Joint V2V Group Association and Transmission Power Control in Federated Vehicular Networks

Abstract

With growing awareness of privacy protection, federated learning (FL) in vehicular network scenarios effectively addresses privacy concerns, leading to the development of federated vehicular networks (FVNs). In FVN, vehicles maintain a global model by transmitting local models and iterative processing, resulting in significant communication overhead. In the Internet of Vehicles (IoV), as the majority of the spectrum resources are allocated to Vehicle-to-Vehicle (V2V) communication, vehicles engaged in FL encounter uplink interference when these resources are reused. This compromises the efficacy of FL vehicle communication. To address this issue, we propose FedCDC, a new federated learning framework with adaptive weight clustering with knowledge distillation and channel sharing-based resource allocation. First, we implement a communication compression strategy based on clustering and distillation to alleviate transmission load. Then, we develop a resource allocation strategy to maximize the signal-to-interference-plus-noise ratio (SINR) for both FL vehicles and V2V groups, which investigates two critical components: 1) channel pairing and 2) power coordination. We formulate the optimization issue as a multiobjective optimization problem, that is, solved offline using the MIDACO solver. Due to the dynamic characteristics of FVN, we employ a multiagent deep deterministic policy gradient (MADDPG) to enhance efficiency. Finally, extensive experiments demonstrate that our approach significantly reduces data transmission and offers an efficient resource coordination plan, thus improving FL communication efficiency and ensuring the Quality of Service (QoS) for both V2V groups and FL vehicles.