BROWSE
Detail
Journal Article
Federated Learning-Based Energy-Efficient Consumer-Centric Access Strategy for Cell-Free MIMO in 6G Wireless Networks
Cited 1 time in 
Share 
Share
- Authors
- Nikhil Kumar Singh, Sonal Telang Chandel, Sunhwan Lim, Joohyung Lee
- Issue Date
- 2025-05
- Citation
- IEEE Transactions on Consumer Electronics, v.71, no.2, pp.4292-4303
- ISSN
- 0098-3063
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Abstract
- With the rapid expansion of consumer-centric 6G mobile communication networks, ensuring efficient consumer access and minimizing energy consumption in cell-free massive multiple-input multiple-output (CF-mMIMO) systems have become significant challenges. Selecting optimal consumer access points (APs) is complex due to varying channel conditions, energy demands, and privacy concerns in densely populated network environments. To address these challenges, this paper proposes a channel ranking-based poor-consumer-first access strategy, where consumers evaluate and rank their channel quality based on channel state information. The strategy enables consumers to select suitable APs, prioritizing those with poorer channel quality to ensure reliable communication. Additionally, a federated learning framework is introduced to strengthen data privacy, and an energy consumption optimization-based alternating optimization algorithm is developed to adjust multidimensional variables such as transmission power, time allocation, and learning accuracy, thus minimizing the system’s overall energy consumption. Simulation results indicate that, compared to traditional user-centric access strategies in massive MIMO, the proposed approach improves the average uplink achievable rate by 20% and doubles the rate for users with poorer channel conditions, while also reducing total energy consumption by over 50%.
- KSP Keywords
- Access point, Achievable rate, Alternating optimization algorithm, Channel State Information(CSI), Channel quality, Consumer-centric, Energy Consumption Optimization, Energy demand, Federated learning, Learning framework, Learning-based