A DDPG-based energy efficient federated learning algorithm with SWIPT and MC-NOMAopen access
- Authors
- Ho, Manh Cuong; Tran, Anh Tien; Lee, Donghyun; Paek, Jeongyeup; Noh, Wonjong; Cho, Sungrae
- Issue Date
- 2024
- Publisher
- Korean Institute of Communications and Information Sciences
- Keywords
- Deep reinforcement learning; Federated learning; Multi-carrier non-orthogonal multiple access; SWIPT
- Citation
- ICT Express, v.10, no.3, pp 600 - 607
- Pages
- 8
- Journal Title
- ICT Express
- Volume
- 10
- Number
- 3
- Start Page
- 600
- End Page
- 607
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/71854
- DOI
- 10.1016/j.icte.2023.12.001
- ISSN
- 2405-9595
2405-9595
- Abstract
- Federated learning (FL) has emerged as a promising distributed machine learning technique. It has the potential to play a key role in future Internet of Things (IoT) networks by ensuring the security and privacy of user data combined with efficient utilization of communication resources. This paper addresses the challenge of maximizing energy efficiency in FL systems. We employed simultaneous wireless information and power transfer (SWIPT) and multi-carrier non-orthogonal multiple access (MC-NOMA) techniques. Also, we jointly optimized power allocation and central processing unit (CPU) resource allocation to minimize latency-constrained energy consumption. We formulated an optimization problem using a Markov decision process (MDP) and utilized a deep deterministic policy gradient (DDPG) reinforcement learning algorithm to solve our MDP problem. We tested the proposed algorithm through extensive simulations and confirmed it converges in a stable manner and provides enhanced energy efficiency compared to conventional schemes. © 2023 The Authors
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/71854)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.