Federated Learning Driven Multi-Modal User Scheduling for 5G Communication Systems

In this paper, we consider a federated learning (FL)-assisted fifth-generation (5G) resource block (RB) allocation scheme for terrestrial users. Enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC) users calculate their possible achievable uplink data rate with its local neural engine based on underlying channel conditions and packet availability at their data queue. Each user conveys this information to the 5G base station (BS), which then allocates the RB to the user that best meets its service requirements, thereby improving the network throughput. Each user trains its neural engine with either baseline clustered FL or our proposed peer-to-peer (P2P) FL. In clustered FL, clients are grouped by local model similarity, implicitly capturing user types such as eMBB, URLLC, and mMTC. In our P2P FL scheme, clients update their models through exchanges with similarity-selected peers, using similarity-adaptive weights. Simulation results demonstrate the effectiveness of our proposed FL approaches in scheduling users for transmission over conventional baseline schemes.