Privacy-Preserving Joint Edge Association and Power Optimization for the Internet of Vehicles via Federated Multi-Agent Reinforcement Learning
This addresses privacy and efficiency challenges in edge computing for vehicular networks, representing an incremental improvement over existing methods.
The paper tackles the problem of improving connectivity-cost trade-off in the Internet of Vehicles without privacy leakage by proposing a federated multi-agent reinforcement learning approach for joint edge association and power optimization, achieving a compelling trade-off and higher privacy than state-of-the-art solutions.
Proactive edge association is capable of improving wireless connectivity at the cost of increased handover (HO) frequency and energy consumption, while relying on a large amount of private information sharing required for decision making. In order to improve the connectivity-cost trade-off without privacy leakage, we investigate the privacy-preserving joint edge association and power allocation (JEAPA) problem in the face of the environmental uncertainty and the infeasibility of individual learning. Upon modelling the problem by a decentralized partially observable Markov Decision Process (Dec-POMDP), it is solved by federated multi-agent reinforcement learning (FMARL) through only sharing encrypted training data for federatively learning the policy sought. Our simulation results show that the proposed solution strikes a compelling trade-off, while preserving a higher privacy level than the state-of-the-art solutions.