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 .
Response to Amendment
Acknowledgement is made of amendment filed on 07/21/2026. The amendments of Applicant are entered and have been considered by Examiner. Claims 1-20 were previously pending. Claims 1, 12, 18 have been amended. Claim 2 is canceled. Claim 21 is added. Claims 1, 3-21 are pending.
Response to Arguments
Applicant argues on Pages 9-12 of applicants remarks that the prior art Alwar/Hedoes not teach facilitating an action for a network traffic load balancing process based on respective results of the application of the object formulation, where the amended claims now indicate the respective results comprises the first result and the second result.
Examiner notes that the previous claims can be interpreted such that an action is determined for each respective result of the application. However, since the applicant has amended the claims such that an action is determined based on both respective first and second results, the scope of invention has changed such that both results are now required as input for determining an action for a network traffic load balancing process.
Applicant’s arguments with respect to claim(s) 1, 3-21 have been considered but are moot because the new ground of rejection relies on new prior art not applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 for establishing a background for determining obviousness under 35 U.S.C. 103 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.
Claim(s) 1-2, 9-12, 15, 16, 18, 20, 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2026/0046694 A1 to Alwar et al. (hereinafter “Alwar”) in view of US 2014/0328190 A1 to Lord et al. (hereinafter “Lord”)
Regarding Claim 1, Alwar teaches A method, comprising:
determining, by a system comprising at least one processor, ([0004], discloses an apparatus including at least one processor for determining the need for offloading at the apparatus) respective results of application of an objective formulation to respective combinations of a specified user equipment of a source cell and respective target cells of a group of target cells, ([0036], discloses In some cases, it may be preferable if a source node prepares a handover to another neighbour cell over a set of UEs. This could help determine a cumulative effect of an AI/ML action to the network performance. In this case, instead of deciding handover actions based on individual UEs, an offloading plan may enable a source gNB (i.e. source cell) to offload all UEs meeting certain criteria to a neighbor gNB (i.e. respective target cell). [0040], discloses the mechanism for offloading plan preparation may take place within the source node such as, for example, within the gNB or gNB-CU. According to some example embodiments, the mechanism may be triggered when UE measurements have been collected at the source node to identify candidate target nodes (i.e. group of target cells) for the offloading. [0043]-[0045], discloses As illustrated in FIG. 2, at 215, gNB-CU2 may request from a neighbor gNB-CU1, an expected (predicted) cost (i.e. respective results of application of an object formulation) according to the same metric of the request transmitted at 205 that the identified set of UEs (i.e. including specified UE) will incur if offloaded at the neighboring gNB (i.e., gNB-CU1). The cost of an offloading plan to different neighbors may be considered (i.e. respective combinations), and the neighbor with the minimum cost (least cost) may be selected.
wherein a communication network comprises the source cell and the group of target cells; and [0040], discloses the mechanism for offloading plan preparation may take place within the source node such as, for example, within the gNB or gNB-CU. According to some example embodiments, the mechanism may be triggered when UE measurements have been collected at the source node (i.e. source cell) to identify candidate target nodes (i.e. group of target cells) for the offloading
based on the respective results of the application of the objective formulation, facilitating, by the system, user equipment association that defines an action for a network traffic load balancing process that transfers network traffic of the specified user equipment from the source cell to a target cell of the group of target cells. ([0044], discloses At 230, if the predicted cost is less than the cost that the UEs cost to the requesting node (i.e. based on the respective results of the application of the objective formulation), then the latter may, at 235, initiate a handover (i.e. user equipment association that defines an action for a network traffic load balancing process) of the offloading plan to the neighboring gNB-CU1. However, if the predicted cost is higher, then the requesting node may request another candidate gNB to obtain the expected cost of an offloading plan to it. The cost of an offloading plan to different neighbors may be considered, and the neighbor with the minimum cost (least cost) may be selected.)
wherein the determining of the respective results of application of the objective formulation comprises: based on the user equipment association, determining a first result of a minimization formulation that minimizes an average energy consumption of the communication network, as compared to a currently measured average energy consumption; and ([0036], discloses The criteria may depend on a cost or reward/gain that the offloading action will incur to the involved nodes. In general, the objective is to reduce the “cost” or maximize the “reward/gain”. A given use case may focus on either of it. For example, in energy saving, the cost is the amount of additional throughout that the offloaded UE cause to the target node, while the reward/gain is the maximization of the energy efficiency (i.e. minimize an average energy consumption) for a given number of UEs that are served. [0038], further discloses Another example of energy saving rewards may include maximizing the data volume or minimizing the energy consumption that can be considered as rewards. [0057], further discloses, if for one or more UEs, a neighboring gNB (e.g., gNB-CU) responds with an expected/predicted cost (i.e. result of minimization formulation) that is less than the current cost (i.e. current measured), then the gNB may add this UE (and possibly other UEs) to the offloading plan for the given neighbor gNB)
determining a second result of a maximization formulation that maximizes a carried traffic metric of the communication network, as compared to a currently measured carried traffic metric during the facilitating the user equipment association. ([0036], further discloses Similarly, for load balancing use cases, the cost is the amount of UEs served by each cell, and the reward/gain is the maximization of aggregated cell throughput (i.e. maximize a carried traffic metric). [0038], further discloses Another example of energy saving rewards may include maximizing the data volume or minimizing the energy consumption that can be considered as rewards. [0057], further discloses, if for one or more UEs, a neighboring gNB (e.g., gNB-CU) responds with an expected/predicted cost (i.e. result of maximization formulation) that is less than the current cost (i.e. current measured), then the gNB may add this UE (and possibly other UEs) to the offloading plan for the given neighbor gNB)
Alwar teaches performing offloading based on a minimization of energy consumption (i.e. first result) or maximization of throughput (i.e. second result), but does not teach facilitating user equipment association that defines an action for a network traffic load balancing process based on the respective results of the application of the objective formulation, wherein the respective results comprise the first result and the second result.
However, optimizing network performance based on multiple factors is well known in the art. For example, in a similar field of endeavor, Lord discloses in [0052], discloses Cloud-based RRM for Wi-Fi networks provides interference management and dynamically optimized reuse of spectrum to enhance Wi-Fi capacity, coverage, and overall throughput (i.e. maximize traffic metric). It allows an operator or enterprise to ensure reliability and performance predictability, such that the Wi-Fi network achieves carrier-grade performance with low probability of outage. Energy-consumption minimization (i.e. minimize energy consumption), potentially based on load, and outage probability minimization can also be incorporated into the algorithm. [0058], discloses The set of network optimization goals may be represented by an objective function or a cost function in an optimization problem. An optimized Wi-Fi parameter resulting from the search is a feasible solution or optimal solution that minimizes (or maximizes) the objective function subject to different constraints. Since multiple types of Wi-Fi parameters may be adjusted simultaneously during a search, different techniques to combat interference, increase throughput, or maximize coverage may be leveraged at the same time (i.e. optimizing the network based on multiple results).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar to include the above limitations as suggested by Lord in order to improve network performance as indicated in [0052] of Lord.
Regarding Claim 9, Alwar/Lord teaches The method of claim 1, further comprising:
Alwar/Lord further teaches prior to the determining of the respective results of application of the objective formulation and based on a traffic class of the specified user equipment, applying, by the system, a weighted value in the objective formulation for the specified user equipment, wherein the weighted value defines a prioritization assigned to the specified user equipment. (Alwar, [0050], discloses According to certain example embodiments, each gNB-DU may respond with a list of UEs corresponding to a handover candidate UE list, and may identify the UEs that are the most expensive according to the cost metric. In certain example embodiments, these identified UEs may represent the candidate UEs for offloading. The list may be an ordered list according to a priority with respect to the cost, namely the most expensive UEs are listed first. [0052], discloses the load balancing cost corresponding to the class of UEs may correspond to the (predicted) amount of traffic or (predicted) load at a gNB (source or target). In particular, the UEs with a lot of traffic may be classified as contributing more (i.e. weighted value defining a prioritization) to the load balancing cost than other UEs. Lord, [0059], discloses The cost function may be a weighted combination of throughput or potential throughput, outage probability, delay, "network" cost or backhaul cost, spectrum cost, infrastructure cost, and the like. Each element of the cost function may be weighted based on the element, the user, and/or the application priority) Examiner maintains same motivation to combine as indicated in claim 1 above.
Regarding Claim 10, Alwar/Lord teaches The method of claim 9, wherein a Lord further teaches weighted combination of quality of service parameters serves as a constraint within the objective formulation. ([0059], discloses The cost function may be a weighted combination of throughput or potential throughput, outage probability, delay, "network" cost or backhaul cost, spectrum cost, infrastructure cost, and the like) Examiner maintains same motivation to combine as indicated in claim 1 above.
Regarding Claim 11, Alwar/Lord teaches The method of claim 1, wherein Alwar further teaches the source cell and the group of target cells are configured to operate according to a fifth generation radio network communication protocol. ([0069], discloses, the method of FIG. 7 may be performed by a network entity, or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For instance, in an example embodiment, the method of FIG. 7 may be performed by a network, network node, or gNB similar to one of apparatuses 10 or 20 illustrated in FIG. 8)
Regarding Claim 12, Alwar teaches A system, comprising:
A processor and memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, ([0004], discloses an apparatus including at least one processor and memory for determining the need for offloading at the apparatus) comprising:
performing a network traffic load balancing procedure that moves network traffic of a user equipment from a source cell to a specified target cell within a communication network, wherein the performing comprises ([0047], discloses a mechanism for offloading plan preparation, and a mechanism to trigger offloading plan exchange between nodes. The source node may decide that there is a need for an AI/ML action (e.g., related to AI/ML load balancing or AI/ML energy saving). Once this is decided, the source node may prepare an offloading plan. According to some example embodiments, this may involve a prediction of an expected cost that a set of UEs will incur to the gNB where they will be offloaded, and a comparison of this cost to the cost of those UEs in the current node. The source node may also perform a bulk resource reservation prediction (between two gNBs or two gNB-CUs over Xn interface or between a gNB-CU and a gNB-DU, over F1 interface), and finalize the candidate UE list and target cell. Once finalized, the source node may trigger a legacy handover procedure for the candidate cells (i.e. network traffic load balancing procedure))
determining, respective results of application of an objective formulation to respective combinations of the user equipment of a source cell and respective target cells of a group of target cells of the communication network, ([0036], discloses In some cases, it may be preferable if a source node prepares a handover to another neighbour cell over a set of UEs. This could help determine a cumulative effect of an AI/ML action to the network performance. In this case, instead of deciding handover actions based on individual UEs, an offloading plan may enable a source gNB (i.e. source cell) to offload all UEs meeting certain criteria to a neighbor gNB (i.e. respective target cell). [0040], discloses the mechanism for offloading plan preparation may take place within the source node such as, for example, within the gNB or gNB-CU. According to some example embodiments, the mechanism may be triggered when UE measurements have been collected at the source node to identify candidate target nodes (i.e. group of target cells) for the offloading. [0043]-[0045], discloses As illustrated in FIG. 2, at 215, gNB-CU2 may request from a neighbor gNB-CU1, an expected (predicted) cost (i.e. respective results of application of an object formulation) according to the same metric of the request transmitted at 205 that the identified set of UEs (i.e. including UE) will incur if offloaded at the neighboring gNB (i.e., gNB-CU1). The cost of an offloading plan to different neighbors may be considered (i.e. respective combinations), and the neighbor with the minimum cost (least cost) may be selected.
based on the respective results and a determination that the specified target cell satisfies an energy consumption condition, transferring the network traffic of the user equipment from the source cell to the specified target cells ([0044], discloses At 230, if the predicted cost (i.e. respective result) is less than the cost that the UEs cost to the requesting node (i.e. satisfies energy consumption condition), then the latter may, at 235, initiate a handover (i.e. transfer network traffic) of the offloading plan to the neighboring gNB-CU1. However, if the predicted cost is higher, then the requesting node may request another candidate gNB to obtain the expected cost of an offloading plan to it. The cost of an offloading plan to different neighbors may be considered, and the neighbor with the minimum cost (least cost) may be selected)
Alwar teaches performing offloading based on a minimization of energy consumption (i.e. first result) or maximization of throughput (i.e. second result), but does not teach facilitating user equipment association that defines an action for a network traffic load balancing process based on the respective results of the application of the objective formulation, wherein the respective results comprise the first result and the second result.
However, optimizing network performance based on multiple factors is well known in the art. For example, in a similar field of endeavor, Lord discloses in [0052], discloses Cloud-based RRM for Wi-Fi networks provides interference management and dynamically optimized reuse of spectrum to enhance Wi-Fi capacity, coverage, and overall throughput (i.e. maximize traffic metric). It allows an operator or enterprise to ensure reliability and performance predictability, such that the Wi-Fi network achieves carrier-grade performance with low probability of outage. Energy-consumption minimization (i.e. minimize energy consumption), potentially based on load, and outage probability minimization can also be incorporated into the algorithm. [0058], discloses The set of network optimization goals may be represented by an objective function or a cost function in an optimization problem. An optimized Wi-Fi parameter resulting from the search is a feasible solution or optimal solution that minimizes (or maximizes) the objective function subject to different constraints. Since multiple types of Wi-Fi parameters may be adjusted simultaneously during a search, different techniques to combat interference, increase throughput, or maximize coverage may be leveraged at the same time (i.e. optimizing the network based on multiple results).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar to include the above limitations as suggested by Lord in order to improve network performance as indicated in [0052] of Lord.
Regarding Claim 15, Alwar/Lord teaches The system of claim 12, wherein Lord further teaches the objective formulation facilitates a tradeoff between user equipment quality of service and an energy consumption of the communication network. ([0037], discloses a session handoff module 210 for providing network-initiated handoffs between heterogeneous networks (e.g., from LTE to cognitive radio or vice versa) which takes into consideration the overall network performance and other factors such as cost, energy consumption, and user preferences (i.e. tradeoff)) Examiner maintains same motivation to combine as indicated in claim 12 above
Regarding Claim 16, Alwar/Lord teaches The system of claim 15, wherein Alwar further teaches the user equipment quality of service is defined for respective user equipment classes of user equipment within the communication network. ([0054], discloses the resource needs may be with respect to the UEs' need of GBR resources, and/or UEs with non-GBR resources. In some example embodiments, the groups may be categorized by group 1 (UE list, GBR-5 Mps), Group 2 (UE list, GBR-10 Mbps), Group 3 (UE list, Non-GBR), etc)
Regarding Claim 18, Alwar teaches A non-transitory machine-readable medium, comprising executable instructs that, when executed by a processor of network equipment, facilitate performance of operations, wherein the operations comprise: ([0004], discloses an apparatus including at least one processor and memory for determining the need for offloading at the apparatus)
Determining respective results of application of an objective formulation to respective combinations of a user equipment connected to a communication network via a source cell and respective target cells of a group of target cells, ([0036], discloses In some cases, it may be preferable if a source node prepares a handover to another neighbour cell over a set of UEs. This could help determine a cumulative effect of an AI/ML action to the network performance. In this case, instead of deciding handover actions based on individual UEs, an offloading plan may enable a source gNB (i.e. source cell) to offload all UEs meeting certain criteria to a neighbor gNB (i.e. respective target cell). [0040], discloses the mechanism for offloading plan preparation may take place within the source node such as, for example, within the gNB or gNB-CU. According to some example embodiments, the mechanism may be triggered when UE measurements have been collected at the source node to identify candidate target nodes (i.e. group of target cells) for the offloading. [0043]-[0045], discloses As illustrated in FIG. 2, at 215, gNB-CU2 may request from a neighbor gNB-CU1, an expected (predicted) cost (i.e. respective results of application of an object formulation) according to the same metric of the request transmitted at 205 that the identified set of UEs (i.e. including specified UE) will incur if offloaded at the neighboring gNB (i.e., gNB-CU1). The cost of an offloading plan to different neighbors may be considered (i.e. respective combinations), and the neighbor with the minimum cost (least cost) may be selected.
wherein the communication network comprises the source cell and the group of target cells; and [0040], discloses the mechanism for offloading plan preparation may take place within the source node such as, for example, within the gNB or gNB-CU. According to some example embodiments, the mechanism may be triggered when UE measurements have been collected at the source node (i.e. source cell) to identify candidate target nodes (i.e. group of target cells) for the offloading
based on the respective results of the application of the objective formulation, implementing a network traffic load balancing process that transfers network traffic of the specified user equipment from the source cell to a target cell of the group of target cells. ([0044], discloses At 230, if the predicted cost is less than the cost that the UEs cost to the requesting node (i.e. based on the respective results of the application of the objective formulation), then the latter may, at 235, initiate a handover (i.e. user equipment association that defines an action for a network traffic load balancing process) of the offloading plan to the neighboring gNB-CU1. However, if the predicted cost is higher, then the requesting node may request another candidate gNB to obtain the expected cost of an offloading plan to it. The cost of an offloading plan to different neighbors may be considered, and the neighbor with the minimum cost (least cost) may be selected.)
Alwar teaches performing offloading based on a minimization of energy consumption (i.e. first result) or maximization of throughput (i.e. second result), but does not teach facilitating user equipment association that defines an action for a network traffic load balancing process based on the respective results of the application of the objective formulation, wherein the respective results comprise the first result and the second result.
However, optimizing network performance based on multiple factors is well known in the art. For example, in a similar field of endeavor, Lord discloses in [0052], discloses Cloud-based RRM for Wi-Fi networks provides interference management and dynamically optimized reuse of spectrum to enhance Wi-Fi capacity, coverage, and overall throughput (i.e. maximize traffic metric). It allows an operator or enterprise to ensure reliability and performance predictability, such that the Wi-Fi network achieves carrier-grade performance with low probability of outage. Energy-consumption minimization (i.e. minimize energy consumption), potentially based on load, and outage probability minimization can also be incorporated into the algorithm. [0058], discloses The set of network optimization goals may be represented by an objective function or a cost function in an optimization problem. An optimized Wi-Fi parameter resulting from the search is a feasible solution or optimal solution that minimizes (or maximizes) the objective function subject to different constraints. Since multiple types of Wi-Fi parameters may be adjusted simultaneously during a search, different techniques to combat interference, increase throughput, or maximize coverage may be leveraged at the same time (i.e. optimizing the network based on multiple results).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar to include the above limitations as suggested by Lord in order to improve network performance as indicated in [0052] of Lord.
Regarding Claim 20, Alwar/Lord teaches The non-transitory machine readable medium of claim 18, wherein
Lord further teaches the objective formulation is based on an optimization function that facilitates a tradeoff between network energy savings and maintain a user equipment quality of service at a defined level, and ([0037], discloses a session handoff module 210 for providing network-initiated handoffs between heterogeneous networks (e.g., from LTE to cognitive radio or vice versa) which takes into consideration the overall network performance and other factors such as cost, energy consumption, and user preferences (i.e. tradeoff))
Alwar further teaches wherein the user equipment quality of service is defined for respective user equipment classes of user equipment within the communication network. ([0054], discloses the resource needs may be with respect to the UEs' need of GBR resources, and/or UEs with non-GBR resources. In some example embodiments, the groups may be categorized by group 1 (UE list, GBR-5 Mps), Group 2 (UE list, GBR-10 Mbps), Group 3 (UE list, Non-GBR), etc)
Examiner maintains same motivation to combine as indicated in claim 18 above.
Regarding Claim 21, Alwar/Lord teaches The system of claim 12, further comprising:
Alwar/Lord further teaches prior to the determining of the respective results of application of the objective formulation and based on a traffic class of the specified user equipment, applying, a weighted value in the objective formulation for the specified user equipment, wherein the weighted value defines a prioritization assigned to the specified user equipment, and wherein a weighted combination of quality of service parameters serves as a constraint within the objective formulation. (Alwar, [0050], discloses According to certain example embodiments, each gNB-DU may respond with a list of UEs corresponding to a handover candidate UE list, and may identify the UEs that are the most expensive according to the cost metric. In certain example embodiments, these identified UEs may represent the candidate UEs for offloading. The list may be an ordered list according to a priority with respect to the cost, namely the most expensive UEs are listed first. [0052], discloses the load balancing cost corresponding to the class of UEs may correspond to the (predicted) amount of traffic or (predicted) load at a gNB (source or target). In particular, the UEs with a lot of traffic may be classified as contributing more (i.e. weighted value defining a prioritization) to the load balancing cost than other UEs. Lord, [0059], discloses The cost function may be a weighted combination of throughput or potential throughput, outage probability, delay, "network" cost or backhaul cost, spectrum cost, infrastructure cost, and the like. Each element of the cost function may be weighted based on the element, the user, and/or the application priority) Examiner maintains same motivation to combine as indicated in claim 12 above.
Claim(s) 3-4, 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alwar/Lord in view of US 2017/0026888 A1 to Kwan et al. (hereinafter “Kwan”)
Regarding Claim 3, Alwar/Lord teaches The method of claim 2, wherein the determining of the first result comprises:
Alwar teaches applying a constraint to the minimization formulation, guaranteed bit rate traffic ([0053], discloses Here, the source node may prepare an offloading plan including, for example, a specific subset of UEs and total amount of resources needed at the target cell. Additionally, the source node may trigger a group preparation procedure to the target node. For instance, the group preparation procedure includes sending to the target node, the UE list, and the total GBR/non-GBR resource needs (i.e. GBR constraint), and the duration for which the resources shall not be allocated for other purposes (L3 mobility, etc.)) but Alwar/Lord does not explicitly teach applying a constraint to the minimization formulation, wherein the constraint facilitates maintaining cells, determined to be necessary for network guaranteed bit rate traffic, in an active state.
However, in a similar field of endeavor, Kwan discloses in [0018], calculating predicted load changes for a target radio access point for one or more potential user equipment (UE) handovers from each of a plurality of source radio access points for a radio access network based, at least in part, on application of current measurement data to a trained statistical model representing load changes for the radio access network; solving an optimization problem associated with energy savings for the radio access network to determine a set of one or more source radio access points that can be powered off to maximize energy savings or minimize energy consumption for the radio access. [0085], further discloses For example, if GBR is deemed critical (i.e. necessary) in defining the load change for one or more radio access points for one or more potential handover events, the multiple linear regression model provided by Equation 14 can be modified in various embodiments to account for the change in the load model (e.g., update Equation 11 to include GBR information) by adjusting the intermediate variable x.sub.2,n, as shown in Equation 19. [0121], further discloses In various embodiments, the method for determining a maximum energy savings for a given RAN (e.g., RAN 416) can generally provide for determining a set of cell radios that can be turned off and have the UE connected thereto handed over to another cell radio without violating the load constraint of the other cell radio (i.e. maintaining cells in an active state necessary for GBR traffic).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar/Lord to include the above limitations as suggested by Kwan, thereby maximizing energy savings for the RAN as indicated in [0121] of Kwan.
Regarding Claim 4, Alwar/Lord/Kwan teaches The method of claim 3, wherein Kwan further teaches the applying of the constraint comprises maintaining a defined guaranteed bit rate level for instantaneous minimization formulation bit rate traffic. ([0085], further discloses For example, if GBR is deemed critical in defining the load change for one or more radio access points for one or more potential handover events, the multiple linear regression model provided by Equation 14 can be modified in various embodiments to account for the change in the load model (e.g., update Equation 11 to include GBR information) by adjusting the intermediate variable x.sub.2,n, as shown in Equation 19. [0066], discloses a user connected to radio access point i is transmitting using an active bearer with a guaranteed bit rate (GBR). Examiner notes that any traffic that flows in a GBR bearer is analogous to “instantaneous minimization formulation bit rate traffic”) Examiner maintains same motivation to combine as indicated in Claim 3 above.
Regarding Claim 17, Alwar/Lord teaches The system of claim 12, wherein the operations further comprise:
Alwar teaches network guaranteed bit rate traffic ([0053]-[0054), but Alwar/Lord does not explicitly teach determining network guaranteed bit rate traffic is dependent on the source cell being in an active state; and preventing a change in state of the source cell from the active state to an inactive state, wherein the preventing comprises applying a constraint to the objective formulation.
However, in a similar field of endeavor, Kwan discloses in [0018], calculating predicted load changes for a target radio access point for one or more potential user equipment (UE) handovers from each of a plurality of source radio access points for a radio access network based, at least in part, on application of current measurement data to a trained statistical model representing load changes for the radio access network; solving an optimization problem associated with energy savings for the radio access network to determine a set of one or more source radio access points that can be powered off to maximize energy savings or minimize energy consumption for the radio access. [0085], further discloses For example, if GBR is deemed critical (i.e. determining network GBR is dependent on source cell being in an active state) in defining the load change for one or more radio access points for one or more potential handover events, the multiple linear regression model provided by Equation 14 can be modified in various embodiments to account for the change in the load model (e.g., update Equation 11 to include GBR information) by adjusting the intermediate variable x.sub.2,n, as shown in Equation 19 (i.e. applying a constraint). [0121], further discloses In various embodiments, the method for determining a maximum energy savings for a given RAN (e.g., RAN 416) can generally provide for determining a set of cell radios that can be turned off (i.e. including preventing a change in state) and have the UE connected thereto handed over to another cell radio without violating the load constraint of the other cell radio (i.e. maintaining cells in an active state necessary for GBR traffic).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar/Lord to include the above limitations as suggested by Kwan, thereby maximizing energy savings for the RAN as indicated in [0121] of Kwan.
Claim(s) 5-8, 13, 14, 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alwar/Lord in view of US 2024/0023028 A1 to Nikopour et al. (hereinafter “Nikopour”)
Regarding Claim 5, Alwar/Lord teaches The method of claim 1, further comprising:
Alwar discloses in [0031]-[0034], and [0063]-[0064], the AI/ML model may be trained to maximize the spectral efficiency for UEs and energy efficiency for cell(s), or to minimize the load of a given cell subject to UE performance constraints and minimize the energy consumption of cells but Alwar/Lord does not explicitly teach prior to the determining of the respective results of the application of the objective formulation, transforming, by the system, details of the communication network into a graphical representation; and based on the graphical representation and based on real-time conditions, generating, by the system, a policy, wherein the policy facilitates a reduction in an amount of energy consumed by the communication network, as compared to a current energy consumption level.
However, in a similar field of endeavor, Nikopour discloses in [0017], technologies and techniques for wireless network energy saving (NES) using graph neural networks (GNNs). [0121], discloses Process 800 begins at operation 801 where the compute node identifies a set of network nodes in a wireless network and generates a graph of the wireless network where each network node in the network is represented as a vertex and connections between the network nodes are represented as edges (see e.g., FIGS. 3-4). (i.e. transforming details of the communication system into a graphical representation). At operation 802, the compute node inputs the graph to a GNN, which outputs node embeddings and/or edge embeddings. At operation 803, the compute node inputs the embeddings to an FCNN, which predicts optimized energy consumption of individual nodes and/or the wireless network as a whole. At operation 804, the compute node generates NES parameters based on the predictions from the FCNN, wherein the NES parameters are used by individual network nodes to adjust one or more control parameters (i.e. generating a policy for reducing energy consumed). [0018], discloses The graph may also include a set of embeddings or node features for each node, which may be based on collected network-related measurements, performance metrics, telemetry data, and/or other features and/or data (i.e. real-time conditions).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar/Lord to include the above limitations as suggested by Nikopour, thereby providing a data-driven network energy efficiency optimization as indicated in [0019]-[0020] of Nikopour.
Regarding Claim 6, Alwar/Lord/Nikopour teaches The method of claim 5, further comprising:
Nikopour teaches prior to the generating of the policy and based on the graphical representation, training, by the system, a model to a defined confidence level. ([0102]-[0104], discloses ML model training. [0090], discloses Message passing may occur iteratively, where in each iteration, one or more nodes send messages to their neighboring nodes, and these messages are aggregated to update the node embeddings. The message passing may be performed in an iterative fashion where the aforementioned operations are repeated for a number of iterations/epochs or until convergence (i.e. defined confidence level) to allow nodes to gather information from their neighbors and refine their representations.) Examiner maintains same motivation to combine as indicated in Claim 5 above.
Regarding Claim 7, Alwar/Lord/Nikopour teaches The method of claim 6, wherein Nikopour further teaches the model is a graph neural network model. ([0017], discloses techniques for wireless network energy saving (NES) using graph neural networks (GNNs)) Examiner maintains same motivation to combine as indicated in Claim 5 above.
Regarding Claim 8, Alwar/Lord/Nikopour teaches The method of claim 7, wherein Nikopour further teaches the graph neural network model is a message passing graph neural network model. ([0017], discloses GNNs are a framework to capture the dependence of nodes in graphs via message passing between the nodes) Examiner maintains same motivation to combine as indicated in Claim 5 above.
Regarding Claim 13, Alwar/Lord teaches The system of claim 2, further comprising:
Alwar/Lord does not explicitly teach prior to the generating of the policy and based on the graphical representation, training a first model to a defined confidence level.
However, in a similar field of endeavor, Nikopour discloses in [0017], technologies and techniques for wireless network energy saving (NES) using graph neural networks (GNNs). [0102]-[0104], discloses ML model training. [0090], discloses Message passing may occur iteratively, where in each iteration, one or more nodes send messages to their neighboring nodes, and these messages are aggregated to update the node embeddings. The message passing may be performed in an iterative fashion where the aforementioned operations are repeated for a number of iterations/epochs or until convergence (i.e. defined confidence level) to allow nodes to gather information from their neighbors and refine their representations.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar/Lord to include the above limitations as suggested by Nikopour, thereby providing a data-driven network energy efficiency optimization as indicated in [0019]-[0020] of Nikopour.
Regarding Claim 14, Alwar/Lord/Nikopour teaches The method of claim 13, wherein Nikopour further teaches the model is a graph neural network model. ([0017], discloses techniques for wireless network energy saving (NES) using graph neural networks (GNNs)) Examiner maintains same motivation to combine as indicated in Claim 13 above.
Regarding Claim 19, Alwar/Lord teaches The non-transitory machine readable medium of claim 18, wherein the operations further comprise:
Alwar/Lord does not explicitly teach based on a graphical representation of the communication network, using a model trained to a defined confidence level, wherein the model is a graph neural network model.
However, in a similar field of endeavor, Nikopour discloses in [0017], technologies and techniques for wireless network energy saving (NES) using graph neural networks (GNNs). [0121], discloses Process 800 begins at operation 801 where the compute node identifies a set of network nodes in a wireless network and generates a graph of the wireless network where each network node in the network is represented as a vertex and connections between the network nodes are represented as edges (see e.g., FIGS. 3-4). (i.e a graphical representation). At operation 802, the compute node inputs the graph to a GNN (i.e. model), which outputs node embeddings and/or edge embeddings. are used by individual network nodes to adjust one or more control parameters). [0102]-[0104], discloses ML model training. [0090], discloses Message passing may occur iteratively, where in each iteration, one or more nodes send messages to their neighboring nodes, and these messages are aggregated to update the node embeddings. The message passing may be performed in an iterative fashion where the aforementioned operations are repeated for a number of iterations/epochs or until convergence (i.e. defined confidence level) to allow nodes to gather information from their neighbors and refine their representations.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Alwar/Lord to include the above limitations as suggested by Nikopour, thereby providing a data-driven network energy efficiency optimization as indicated in [0019]-[0020] of Nikopour.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JENKEY VAN whose telephone number is (571)270-7160. The examiner can normally be reached Monday - Friday 9am - 5pm.
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, Chirag Shah can be reached at (571)272-3144. 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.
/JENKEY VAN/ Primary Examiner, Art Unit 2477
Prosecution Insights