Facilitating cell and carrier switch off for energy awareness in advanced communication networks

Patent metadata

Field	Value
Publication number	US-12574840-B2
Application number	US-202318337594-A
Country	US
Kind code	B2
Filing date	Jun 20, 2023
Priority date	Jun 20, 2023
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

Facilitating cell and carrier switch off for energy awareness in advanced communication networks is provided herein. A method includes determining a first result of a utility function associated with a first configuration of a set of carriers that service a group of user equipment in a communication network. The first configuration is based on respective activation states of carriers of the set of carriers. The method also includes, based on respective traffic patterns of user equipment of the group of user equipment, evaluating respective results of the utility function for respective configurations of a group of configurations, other than the first configuration, for the set of carriers. Further, the method includes selecting a second configuration from the group of configurations based on a second result of the utility function for the second configuration being determined to be a higher value than a value of the first result.

First claim

What is claimed is:

1 . A method, comprising:
determining, by a system comprising at least one processor, a first result of a utility function associated with a first configuration of a set of carriers that service a group of user equipment in a communication network, wherein the first configuration is based on respective activation states of carriers of the set of carriers, and wherein the utility function is based on a power consumption of the set of carriers and a quality of service target for the group of user equipment; based on respective traffic patterns of user equipment of the group of user equipment, evaluating, by the system, respective results of the utility function for respective configurations of a group of configurations, other than the first configuration, for the set of carriers; and selecting, by the system, a second configuration from the group of configurations based on a second result of the utility function for the second configuration being determined to be a higher value than a value of the first result, wherein the determining comprises deriving the power consumption of the set of carriers based on a ratio of a first amount that represents a number of carriers in a fully active state and a second amount that represents a total number of carriers in the communication network, and wherein the total number of carriers comprises a first quantity of carriers in an active mode and a second quantity of carriers in a sleep mode.

2 . The method of claim 1 , wherein the evaluating the respective results of the utility function for the respective configurations of the group of configurations comprises:
employing, by the system, artificial intelligence to simulate toggling of a state of at least one carrier of the set of carriers between an active state and an inactive state.

3 . The method of claim 1 , wherein the evaluating comprises using a metric based on a long-term performance expectation as an objective of the utility function.

4 . The method of claim 1 , wherein the evaluating comprises:
determining the first result and the second result based on the utility function being a combination of respective metrics representative of the power consumption, a latency, and a performance of the communication network.

5 . The method of claim 1 , further comprising:
aggregating, by the system, respective weights of local models, resulting in a centralized model, wherein the local models are associated with energy saving groups comprising network equipment; and updating, by the system, a global model based on the centralized model.

6 . The method of claim 5 , wherein the local models are federated learning models.

7 . The method of claim 5 , wherein the local models are transfer learning models.

8 . The method of claim 5 , wherein the local models are federated learning models and transfer learning models.

9 . The method of claim 1 , wherein the system is implemented within a disaggregated architecture that comprises central units, distributed units, and a near-real-time-radio access network intelligent controller.

10 . The method of claim 1 , wherein the communication network is configured to operate according to a new radio network communication protocol.

11 . A system, comprising:
at least one processor; and at least one memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
based on respective traffic patterns of user equipment of a group of user equipment, evaluating respective results of a utility function for respective configurations of a group of configurations of a set of carriers that service the group of user equipment in a communication network, wherein the utility function is based on a power consumption of the set of carriers and a quality of service target for the group of user equipment; and
based on a result of the utility function for one configuration of the group of configurations being determined to have a first value that is more than a second value of a current result of the utility function, implementing the one configuration in the communication network, wherein the group of configurations comprise different combinations of active and inactive carriers of the set of carriers, and wherein the evaluating the respective results comprises:
initiating a local model with initial parameters via transfer learning; and
training the local model with an aggregation of global model parameters via federated learning.

12 . The system of claim 11 , wherein the operations further comprise:
receiving feedback data associated with the implementing of the one configuration; and retraining the local model based, at least in part, on the feedback data.

13 . The system of claim 11 , wherein the evaluating comprises using a metric based on a long-term performance expectation as an objective of the utility function.

14 . The system of claim 11 , wherein the respective results of the utility function are based on a combination of respective metrics representative of the power consumption, a latency, and a performance of the communication network for the respective configurations.

15 . The system of claim 11 , wherein the system is deployed in a disaggregated architecture of network equipment.

16 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by at least one processor of network equipment, facilitate performance of operations, comprising:
determining a first result of a utility function associated with a first configuration of a set of carriers that service a group of user equipment in a communication network, wherein the first configuration is based on respective activation states of carriers of the set of carriers, and wherein the utility function is based on a power consumption of the set of carriers and a quality of service target for the group of user equipment; based on respective traffic patterns of user equipment of the group of user equipment, evaluating respective results of the utility function for respective configurations of a group of configurations, other than the first configuration; and selecting a second configuration from the group of configurations based on a second result of the utility function for the second configuration being determined to be increased as compared to the first result, wherein the determining comprises deriving the power consumption of the set of carriers based on a ratio of a first amount that represents a number of carriers in a fully active state and a second amount that represents a total number of carriers in the communication network, and wherein the total number of carriers comprises a first quantity of carriers in an active mode and a second quantity of carriers in a sleep mode.

17 . The non-transitory machine-readable medium of claim 16 , wherein the evaluating the respective results comprises:
initiating a local model with initial parameters via transfer learning; and training the local model with an aggregation of global model parameters via federated learning.

18 . The non-transitory machine-readable medium of claim 16 , wherein the evaluating comprises:
determining the first result and the second result based on the utility function being a combination of respective metrics representative of the power consumption, a latency, and a performance of the communication network.

19 . The non-transitory machine-readable medium of claim 16 , wherein the operations further comprise:
aggregating r

Assignees

• Dell Products Lp

Inventors

• Hashmi Umair Sajid
• Poitau Gwenael
• Mitra Jeebak

Classifications

• H04L41/0803

  Configuration setting · CPC title

• G06N3/098

  Distributed learning, e.g. federated learning · CPC title

• H04W52/0203 Primary

  in the radio access network or backbone network of wireless communication networks · CPC title

• G06N3/096

  Transfer learning · CPC title

• Y02D30/70

  in wireless communication networks · CPC title