitation is also analogous to mentally performing numerical comparisons, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation of Claim 1 of “maintaining and using by the VPPP the scheduler neural network model to generate a schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the neural network scheduler model is less than the cost optimization calculation.” recites the mathematical concept of generating a schedule. The claim limitation is also analogous to mentally making a schedule, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation of Claim 10 of “the day ahead forecast and state information to generate a long term day ahead schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of the microgrids connected to the electrical grid;” recites the mathematical concept of generating a schedule. The claim limitation is also analogous to mentally making a schedule, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation of Claim 10 of “a mixed integer non-linear programing (MINLP) solver executed by the processor that receives the state information and performs a cost optimization calculation to develop a schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid;” recites the mathematical concept of generating a schedule and performing cost optimization. The claim limitation is also analogous to mentally making a schedule and also solving a cost optimization, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation of Claim 10 of “a schedule validator coupled to the neural network scheduler and the MINLP compares the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation developed by the MINLP;” recites the mathematical concept of generating a schedule and comparing cost optimization. The claim limitation is also analogous to mentally making a schedule and also comparing cost optimization results, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
The limitation of Claim 10 of “maintaining the scheduler neural network model in a microgrid scheduler associated with a microgrid to generate a long term day ahead schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the scheduler neural network model is less than the cost optimization calculation.” recites the mathematical concept of generating a schedule. The claim limitation is also analogous to mentally making a schedule, which constitutes a Mental Process that could be performed in the mind or with pencil and paper.
Regarding Claim 1, other than reciting “neural network model” and in Claim 10, other than reciting “a processor”, “a communication interface”, “a neural network scheduler”, “a mixed integer non-linear programing (MINLP) solver”, and “a schedule validator”, nothing in these claim elements precludes the steps from being performed mentally or with the aid of mathematical tools such as pencil and paper.
Dependent claims 2-9, and 11-20 further narrow the abstract idea identified in the independent claims.
iii) In view of Step 2A, Prong Two, the judicial exception is not integrated into a practical application. In Claim 1, the additional element of “neural network model” and in Claim 10, the additional elements of “a memory”, and “a processor”, “a communication interface”, “a neural network scheduler”, “a mixed integer non-linear programing (MINLP) solver”, and “a schedule validator”, merely uses a computer device as a tool to perform the abstract idea. (MPEP 2106.05(f)) The limitation in Claim 1, and similarly recited in Claim 10, of “receiving from external sources a day ahead forecast for electrical grid demand and price of electrical power;”, and “receiving from each controller connected to the plurality of microgrids state information for each microgrid connected to the electrical grid;” are mere instructions to implement an abstract idea using a computer in its ordinary capacity, or merely uses the computer as a tool to perform the identified abstract idea. See MPEP (2106.05(f)) Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a mental process) does not integrate a judicial exception into a practical application. (MPEP 2106.05(f)(2)) Additionally the limitation in Claim 1, and similarly recited in Claim 10, of “receiving from external sources a day ahead forecast for electrical grid demand and price of electrical power;”, and “receiving from each controller connected to the plurality of microgrids state information for each microgrid
connected to the electrical grid;”, alternatively can be viewed as insignificant extra-solution activity specifically pertaining to mere data gathering/output necessary to perform the idea (MPEP 2106.05(g)) and is not sufficient to integrate the judicial exception into a practical application. This is akin to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, which has been identified as extra solution activity. Therefore, the judicial exception is not integrated into a practical application.
Dependent claims 2-9 and 11-20 further narrow the abstract ideas, identified in the independent claims and do not introduce further additional elements for consideration beyond those addressed above.
iv) In view of Step 2B, claims 1 and 10 do not include additional elements that are sufficient to amount to significantly more than the judicial exception. In Claim 1, the additional element of “neural network model” and in Claim 10, the additional elements of “a memory”, and “a processor”, “a communication interface”, “a neural network scheduler”, “a mixed integer non-linear programing (MINLP) solver”, and “a schedule validator”, merely uses a computer device as a tool to perform the abstract idea. (MPEP 2106.05(f)) The limitation in Claim 1, and similarly recited in Claim 10, of “receiving from external sources a day ahead forecast for electrical grid demand and price of electrical power;”, and “receiving from each controller connected to the plurality of microgrids state information for each microgrid connected to the electrical grid;” are mere instructions to implement an abstract idea using a computer in its ordinary capacity, or merely uses the computer as a tool to perform the identified abstract idea. See MPEP (2106.05(f)) Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a mental process) does not integrate a judicial exception into a practical application. (MPEP 2106.05(f)(2)) Additionally the limitation in Claim 1, and similarly recited in Claim 10, of “receiving from external sources a day ahead forecast for electrical grid demand and price of electrical power;”, and “receiving from each controller connected to the plurality of microgrids state information for each microgrid connected to the electrical grid;”, alternatively can be viewed as an insignificant extra-solution activity, specifically pertaining to mere data gathering/output necessary to perform the abstract idea (MPEP 2106.05(g)) and is not sufficient to integrate the judicial exception into a practical application. This is akin to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, which has been identified as extra solution activity. Therefore, the claim as a whole does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, when considered alone or in combination, do not amount to significantly more than the judicial exception. As stated in Section I.B. of the December 16, 2014 101 Examination Guidelines, “[t]o be patent-eligible, a claim that is directed to a judicial exception must include additional features to ensure that the claim describes a process or product that applies the exception in a meaningful way, such that it is more than a drafting effort designed to monopolize the exception.”
The dependent claims include the same abstract ideas recited in the independent claims and merely incorporate additional details that narrow the abstract ideas without adding significantly more.
Dependent claims 2 and 11 further define the types of data calculations, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. These do not add significantly more than the abstract idea.
Dependent claims 3 and 13 further define the types of data calculations, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. These do not add significantly more than the abstract idea.
Dependent claims 4 and 12 further define the types of data analysis, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. These do not add significantly more than the abstract idea.
Dependent claims 5 and 20 further define the types of data conversion and mathematical determination, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. These do not add significantly more than the abstract idea.
Dependent claims 6 further define the types of data conversion and mathematical determination, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. These do not add significantly more than the abstract idea.
Dependent claims 7 and 17 further define the types of data, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. The receiving of long-term day ahead is similar to selecting information, based on types of information and availability of information and constitutes extra-solution activity necessary to execute the abstract idea but is insufficient to integrate it into a practical application. These do not add significantly more than the abstract idea.
Dependent claims 8 and 18 further define the types of data conversion, optimization and mathematical determination, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. The uploading of the selected day ahead schedule to the VPPP amount to mere transmission of the output of the abstract idea, and constitutes extra-solution activity necessary to execute the abstract idea but is insufficient to integrate it into a practical application. These do not add significantly more than the abstract idea.
Dependent claims 9 and 19 further define the types of data conversion and mathematical determination, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. The receiving of real-time price, demand forecast, microgrid data, and local weather station data and the uploading of the generated short-term schedule to the VPPP amount to mere data gathering and mere transmission of the output, and constitutes extra-solution activity necessary to execute the abstract idea but is insufficient to integrate it into a practical application. These do not add significantly more than the abstract idea.
Dependent claims 14 and 15 further define the types of data conversion and mathematical determination, which merely narrows the abstract idea identified as a mental process and/or mathematical concepts including mathematical formulas. The sending of real-time and instantaneous data to VPPP and the downloading of the schedule to the RTU controller amount to mere data gathering and mere transmission of the output, and constitutes extra-solution activity necessary to execute the abstract idea but is insufficient to integrate it into a practical application. These do not add significantly more than the abstract idea.
Dependent claim 16 recites the additional elements of “a processor and a memory each coupled to a hardware infrastructure that includes network circuitry”, and “a host operating system executed by the processor”, which is merely use of a computer device as a tool to perform the abstract idea. These do not add significantly more than the abstract idea.
v) Accordingly, claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. abstract idea) without anything significantly more.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
5. Claim 1-20 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
i) Claims 1, 4, 7, and 10 are rejected under 35 U.S.C. 112(b) as being indefinite. The term “long term day ahead” in claim 1, 4, 7, and 10 is a relative term which renders the claim indefinite. The term “long term day ahead” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The specification at paragraph [0035] and FIG.4 reference a “long term day ahead aggregate schedule” and at paragraph [0045] reference “long term day ahead forecasts” but never define a temporal lower or upper bound on the term “long term”. The specification indicates a 24-hour scheduling limit however, the claim does not limit further and “long term” is more than 24-hours in nature. This renders the claims vague and indefinite.
The term “short-term near real-time” in claim 1 and variants “short term real-time” and “short term near real-time” in claim 6 are relative terms which renders the claim indefinite. The terms are not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The specification at FIG.9B reference “default value of RT_interval is 15 minutes”, however, no standard is provided for distinguishing “short-term near real-time”, “short term real-time” and “short term near real-time” from one another or from the generic “real-time” This renders the claims vague and indefinite.
ii) Claim 1, in the preamble, recites the limitation "for use by a plurality of controllers connected to the VPPP, the controller controlling a plurality of microgrids connected to an electrical grid". There is insufficient antecedent basis for this limitation in the claim. It is unclear whether “the controller” refers to one specific controller of the “plurality of controllers”, all the controllers collectively, or a different controller altogether. This renders the claims vague and indefinite.
iii) Claim 5, recites the limitation "downloading the scheduler model developed by the VPPP to the controller controlling a microgrid". There is insufficient antecedent basis for this limitation in the claim. It is unclear whether “the controller” refers to one specific controller of the “plurality of controllers” stated in claim 1, all the controllers collectively, or a different controller altogether. This renders the claims vague and indefinite.
iv) Claim 6, recites the limitation " the controller of each of the plurality of microgrids". There is insufficient antecedent basis for this limitation in the claim. It is unclear whether “the controller” refers to one specific controller of the “plurality of controllers” stated in claim 1, all the controllers collectively, or a different controller altogether. This renders the claims vague and indefinite.
v) Claim 7, recites the limitation "scheduler model downloaded to the controller from the VPPP to generate a first day ahead schedule". There is insufficient antecedent basis for this limitation in the claim. It is unclear whether “the controller” refers to one specific controller of the “plurality of controllers” stated in claim 1, all the controllers collectively, or a different controller altogether. This renders the claims vague and indefinite.
vi) Claim 16, recites the limitation "the controller controlling a microgrid of the plurality of microgrids". There is insufficient antecedent basis for this limitation in the claim. It is unclear whether “the controller” refers to one specific controller of the “plurality of controllers” stated in claim 10, all the controllers collectively, or a different controller altogether. This renders the claims vague and indefinite.
Appropriate correction is required.
All claims dependent upon a rejected base claim are rejected by virtue of their dependency.
Claim Rejections - 35 USC § 103
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103(a) are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
6. Claim 1 is rejected under 35 U.S.C. 103 as being unpatentable over the teachings of Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507.; hereafter Abdolrasol,
Regarding Claim 1, Sanders discloses, “A method for developing a scheduler model by a virtual peaker power plant (VPPP) for use by a plurality of controllers connected to the VPPP, the controller controlling a plurality of microgrids connected to an electrical grid, the method comprising;” (See Sanders at paragraphs [0034], [0037], and [0038]), wherein a cloud-based virtual power plant architecture in which a centralized site management system develops scheduling logic for distributed site gateway controllers, each of which manages a microgrid-scale energy system connected to the utility grid is disclosed. The “site management system” constitutes the VPPP, the “site gateways” constitutes the controllers, and the site-resident energy systems each constitute a microgrid connected to the electrical grid.)
“receiving from external sources a day ahead forecast for electrical grid demand and price of
electrical power;” (See Sanders at paragraph [0056], and [0034] wherein receiving from external
sources a day ahead forecast for electrical grid demand and price of electrical power is disclosed.)
“receiving from each controller connected to the plurality of microgrids state information for each microgrid connected to the electrical grid;” (See Sanders at paragraph [0034]).
“generating a long term day ahead schedule for battery charge and discharge, controllable power generation and load dispatch using a schedular neural network model and a short-term near real-time schedule using the scheduler neural network model for forecasted power generation from renewable sources, demand, price, and costs for the aggregation of the plurality of the microgrids connected to the electrical grid;” (See Sanders at paragraph [0052], [0125], and [0123]).
However, Sanders, does not disclose, “scheduler neural network model” and “performing a cost optimization calculation using a gradient descent algorithm to develop a schedule for the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid; comparing the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation; and maintaining and using by the VPPP the scheduler neural network model to generate a schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the neural network scheduler model is less than the cost optimization calculation.”
Therefore, a secondary reference, Abdolrasol discloses, “scheduler neural network model” (See Abdolrasol Abstract and Equation 1) “performing a cost optimization calculation using a gradient descent algorithm to develop a schedule for the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid;” (See Abdolrasol, Abstract line 1, Section. 3 paragraph 1 and last paragraph, and FIG. 3 and 4. The Levenberg-Marquardt algorithm is a well-known gradient-descent-based optimization method that interpolates between Gauss-Newton and steepest-descent steps. The optimization drives the cost objective to an extremely low residual.) “comparing the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation;” (See Abdorasol section 1 last paragraph and Table 11, wherein a side-by-side comparison of the ANN-based scheduler’s cost performance against the cost performance of alternative optimization-based schedulers is disclosed.) “and maintaining and using by the VPPP the scheduler neural network model to generate a schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the neural network scheduler model is less than the cost optimization calculation.” (See Abdolrasol Conclusion)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution that can satisfy the per-second response requirements of the cloud-grid interface while being cost-validated against an offline optimal schedule. (See Sanders Abstract and paragraph [0034] and [0042], wherein Sanders acknowledges the need for real-time, sub-second response cloud to edge control loop and Abdolrasul teaches that precisely.)
7. Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over the teachings of Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507.; hereafter Abdolrasol, in further view of Nakabi et al., Nakabi, Taha Abdelhalim, and Pekka Toivanen. "Deep reinforcement learning for energy management in a microgrid with flexible demand." Sustainable energy, grids and networks 25 (2021): 100413; hereafter Nakabi
Regarding Claim 10, Sanders disclose,“A system for developing a scheduler model by a virtual peaker power plant (VPPP) for use by a plurality of controllers, each controller controlling a microgrid of a plurality of microgrids connected to an electrical grid comprising;” (See Sanders at paragraphs [0034], [0037], and [0038]), wherein a cloud-based virtual power plant architecture in which a centralized site management system develops scheduling logic for distributed site gateway controllers, each of which manages a microgrid-scale energy system connected to the utility grid is disclosed. The “site management system” constitutes the VPPP, the “site gateways” constitutes the controllers, and the site-resident energy systems each constitute a microgrid connected to the electrical grid.) “a processor;” (See Sanders at paragraph [0078]).
“a communication interface coupled to the processor, the communication interface configured to communicate with external sources to receive a day ahead forecast for electrical grid demand and price of electrical power, the communication interface further coupled to each controller connected to the plurality of microgrids to receive state information for each microgrid connected to the electrical grid;” (See Sanders at paragraphs [0063-0064], and [0066], wherein the communication interface as part of the cloud-connected site management system, the system receives day-ahead forecast and price data from external sources, and receives complete operational data from each site gateway at four-second intervals).
However, Sanders does not disclose, “a neural network scheduler executed by the processor that runs a scheduler neural network model that receives the day ahead forecast and state information to generate a long term day ahead schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of the microgrids connected to the electrical grid; a mixed integer non-linear programing (MINLP) solver executed by the processor that receives the state information and performs a cost optimization calculation to develop a schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid; a schedule validator coupled to the neural network scheduler and the MINLP compares the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation developed by the MINLP; and maintaining the scheduler neural network model in a microgrid scheduler associated with a microgrid to generate a long term day ahead schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the scheduler neural networkmodel is less than the cost optimization calculation.”
Therefore, a secondary reference, Abdolrasol discloses, “a neural network scheduler executed by the processor that runs a scheduler neural network model that receives the day ahead forecast and state information to generate a long term day ahead schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of the microgrids connected to the electrical grid;” (See Abdolrasol Abstract, and Section 2 paragraph 1, wherein the ANN produces a 24-hour binary schedule for 25 distributes generators across the 5 microgrids on an hourly basis).
“and maintaining the scheduler neural network model in a microgrid scheduler associated with a microgrid to generate a long term day ahead schedule for battery charge and discharge, controllable power generation and load dispatch for each microgrid of the plurality of microgrids when the total weighted costs of the scheduler neural network model is less than the cost optimization calculation.” (See Abdolrasol, conclusion, wherein the selection and retention of the ANN scheduler when its cost outperforms the comparator. The retained ANN scheduler then generates schedules for battery charge/discharge, controllable generation, and load dispatch for each of the five microgrids.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution that can satisfy the per-second response requirements of the cloud-grid interface while being cost-validated against an offline optimal schedule. (See Sanders Abstract and paragraph [0034] and [0042], wherein Sanders acknowledges the need for real-time, sub-second response cloud to edge control loop and Abdolrasul teaches that precisely.)
However, Sanders in view of Abdolrasol does not disclose, “a mixed integer non-linear programing (MINLP) solver executed by the processor that receives the state information and performs a cost optimization calculation to develop a schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid; a schedule validator coupled to the neural network scheduler and the MINLP compares the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation developed by the MINLP;”
Therefore, an analogous reference, Nakabi discloses, “a mixed integer non-linear programing (MINLP) solver executed by the processor that receives the state information and performs a cost optimization calculation to develop a schedule for using the forecasted power generation using renewable sources, demand, price, and costs for the aggregation of the plurality of microgrids connected to the electrical grid;” (See Nakabi Section 4.2 paragraph 2, wherein the gradient ascent on expected return, where reward is gross margin from operations, using production, consumption, price, and temperature forecast). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs. “a schedule validator coupled to the neural network scheduler and the MINLP compares the total weighted cost of the schedule developed by the scheduler neural network model and the cost optimization calculation developed by the MINLP;” (See Nakabi, Figure 11, wherein the schedule validator by plotting the per-day cost of the neural-network scheduler against the per-day cost of the gradient-based optimizer).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the cloud-based virtual power plant of Sanders with the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol and the profit performance and mathematical advancements of Nakabi in order to provide fast, real-time capable scheduling solution that can satisfy the per-second response requirements of the cloud-grid interface while being cost-validated against an offline optimal schedule. (See Sanders Abstract and [0032]).
8. Claims 2 and 3 is rejected under 35 U.S.C. 103 as being unpatentable over the teachings of Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507.; hereafter Abdolrasol, in further view of Fu et al., Fu, Tao, et al. "Predicting peak day and peak hour of electricity demand with ensemble machine learning." Frontiers in Energy Research 10 (2022): 944804.; hereafter Fu
Regarding Claim 2, Sander discloses,
“The method of claim 1, wherein the method further comprises; performing error analysis on the day ahead forecast before generating the long term day ahead schedule using past forecasts and historical data from a historian;” (See sanders [0035], wherein the central VPPP uses historical data.)
However, Sanders in view of Abdolrasol does not disclose, “and estimating uncertainty in the
day ahead forecasts using the historical data.”
Therefore, Fu discloses, “and estimating uncertainty in the day ahead forecasts using the historical data.” (See Fu Abstract, Introduction paragraph 5, and Section 2.1 paragraph 1, wherein the procedure trains the uncertainty-quantification ML models on historical data). In the interest of compact prosecution, also note that the applicant’s specification defines “uncertainty estimator” as using “historical data and information on past forecasts to arrive at an estimate for the uncertainty associated with the current forecasts” at paragraph [0038].
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol with Fu’s probabilistic uncertainty-quantification ML procedure as it drives the BESS dispatch decision-making. (See Fu Abstract).
Regarding Claim 3, Sanders does not disclose,
“The method of claim 2, wherein the method retrains the scheduler neural network model for the aggregation on microgrids when the total weighted costs of the scheduler neural network model is greater than the cost optimization calculation.”
Therefore, Abdolrasol discloses, “The method of claim 2, wherein the method retrains the scheduler neural network model for the aggregation on microgrids when the total weighted costs of the scheduler neural network model is greater than the cost optimization calculation.” (See Abdolrasol, Section 4.2 paragraph 1, and Section 5 paragraph 2, wherein it is disclosed that the ANN scheduler must be retrained when its performance does not match the underlying optimization-based scheduler’s performance and when the ANN’s output departs from the optimization-based BBSA schedule, the ANN parameters must be re-tuned).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol with the teachings of Sanders in order to retrain the ANN scheduler in the aggregated-microgrid VPP whenever its cost performance falls below the optimization-based scheduler’s cost performance. (See Abdolrasol Table 11).
9. Claims 4-6, 9, 11-16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over the teachings of Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507; hereafter Abdolrasol, in view of Fu et al., Fu, Tao, et al. "Predicting peak day and peak hour of electricity demand with ensemble machine learning." Frontiers in Energy Research 10 (2022): 944804.; hereafter Fu further in view of Nakabi et al., Nakabi, Taha Abdelhalim, and Pekka Toivanen. "Deep reinforcement learning for energy management in a microgrid with flexible demand." Sustainable energy, grids and networks 25 (2021): 100413; hereafter Nakabi.
Regarding Claim 4, Sanders does not disclose,
“The method of claim 3, wherein generating the long term day ahead schedule for each microgrid of the plurality of microgrids comprises: generating a long term day ahead schedule using the scheduler neural network model for a microgrid of the plurality of microgrids; computing a total weighted cost using the schedule generated by the scheduler neural network model;”
Therefore, Abdolrasol discloses,
“The method of claim 3, wherein generating the long term day ahead schedule for each microgrid of the plurality of microgrids comprises: generating a long term day ahead schedule using the scheduler neural network model for a microgrid of the plurality of microgrids; computing a total weighted cost using the schedule generated by the scheduler neural network model;” (See Abdolrasol Section 2 paragraph 2, Section 5 paragraph 2, and Table 8, discloses generating the long-term day-ahead schedule using the ANN scheduler for “a microgrid of the plurality of microgrids” and computing the resulting cost on a per-microgrid basis).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution. (See Sanders Abstract).
However, Sanders, Abdolrasol, and Fu do not disclose,
“running a mixed integer non-linear programing (MINLP) solver on forecasted generation, demand, price, and costs to calculate a total weighted cost; and comparing the total weighted cost of the schedule developed by the scheduler neural network model to the total weighted cost calculated by the MINLP solver;”
Therefore, Nakabi discloses,
“running a mixed integer non-linear programing (MINLP) solver on forecasted generation, demand, price, and costs to calculate a total weighted cost; and comparing the total weighted cost of the schedule developed by the scheduler neural network model to the total weighted cost calculated by the MINLP solver;” (See Nakabi Section 4.2 paragraph 2, wherein the comparison and retraining trigger using a gradient descent cost optimizer is disclosed). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol and Fu with Nakabi’s gradient based cost optimizer as the per microgrid MINLP comparator to reduce cost. (See Abdolrasol Section 6. And Nakabi Section 7 paragraph 1).
Regarding Claim 5, Sanders discloses,
“The method of claim 4, wherein the method further comprises: downloading the scheduler model developed by the VPPP to the controller controlling a microgrid when the total weighted costs of the MINLP solver is greater than the total weighted cost of the scheduler neural network model.” (See Sanders at paragraph [0034], [0037] and [0071], wherein downloading of a centrally-developed scheduler model from the cloud-based VPPP to a microgrid controller is disclosed).
Regarding Claim 6, Sanders discloses,
“The method of claim 5, wherein the controller of each of the plurality of microgrids uploads a short-term real-time schedule to the VPPP, the method further comprising:” (See Sanders Paragraph [0034], wherein the four-second reporting constitutes the short term real time).
“downloading updated price schedules to the controllers of the plurality of microgrids when the total weighted costs of the MINLP solver is less than the total weighted cost of the short term near real-time schedule;” (See Sanders at paragraph [0025], wherein when the comparator’s cost beats the neural network scheduler’s cost, the central VPPP downloads the comparator-derived price schedule to each site gateway controller).
“downloading a new scheduler model to each microgrid controller.” (See Sanders at paragraph [0025], wherein, the central VPPP downloads the comparator-derived price schedule to each site gateway controller).
However, Sanders does not disclose, “calculating the total weighted cost of using the short term real-time schedule received from the plurality of microgrids; calculating using the MINLP solver a total weighted cost for a buying/selling price schedule for the plurality of microgrids; comparing the total weighted costs of the short term real-time schedules to the total weighted costs calculated by the MINLP;” and “; retraining the scheduler neural net model for the microgrids;”
Therefore, Abdolrasol discloses,
“retraining the scheduler neural net model for the microgrids; and” (See Abdolrasol at Section 4 paragraph 1 and Table.6, wherein the neural network scheduler must be retrained when its performance does not match the optimization-based schedule).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution. (See Sanders Abstract)
However, Sanders in view of Abdolrasol and Fu does not disclose, “calculating the total weighted cost of using the short term real-time schedule received from the plurality of microgrids; calculating using the MINLP solver a total weighted cost for a buying/selling price schedule for the plurality of microgrids; comparing the total weighted costs of the short term real-time schedules to the total weighted costs calculated by the MINLP;”
Therefore, Nakabi discloses,
“calculating the total weighted cost of using the short term real-time schedule received from the plurality of microgrids;” (Nakabi Section 3.3 paragraph 1, and Figure 12(a), wherein it is disclosed that the cost calculation can be performed on a per-day, per-schedule basis).
“calculating using the MINLP solver a total weighted cost for a buying/selling price schedule for the plurality of microgrids;” (See Nakabi Section 6.2 paragraph 2, FIG 15, a cost-optimization comparator that develops a buying/selling price schedule from the same forecasted inputs is disclosed). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs.)
“comparing the total weighted costs of the short term real-time schedules to the total weighted costs calculated by the MINLP;” (See Nakabi Section 6.2 paragraph 3-4, FIG 11, wherein the cost performance of the neural-network scheduler is compared against the cost performance of the gradient-based optimizer). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs.
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention combine the teachings of Sanders and Abdolrasol and Fu with Nakabi’s comparator vs. neural network cost evaluation to reduce cost and emission. (See Abdolrasol section 6.)
Regarding Claim 9, Sanders discloses,
“The method of claim 5, wherein each controller: receives real-time price and short term demand forecast from the VPPP;” (See Sanders paragraph [0032], wherein real-time price and forecast data flowing from the central VPPP to the site gateway is disclosed.)
“and uploads the generated short term schedule to the VPPP.” (See Sanders paragraph [0032], wherein periodic upstream upload of operational data from each site gateway to the central management system is disclosed.)
However, Sanders does not disclose “receives real-time microgrid demand, generation, battery system SOC, and local weather station data from the microgrid; generates a short term schedule using the schedular neural network model; generates a short term schedule using the MINLP solver; selects the lowest weighted cost of energy for the microgrid from the generated short term schedules;”
Therefore, Abdolrasol discloses,
“receives real-time microgrid demand, generation, battery system SOC, and local weather station data from the microgrid;” (See Abdolrasol Equation 1, wherein the state variables are disclosed at a microgrid level.)
“generates a short term schedule using the scheduler neural network model;” (See Sanders paragraph [0032], wherein short-term schedule generation at fast time scales is disclosed. Abdolrasol at section 3 paragraph 4 discloses the neural-network scheduler implementation of the short-term schedule.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution. (See Sanders Abstract)
However, Sanders in view of Abdolrasol and Fu does not disclose “generates a short term schedule
using the MINLP solver; selects the lowest weighted cost of energy for the microgrid from the generated short term schedules;”
Therefore, Nakabi discloses,
“generates a short term schedule using the MINLP solver;” (See Sanders paragraph [0032], wherein short-term schedule generation at fast time scales is disclosed. See Nakabi section 6.2 paragraphs 2-4, wherein gradient ascent on expected return is mathematically equivalent to gradient descent on cost). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs.
“selects the lowest weighted cost of energy for the microgrid from the generated short term schedules;” (See Nakabi Section 6.2, and FIG 11, wherein the per-day cost of the neural network scheduler is plotted against the per-day cost of the optimization-based comparator, and the lowest-cost scheduler is selected for use.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol and Fu with Nakabi’s parallel optimizer comparator and cost-based selection logic to achieve cost and emission benefits. (See Nakabi Conclusion paragraph 1).
Regarding Claim 11, Sanders discloses,
“The system of claim 10, wherein the system further includes; a historian coupled to the memory and to a source of historical data; and a forecast uncertainty estimator coupled to the neural network scheduler that receives the day ahead forecast and state information and using the historical data from the historian forecasts values for the actual observations input to the neural network scheduler.” (See sanders [0035], wherein the central VPPP uses historical data.)
However, Sanders in view of Abdolrasol does not disclose, “The system of claim 10, wherein the system further includes; a historian coupled to the memory and to a source of historical data; and a forecast uncertainty estimator coupled to the neural network scheduler that receives the day ahead forecast and state information and using the historical data from the historian forecasts values for the actual observations input to the neural network scheduler.”
Therefore, Fu discloses, “The system of claim 10, wherein the system further includes; a historian coupled to the memory and to a source of historical data; (See Fu Abstract, Introduction paragraph 5, Section 2 paragraph 1, wherein the procedure trains the uncertainty-quantification ML models on historical data)
“and a forecast uncertainty estimator coupled to the neural network scheduler that receives the day ahead forecast and state information and using the historical data from the historian forecasts values for the actual observations input to the neural network scheduler.” (See Fu Introduction paragraph 5, Table 2, Section 2 paragraph 1 and 2.1 paragraph 1, wherein the forecast uncertainty estimator uses the historical data store to generate probabilistic forecasts of the observations that are then input to the scheduler).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol with Fu’s probabilistic uncertainty-quantification ML procedure as it drives the BESS dispatch decision-making. (See Fu Abstract).
Regarding Claim 12, Sanders discloses,
“The system of claim 11, wherein the system further includes: grid peak detection software
executed by the processor that receives the day ahead forecast from the external sources and couples the day ahead forecasts to the neural network scheduler, the forecast uncertainty estimator, and the historian.” (Sanders paragraph [0064-0065], wherein Sanders discloses that the VPPP processor routes receives day ahead forecast inputs to downstream consumers including the scheduling and historical analysis modules.)
However, Sanders in view of Abdorasol does not disclose, “grid peak detection software” and “to the neural network scheduler”
Therefore, Fu discloses, “grid peak detection software” and “to the neural network scheduler” (See Fu Table 2, wherein Fu discloses that the day-ahead forecast predictors are used for both the peak-day probability model and the uncertainty quantification model, and both models are trained on the historical data store.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdorasol with Fu for Sander’s architectural routing of forecast inputs with Fu’s teaching of the peak detection software to simultaneously feed the neural network model, uncertainty estimator, and historical data. (See Fu Abstract).
Regarding Claim 13, is being rejected under being the system counterpart of method claim 3,
“The system of claim 11, wherein the system includes: a trainer for the microgrid scheduler wherein the trainer retrains the scheduler model when the total weighted costs of the scheduler neural network model is greater than the cost optimization calculation.”
Regarding Claim 14, Sanders discloses,
“The system of claim 11, wherein the microgrid state information from each controller connected to a microgrid sends real-time data and instantaneous generation, demand, and state of charge (SOC) data to the VPPP.” (See Sanders paragraph [0064] and [0066], wherein periodic real-time upstream reporting of complete operational state from each gateway to the central VPPP is disclosed. )
However, Sanders does not explicitly disclose, “instantaneous generation, demand, and state of charge (SOC) data”
Therefore, Abdorasol discloses, “instantaneous generation, demand, and state of charge (SOC) data” (See Abdolrasol EQ 1, wherein the local microgrid includes the variables.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol to implement real-time reporting of instantaneous generation, demand, and SOC data from each microgrid controller to the VPPP to enable accurate short-interval scheduling decision. (See Abdorasol EQ 1).
Regarding Claim 15, Sanders discloses,
“The system of claim 11, wherein the system further includes an optimization outcome analyzer coupled to a remote terminal unit (RTU) controller controlling a microgrid of the plurality of microgrids, the outcome analyzer developing a schedule for grid interactive power flow for the microgrid controlled by the RTU that is downloaded to and executed by the RTU controller.” (See Sanders paragraph [0050], wherein each gateway controller functions as a field-level and control mode, [0052], wherein grid import/export scheduling is disclosed and [0037], wherein the developed schedule and rule logic is downloaded from the central site management system to each site gateway/RTU for local execution.)
However, Sanders in view of Abdorasol and Fu does not disclose “optimization outcome analyzer” and “grid interactive power flow”.
Therefore, Nakabi discloses, “optimization outcome analyzer”(See Nakabi FIG.11, wherein the
optimization outcome analyzer function compares the cost outcome of the neural network scheduler against the cost outcome of the optimization-based comparator) and “grid interactive power flow”(See Nakabi, FIG 15, wherein the optimization outcome analyzer’s schedule covers energy purchased from and sold to the main grid.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdorasol and Fu with Nakabi to make the RTU the natural execution point for the grid-interactive schedule for cost and emission benefits. (See Nakabi Conclusion Paragraph 1).
Regarding Claim 16, Sanders discloses,
“The system of claim 11, wherein the controller controlling a microgrid of the plurality of microgrids is an intelligent edge controller comprising:” (See Sanders paragraph [0129])
“a processor and a memory each coupled to a hardware infrastructure that includes network circuitry that communicatively connects the intelligent edge controller to the VPPP communication interface, which receives the scheduler model from the VPPP for the microgrid controlled by the intelligent edge controller;” (See Sanders paragraph [0018], wherein a processor and memory is disclosed; [0019],
wherein the site gateway uses open-standard network communication to connect to the central management system; ([0037], wherein the central site management system pushes scheduler software to each edge controller).
“and a host operating system executed by the processor that executes the downloaded scheduler model to develop a schedule for grid interactive power flow for the microgrid.” (See Sanders paragraph [0037], and [0052], wherein the edge controller includes a host operating system that executes locally-deployed software.)
However, Sanders in view of Abdorasol and Fu does not disclose “grid interactive power flow”.
Therefore, Nakabi discloses, “grid interactive power flow”(See Nakabi, FIG 15, wherein the
optimization outcome analyzer’s schedule covers energy purchased from and sold to the main grid.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol and Fu with Nakabi to implement an intelligent edge controller with the hardware architecture for cost and emission benefits. (See Nakabi Conclusion Paragraph 1).
Regarding Claim 19, Sanders discloses,
“The system of claim 16, wherein the schedule developed by the intelligent edge controller scheduler model is uploaded to the VPPP as a real-time schedule for the microgrid controlled by the intelligent edge control to retrain the scheduler neural net model.” (See Sanders at paragraph [0034], [0037] and [0071], wherein downloading of a centrally-developed scheduler model from the cloud-based VPPP to a microgrid controller is disclosed)
However, Sanders does not disclose, “retrain the scheduler neural net model”
Therefore, Abdolrasol discloses, “retrain the scheduler neural net model” (See Abdolrasol at Section 4 paragraph 1 and Table.6, wherein the neural network scheduler must be retrained when conditions aren’t met).
It would have been obvious to a person having ordinary skill in the art before the effective filling
date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution. (See Sanders Abstract).
Regarding Claim 20, Sanders discloses,
“The system of claim 19, wherein the retrained scheduler model is downloaded to the intelligent
edge controller controlling the microgrid.” (See Sanders at paragraph [0025], wherein, the central VPPP downloads the schedule to each site gateway controller).
However, Sanders does not disclose, “retrained”
Therefore, Abdolrasol discloses, “retrained” (See Abdolrasol at Section 4 paragraph 1 and Table.6, wherein the neural network scheduler is retrained).
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to utilize the artificial neural network scheduler trained against an optimization-based scheduler of Abdolrasol for the cloud-based virtual power plant of Sanders in order to provide fast, real-time capable scheduling solution. (See Sanders Abstract).
10. Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over the teachings of
Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507; hereafter Abdolrasol, in view of Fu et al., Fu, Tao, et al. "Predicting peak day and peak hour of electricity demand with ensemble machine learning." Frontiers in Energy Research 10 (2022): 944804.; hereafter Fu, in further view of Nakabi et al., Nakabi, Taha Abdelhalim, and Pekka Toivanen. "Deep reinforcement learning for energy management in a microgrid with flexible demand." Sustainable energy, grids and networks 25 (2021): 100413; hereafter Nakabi in further view of Aprillia et al., Aprillia, Happy, Hong-Tzer Yang, and Chao-Ming Huang. "Optimal decomposition and reconstruction of discrete wavelet transformation for short-term load forecasting." Energies 12.24 (2019): 4654.; hereafter Aprillia
Regarding Claim 7, Sander’s discloses,
“The method of claim 5, wherein each controller: receives long term day ahead forecasts for weather, peak power, grid demand from the VPPP and microgrid generation, demand, battery energy system and the state of their charge (SOC) and loads for the microgrid connected to the controller;” (See Sanders at paragraph [0035], wherein the VPPP distributes day-ahead forecast data to each site gateway controller); and “inputs the transformed day ahead forecasts to the scheduler model downloaded to the controller from the VPPP to generate a first day ahead schedule;” (Sanders paragraph [0062], wherein the scheduler model is downloaded from the VPPP to the controller for local execution.)
However, Sanders in view of Abdolrasol does not disclose, “peak power” and “transformers the day ahead forecasts to a frequency and a scale domain”
Therefore, Fu discloses, “peak power”, (See and Fu Abstract, Table 2 and introduction paragraph
4, wherein peak power day ahead scheduling is disclosed.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdorasol and Nakabi with Fu for Sander’s architecture with Fu’s teaching of the peak detection software to simultaneously feed the neural network model, uncertainty estimator, and historical data. (See Fu Abstract).
However, Sanders in view of Abdorasol and Fu does not disclose, “peak power”, “transformers the day ahead forecasts to a frequency and a scale domain” and “generates a second day ahead schedule with the day ahead forecasts using the MINLP solver.”
Therefore, Nakabi discloses, “and generates a second day ahead schedule with the day ahead forecasts using the MINLP solver.” (See Nakabi Section 6.2 paragraph 2-3 wherein a parallel optimization-based schedule generation is disclosed). In the interest of compact prosecution, also note that the applicant specification at paragraph [0042], the “MINLP solver” means a gradient-descent cost optimizer using forecasted inputs.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol and Fu with Nakabi’s parallel optimizer comparator and cost-based selection logic to achieve cost and emission benefits. (See Nakabi Conclusion paragraph 1).
However, Sanders in view of Abdolrasol in view of Fu in further view of Nakabi does not disclose, “transformers the day ahead forecasts to a frequency and a scale domain” and “generates a second day ahead schedule with the day ahead forecasts using the MINLP solver.”
Therefore, Aprillia, discloses, “transformers the day ahead forecasts to a frequency and a scale domain;” (See Aprillia section 1 paragraph 3, section 3.1 paragraph 3 and equation 1, wherein transforming the day-ahead forecast inputs to a frequency and scale domain before feeding them to the scheduler model.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol, Fu and Nakabi with Aprillia for the forecast preprocessing that improves scheduler accuracy to deliver a controller whose scheduling accuracy and cost performance is accurate. (See Nakabi Conclusion paragraph 1)
Regarding Claim 8, Sanders discloses,
“The method of claim 7, wherein each controller: compares the first day ahead schedule to the second day ahead schedule using an optimization outcome analyzer to select either the first or the
second day ahead schedule with the lowest weighted cost of energy for the microgrid to upload the selected day ahead schedule to the VPPP.” (Sanders at paragraph [0037], and [0034], wherein a value optimizing scheduling system and periodic upstream of complete operational data from each site gateway to the central site management system is disclosed).
However, Sanders in view of Abdolrasol and Fu does not disclose, “optimization outcome analyzer”
Therefore, Nakabi discloses, “optimization outcome analyzer” (See Nakabi Section 6.2 paragraph 3-4, FIG 11, and Conclusion, wherein comparing and selecting logic and that the neural network scheduler’s per day cost is plotted against the optimization-based comparators per day cost is disclosed.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol with Nakabi to achieve a dual schedule architecture. (See Nakabi Conclusion paragraph 1)
11. Claims 17 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over the teachings of
Sanders et al. US 9960637 B2, hereafter Sanders, in view of Abdolrasol et al., GM Abdolrasol, Maher, et al. "Energy management scheduling for microgrids in the virtual power plant system using artificial neural networks." Energies 14.20 (2021): 6507; hereafter Abdolrasol, in view of Fu et al., Fu, Tao, et al. "Predicting peak day and peak hour of electricity demand with ensemble machine learning." Frontiers in Energy Research 10 (2022): 944804.; hereafter Fu, in further in view of Nakabi et al., Nakabi, Taha Abdelhalim, and Pekka Toivanen. "Deep reinforcement learning for energy management in a microgrid with flexible demand." Sustainable energy, grids and networks 25 (2021): 100413; hereafter Nakabi further view of Hernandez et al., Hernández, Luis, et al. "Artificial neural networks for short-term load forecasting in microgrids environment." Energy 75 (2014): 252-264.; hereafter Hernandez
Regarding Claim 17, Sanders discloses,
“The system of claim 16, wherein the intelligent edge controller further includes a microgrid forecaster model executed by the host operating system the forecaster model generating a forecast for local demand and power generation for the intelligent edge controllers associated microgrid based on instantaneous aggregate demand, generation and battery system state of charge (SOC) inputs supplied to the intelligent edge controller from the microgrid.” (See Sanders paragraph [0103], wherein the intelligent gateway controller includes a host operation system capable of executing locally-deployed software models.)
However, Sanders in view of Abdolrasol in view of Fu in further view of Nakabi does not disclose,
“The system of claim 16, wherein the intelligent edge controller further includes a microgrid forecaster model executed by the host operating system the forecaster model generating a forecast for local demand and power generation for the intelligent edge controllers associated microgrid based on instantaneous aggregate demand, generation and battery system state of charge (SOC) inputs supplied to the intelligent edge controller from the microgrid.”
Therefore, Hernandez discloses, “The system of claim 16, wherein the intelligent edge controller further includes a microgrid forecaster model executed by the host operating system the forecaster model generating a forecast for local demand and power generation for the intelligent edge controllers associated microgrid based on instantaneous aggregate demand, generation and battery system state of charge (SOC) inputs supplied to the intelligent edge controller from the microgrid.” (See Hernandez Abstract, wherein a microgrid-resident forecaster model in disclosed; and section 4.2 subsection Input, wherein the demand forecaster receives aggregated demand inputs;)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol, Nakabi and Fu with Hernandez’s demand forecaster to achieve local forecasting capability needed to populate the edge controller’s scheduler inputs from local data alone, reducing dependency on VPPP-sourced forecasts and improving scheduling responsiveness at the edge. (See Hernandez page 253 section 1 paragraph 5)
Regarding Claim 18, Sanders in view of Abdolrasol and Fu do not disclose,
“The system of claim 17, wherein the forecaster model includes: A demand forecaster model that when executed by the processor generates a forecast for peak power flows with the microgrid; and a renewable generation forecaster model that when executed by the processor generates a forecast schedule for the generation of renewable energy within the microgrid to meet peak power flows.”
Therefore, Nakabi discloses, “and a renewable generation forecaster model that when executed by the processor generates a forecast schedule for the generation of renewable energy within the microgrid to meet peak power flows.” (See Nakabi section 3.1 paragraph 1 and abstract, the renewable generation forecaster is disclosed at a microgrid level.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders and Abdolrasol and Fu with Nakabi’s renewable energy generation to achieve cost and emission benefits. (See Nakabi Conclusion paragraph).
However, Sanders in view of Abdolrasol in view of Fu in further view of Nakabi does not disclose, “The system of claim 17, wherein the forecaster model includes: A demand forecaster model that when executed by the processor generates a forecast for peak power flows with the microgrid”
Therefore, Hernandez discloses, “The system of claim 17, wherein the forecaster model includes: A demand forecaster model that when executed by the processor generates a forecast for peak power flows with the microgrid;” (See Hernandez abstract, table 2, and page 257, wherein the demand forecaster model for microgrids that generates aggregated load forecasts is disclosed.)
It would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention to combine the teachings of Sanders, Abdolrasol, Nakabi and Fu with Hernandez’s to give the edge controller the expected supply-demand balance at peak times. (See Nakabi Abstract).
Conclusion
12. All Claims are rejected.
13. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
a. US 2017/0025894 A1; Sunverge Energy, Inc.,
b. US 2022/0247188 A1; Honeywell International Inc.,
c. US 2015/0039145 A1; ABB Technology AG,
14. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Saif A. Alhija whose telephone number is (571) 272-8635. The examiner can normally be reached on M-F, 10:00-6:00.
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, Renee Chavez, can be reached at (571) 270-1104. The fax phone number for the organization where this application or proceeding is assigned is (571) 273-8300. Informal or draft communication, please label PROPOSED or DRAFT, can be additionally sent to the Examiners fax phone number, (571) 273-8635.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
SAA
/SAIF A ALHIJA/Primary Examiner, Art Unit 2186
Prosecution Insights