Graph-based systems and methods for controlling power switching of components

Patent metadata

Field	Value
Publication number	US-2023403652-A1
Application number	US-202018027482-A
Country	US
Kind code	A1
Filing date	Sep 22, 2020
Priority date	Sep 22, 2020
Publication date	Dec 14, 2023
Grant date	—

Abstract

A computer implemented method of managing power control in a communication system includes generating a graph representation of interdependencies of components of the communication system, wherein the graph representation includes graph nodes corresponding to the components of the communication system and edges between pairs of graph nodes representing dependency relationships between the pairs of nodes. The method generates edge weights for the edges of the graph representation that correspond to the relative importance of the dependency relationship represented by the edge weight, and generates a policy for managing power control by determining an order for switching the components of the communication system on or off based on the edge weights.

First claim

1 . A computer implemented method for managing power control in a communication system, comprising:
generating a graph representation of interdependencies of components of the communication system, wherein the graph representation comprises graph nodes corresponding to the components of the communication system and edges between pairs of graph nodes representing dependency relationships between the pairs of graph nodes; generating edge weights for the edges of the graph representation, the edge weight of an edge corresponding to a relative importance of the dependency relationship represented by the edge; and generating a policy for managing power control by determining an order for switching components represented by the graph nodes on or off based on the edge weights.

2 . The method of claim 1 , wherein determining the order for switching components represented by the graph nodes on or off comprises:
for each graph node in the graph representation, generating a sum of edge weights of edges connected to the graph node; selecting graph nodes with a smallest sum of edge weights; removing selected graph nodes from the graph representation; and updating the policy for managing power control with the selected graph nodes.

3 . The method of claim 1 ,
wherein determining the order for switching components represented by the graph nodes on or off comprises: repeating steps of: for each graph node in the graph representation, generating a sum of edge weights of edges connected to the graph node; and selecting graph nodes with a smallest sum of edge weights; removing selected graph nodes from the graph representation; and updating the policy for managing power control with the selected graph nodes; until all nodes have been removed from the graph.

4 . The method of claim 1 , wherein the edge weights are generated based on one or more of:
on-to-off switching duration, off-to-on switching duration, power consumption during on-to-off transition, power consumption during off-to-on transition, power consumption during active state, network element priority and physical location.

5 . The method of claim 1 , wherein generating the edge weights comprises evaluating a cost function that minimizes an energy consumption metric.

6 . The method of claim 5 , wherein generating the edge weights comprises evaluating the cost function that minimizes the energy consumption metric while maintaining a quality of service, QoS, metric above a predetermined threshold.

7 . The method of claim 1 , wherein generating the edge weights comprises evaluating a cost function that maximizes a quality of service, QoS, metric.

8 . The method of claim 7 , wherein generating the edge weights comprises evaluating the cost function that maximizes the QoS metric while maintaining an energy consumption metric below a predetermined threshold.

9 . The method of claim 7 , wherein the QoS metric is based on one or more of:
a service level agreement, a number of active user devices in the communication system, a number of active connections in the communication system, a throughput in the communication system, a number of handovers in the communication system, a number of dropped calls in the communication system, and a number of dropped packets in the communication system.

10 . The method of claim 1 , wherein generating the edge weights comprises generating the edge weights using a reinforcement learning system that measures a reward and a system state in response to operation of a policy for managing power control and adjusts the edge weights in response to the reward the system state.

11 . The method of claim 10 , wherein the edge weights are selected based on maximizing a sum of the rewards received in response to operation of the policy for managing power control.

12 . The method of claim 10 , wherein the reward corresponds to an energy saving in the communication system or a Quality of Service, QoS, improvement of the communication system.

13 . The method of claim 1 , further comprising controlling the communication system in accordance with the policy for managing power control.

14 . The method of claim 13 , wherein controlling the communication system comprises switching components of the system on or off in accordance with the policy.

15 . The method of claim 1 , wherein the interdependencies comprise power switching interdependencies.

16 . The method of claim 1 , wherein the communication system comprises a wireless communication system.

17 . The method of claim 1 , wherein the components of the communication system comprise one or more communication equipment, base stations, base station components, cells, sites, switches, antennas, processors, and radios.

18 . A server, comprising:
a processing circuit; and a memory ( 255 ) coupled to the processing circuit and comprising computer readable program instructions that, when executed by the processing circuit, cause the server to; generate a graph representation of interdependencies of components of the communication system, wherein the graph representation comprises nodes corresponding to the components of the communication system and edges between pairs of nodes representing dependency relationships between the pairs of nodes; generate edge weights for the edges of the graph representation, each edge weight corresponding to a relative importance of the dependency relationship represented by the edge weight; and generate a policy for managing power control by determining the order for switching components represented by the graph nodes on or off based on the edge weights.

19 . (canceled)

20 . (canceled)

Assignees

• Ericsson Telefon Ab L M

Inventors

• Ickin Selim
• Gorbatov Oleg
• Lindström Daniel
• Bergkvist Adam
• Inam Rafia
• Eleftheriadis Lackis

Classifications

• H04W52/0274 Primary

  by switching on or off the equipment or parts thereof · CPC title

• H04W52/0264

  by selectively disabling software applications · CPC title

• H04W52/0254

  detecting a user operation or a tactile contact or a motion of the device · CPC title

• Y02D30/70

  in wireless communication networks · CPC title