Federated Learning Uplink Scheduling With Conjugate Signal Pairing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing federated learning methods in wireless communication systems are affected by channel estimation errors, leading to operational ambiguity between user equipments (UEs) and base stations, and there is a need for a method to reduce the impact of these errors and define proper operation schemes.

Innovation Solution

A method involving complex conjugate relationships in signal transmission between UEs and a base station, with channel compensation operations based on channel estimation error power ratios, to enhance federated learning in wireless communication systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional federated learning methods are used in wireless communication systems, then the learning process can be performed, but channel estimation errors significantly degrade the performance and accuracy of the learning process

Engineering Contradiction:
Improvefederated learning performanceVSAvoidchannel estimation error impact
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by performing channel compensation operations before the federated learning parameter transmission. The base station estimates channels and computes compensation values in advance, then uses these to pre-process the uplink signals from UEs. This preliminary channel compensation removes the harmful effect of channel estimation errors before they can degrade the federated learning performance, thereby improving reliability while addressing the harmful factor.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If channel compensation operations are performed to reduce estimation errors, then federated learning accuracy improves, but operational ambiguity between UEs and base station increases

Engineering Contradiction:
Improvechannel estimation accuracyVSAvoidoperation protocol clarity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent implements feedback by establishing a closed-loop communication protocol where the base station estimates channels, computes compensation values, and feeds back the necessary information to UEs. The UEs then apply the compensation and feed back their processed parameters. This structured feedback mechanism clarifies the operational roles of each entity, resolving the ambiguity that would otherwise arise from the complex channel compensation operations.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary role through the base station, which acts as a central coordinator that estimates channels, computes compensation values, and manages the federated learning process. This intermediary structure provides clear operational guidance to both UEs and the network, eliminating the ambiguity that would exist if UEs had to independently perform complex channel compensation without centralized coordination.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If complex conjugate relationship is used in signal transmission, then channel estimation error impact is reduced, but device complexity increases

Engineering Contradiction:
Improvesignal transmission accuracyVSAvoidsignal processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies self-service by having each UE independently compute its own channel compensation using the estimated channel information and compensation values provided by the base station. Each UE processes its own uplink signal with the complex conjugate relationship without requiring complex coordination with other UEs. This self-service approach reduces the overall system complexity while maintaining the reliability benefits of channel compensation.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS12568000B2Method and device for performing federated learning in wireless communication system
Publication Date: 2026.03.03 LG ELECTRONICS INC
  • US12568000B2 patent drawing
  • US12568000B2 patent drawing
  • US12568000B2 patent drawing

AI summary

A method of performing, by a plurality of user equipments (UEs), a federated learning in a wireless communication system comprises receiving, from a base station (BS), control information related to a scheduling of a resource on which the one UE repeatedly transmits a local parameter of the one UE, wherein a global parameter for the federated learning is updated based on respective local parameters of the plurality of UEs; transmitting, to the BS, a first signal including the local parameter on a first resource scheduled based on the control information; and transmitting, to the BS, a second signal including the local parameter on a second resource that is scheduled based on the control information and is different from the first resource, wherein the first signal and the second signal are transmitted based on the first signal and the second signal being in a complex conjugate relationship.