Wireless channel estimation using federated learning

Jasneet Kaur, M. Arif Khan

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

Contemporary Machine Learning (ML) techniques can now be conveniently applied to the wireless channel estimation problem to reduce the estimation complexity and enhance the system's overall data rate. Traditionally, the wireless channel is estimated at the base station (BS), where BS receives the channel information from the users via the feedback channel. This poses a potential problem with the privacy and security of users' channel information as well as requires large bandwidth for the feedback channel in a system with a large number of users. To address, the dual issues of users' privacy and lessening the required bandwidth for the feedback channel, this paper proposes a Federation Learning (FL) based wireless channel estimation solution for a commonly used wireless communication system. In this technique, each user estimates its own channel and only shares the model parameters with the BS which then combines the information from all users to construct a joint wireless channel to be used for transmission for the next time slot. To evaluate the accuracy of proposed model, we used Stochastic Gradient Descent (SGD) to optimise the solution and compared the results with the results presented in [1]. The numerical results show that the proposed model renders more stable and accurate estimation results in conjunction with the use of SGD and FL.

Original languageEnglish
Title of host publication2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9798350394474
ISBN (Print)9798350394450
DOIs
Publication statusPublished - 2024
Event9th IEEE International Conference for Convergence in Technology, I2CT 2024 - The Fern Ecotel Hotel, Lonavala, India
Duration: 05 Apr 202407 Apr 2024
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/xpl/conhome/10543249/proceeding (Proceedings)
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/stamp/stamp.jsp?tp=&arnumber=10543345 (Front matter)
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/stamp/stamp.jsp?tp=&arnumber=10543967 (Schedule)

Publication series

Name2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024

Conference

Conference9th IEEE International Conference for Convergence in Technology, I2CT 2024
Abbreviated titleConvergence in innovative technology
Country/TerritoryIndia
CityLonavala
Period05/04/2407/04/24
OtherThe theme for 9th I2CT 2024 is convergence in Innovative Technology – researchers and engineers will be brought together from academia and industry, and they will freely expose their ideas and opinions on emerging issues in the field of electrical, electronics and computer engineering as well as information technologies.

Prospective authors are invited to submit full paper with six- seven pages in double-column IEEE conference format via the conference website. More information on about paper format and guidelines for paper submission can be found at the conference website.
Internet address

Fingerprint

Dive into the research topics of 'Wireless channel estimation using federated learning'. Together they form a unique fingerprint.

Cite this