Federated Learning-based Base Station Selection on 3D LiDAR Data for Beyond 5G Communications
Sivalingam, Thushan; Sharma, Anupma; Bhatia, Vimal; Rajatheva, Nandana; Sharma, Sanjeev; Deka, Kuntal (2024-03-25)
IEEE
25.03.2024
T. Sivalingam, A. Sharma, V. Bhatia, N. Rajatheva, S. Sharma and K. Deka, "Federated Learning-based Base Station Selection on 3D LiDAR Data for Beyond 5G Communications," 2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), Jaipur, India, 2023, pp. 1-6, doi: 10.1109/ANTS59832.2023.10469265.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202404162774
https://urn.fi/URN:NBN:fi:oulu-202404162774
Tiivistelmä
Abstract
The optimum selection of a base station (BS) among multiple BSs for a moving vehicle ensures a continuous, reliable, and low-latency link in the millimeter wave (mmwave)-communication systems. Each BS performs a handshake with the mobile vehicle using ray tracing and then calculates the power loss to select the best BS. In this work, we compare the best BS selection out of three BSs using ray tracing and received signal strength indicator (RSSI) with the federated learning (FL) model. Also, we emphasized the simple 3D model over the RSSI-based approaches. The proposed FL approach significantly reduces the communication overhead while preserving user privacy. Different FL algorithms are compared based on various parameters in our model to get the test accuracy of these algorithms, where the simulation results show the achieved accuracy. Furthermore, the impact on the accuracy of various parameters of the FL model is highlighted. In addition, we show a detailed system model and process for generating a 3D ray-traced model for two US cities for validation and reproducibility of the results.
The optimum selection of a base station (BS) among multiple BSs for a moving vehicle ensures a continuous, reliable, and low-latency link in the millimeter wave (mmwave)-communication systems. Each BS performs a handshake with the mobile vehicle using ray tracing and then calculates the power loss to select the best BS. In this work, we compare the best BS selection out of three BSs using ray tracing and received signal strength indicator (RSSI) with the federated learning (FL) model. Also, we emphasized the simple 3D model over the RSSI-based approaches. The proposed FL approach significantly reduces the communication overhead while preserving user privacy. Different FL algorithms are compared based on various parameters in our model to get the test accuracy of these algorithms, where the simulation results show the achieved accuracy. Furthermore, the impact on the accuracy of various parameters of the FL model is highlighted. In addition, we show a detailed system model and process for generating a 3D ray-traced model for two US cities for validation and reproducibility of the results.
Kokoelmat
- Avoin saatavuus [34150]