Load balancing method and wireless communication system

Patent metadata

Field	Value
Publication number	US-12408077-B2
Application number	US-202318157661-A
Country	US
Kind code	B2
Filing date	Jan 20, 2023
Priority date	Jan 20, 2023
Publication date	Sep 2, 2025
Grant date	Sep 2, 2025

Abstract

A load balancing method of balancing computational workload in a wireless communication network is described. The wireless communication network includes at least two nodes being configured to communicate with each other. The at least two nodes include a first node and a second node. Further, a wireless communication network is described.

First claim

The invention claimed is:

1. A load balancing method of balancing computational workload in a wireless communication network, the wireless communication network includes at least two nodes being configured to communicate with each other, wherein the at least two nodes comprise a first node and a second node, the load balancing method comprising the steps of:
determining, by the first node, at least one first load parameter, wherein the at least one first load parameter is indicative of a computational workload of the first node;
determining, by the second node, at least one second load parameter, wherein the at least one second load parameter is indicative of a computational workload of the second node;
transmitting, by the first node, the at least one first load parameter to the second node; and
allocating, by at least the second node, a computational artificial intelligence (AI) task to at least one of the first node and the second node based on the at least one first load parameter and based on the at least one second load parameter.

2. The load balancing method of claim 1 , wherein the second load parameter is transmitted to the first node, and wherein the computational AI task is mutually allocated by the first node and the second node.

3. The load balancing method of claim 1 , wherein at least one of the first node and the second node is established as a base station.

4. The load balancing method of claim 1 , wherein at least one of the first node and the second node is established as user equipment (UE).

5. The load balancing method of claim 1 , wherein the computational AI task is a machine-learning inference task.

6. The load balancing method of claim 5 , wherein the machine-learning inference task relates to channel state information compression, beam management, or determination of a position.

7. The load balancing method of claim 1 , wherein the at least one first load parameter and the at least one second load parameter respectively comprise a computing headroom report, a power consumption report, a state of charge report, and/or a type of power supply.

8. The load balancing method of claim 1 , wherein the at least one first load parameter is determined and transmitted to the second node according to a predefined schedule.

9. The load balancing method of claim 1 , wherein transmission of the at least one first load parameter is initiated by the first node or by the second node.

10. The load balancing method of claim 1 , wherein transmission of the at least one first load parameter is initiated by the first node based on the at least one first load parameter, or by the second node based on the at least one second load parameter.

11. The load balancing method of claim 10 , wherein the at least one first load parameter is compared with at least one corresponding first threshold, and/or wherein the at least one second load parameter is compared with at least one corresponding second threshold.

12. The load balancing method of claim 1 , wherein the at least two nodes are configured to communicate at least one computation parameter to the communication network, respectively, wherein the at least one computation parameter is indicative of computational resources of the respective node, and wherein a coordinating node is selected from the at least two nodes based on the computation parameters of the at least two nodes.

13. The load balancing method of claim 12 , wherein a plurality of computational AI tasks is allocated to the at least two nodes by the coordinating node.

14. The load balancing method of claim 12 , wherein a new coordinating node is selected if the previous coordinating node disconnects from the wireless communication network.

15. The load balancing method of claim 12 , wherein a new coordinating node is selected if a new node connects to the wireless communication network, wherein the new node has more computational resources than the previous coordinating node.

16. The load balancing method of claim 12 , wherein the computation parameters are transmitted by a sidelink.

17. The load balancing method of claim 1 , wherein the first node and the second node are configured to communicate with each other via 4G and/or 5G New Radio.

18. A wireless communication system, comprising:
at least two nodes being configured to communicate with each other, wherein the at least two nodes comprise a first node and a second node,
the first node being configured to determine at least one first load parameter, wherein the at least one first load parameter is indicative of a computational workload of the first node;
the second node being configured to determine at least one second load parameter, wherein the at least one second load parameter is indicative of a computational workload of the second node;
the first node being configured to transmit the at least one first load parameter to the second node; and
the second node being configured to allocate a computational artificial intelligence (AI) task to at least one of the first node and the second node based on the at least one first load parameter and based on the at least one second load parameter.

19. The wireless communication system of claim 18 , wherein the second node is configured to transmit the at least one second load parameter to the first node, and wherein the first node and the second node are configured to mutually allocate the computational AI task.

20. The wireless communication system of claim 18 , wherein the wireless communication system is a 4G communication system or a 5G New Radio communication system.

Assignees

• Rohde & Schwarz

Inventors

• Wang Lilei
• Schlienz Juergen

Classifications

• H04W72/044

  based on the type of the allocated resource · CPC title

• H04W28/0861 Primary

  between base stations · CPC title