Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles
Aiming at the problem that it is difficult to achieve an optimal trade-off between wireless communication and model accuracy in FEEL training caused by the heterogeneity of wireless links and data distribution, a reconfigurable intelligent surface (RIS) enabled federated edge learning system was pro...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023192/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540078695874560 |
|---|---|
| author | Ping WANG Zhiwei YANG Heju LI |
| author_facet | Ping WANG Zhiwei YANG Heju LI |
| author_sort | Ping WANG |
| collection | DOAJ |
| description | Aiming at the problem that it is difficult to achieve an optimal trade-off between wireless communication and model accuracy in FEEL training caused by the heterogeneity of wireless links and data distribution, a reconfigurable intelligent surface (RIS) enabled federated edge learning system was proposed, which exploited the channel reconfigurability of RIS to adaptively manipulate the signal propagation environment, and utilized the over-the-air computation (Aircomp) to achieve fast model aggregation.Specifically, the convergence behavior of the FEEL algorithm under the influence of wireless channels and data heterogeneity was rigorously derived, and accordingly, an unified wireless resources optimization problem was constructed with the goal of minimizing the learning loss by jointly designing the transceiver design and the RIS phase shift.Simulation results demonstrate that the proposed scheme achieves substantial performance improvement compared against several baselines, and prove that RIS can play an important role in improving the accuracy of Aircomp enabled FEEL systems under data heterogeneity.Finally, the probability of applying it into Internet of vehicles is discussed. |
| format | Article |
| id | doaj-art-dfa03c947d3f48678bda28283eab79f2 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-dfa03c947d3f48678bda28283eab79f22025-01-14T06:23:27ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-10-0144465759388129Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehiclesPing WANGZhiwei YANGHeju LIAiming at the problem that it is difficult to achieve an optimal trade-off between wireless communication and model accuracy in FEEL training caused by the heterogeneity of wireless links and data distribution, a reconfigurable intelligent surface (RIS) enabled federated edge learning system was proposed, which exploited the channel reconfigurability of RIS to adaptively manipulate the signal propagation environment, and utilized the over-the-air computation (Aircomp) to achieve fast model aggregation.Specifically, the convergence behavior of the FEEL algorithm under the influence of wireless channels and data heterogeneity was rigorously derived, and accordingly, an unified wireless resources optimization problem was constructed with the goal of minimizing the learning loss by jointly designing the transceiver design and the RIS phase shift.Simulation results demonstrate that the proposed scheme achieves substantial performance improvement compared against several baselines, and prove that RIS can play an important role in improving the accuracy of Aircomp enabled FEEL systems under data heterogeneity.Finally, the probability of applying it into Internet of vehicles is discussed.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023192/federated edge learningdata heterogeneityreconfigurable intelligent surfaceover-the-air computation, convergence analysisInternet of vehicles |
| spellingShingle | Ping WANG Zhiwei YANG Heju LI Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles Tongxin xuebao federated edge learning data heterogeneity reconfigurable intelligent surface over-the-air computation, convergence analysis Internet of vehicles |
| title | Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles |
| title_full | Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles |
| title_fullStr | Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles |
| title_full_unstemmed | Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles |
| title_short | Federated edge learning with reconfigurable intelligent surface and its application in Internet of vehicles |
| title_sort | federated edge learning with reconfigurable intelligent surface and its application in internet of vehicles |
| topic | federated edge learning data heterogeneity reconfigurable intelligent surface over-the-air computation, convergence analysis Internet of vehicles |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023192/ |
| work_keys_str_mv | AT pingwang federatededgelearningwithreconfigurableintelligentsurfaceanditsapplicationininternetofvehicles AT zhiweiyang federatededgelearningwithreconfigurableintelligentsurfaceanditsapplicationininternetofvehicles AT hejuli federatededgelearningwithreconfigurableintelligentsurfaceanditsapplicationininternetofvehicles |