Dynamic D2D-Assisted Federated Learning Over O-RAN: Performance Analysis, MAC Scheduler, and Asymmetric User Selection

Existing studies on federated learning (FL) are mostly focused on system orchestration for static snapshots of the network and making static control decisions (e.g., spectrum allocation). However, real-world wireless networks are susceptible to temporal variations of wireless channel capacity and users' datasets. In this paper, we study the impacts of the dynamics: 1) wireless channels and 2) users' datasets on the FL execution. The former is captured by introducing a set of discrete time events while the latter is characterized by a novel ordinary differential equation and the metric of dynamic model drift, formulated via a partial differential inequality, drawing concrete analytical connections between the dynamics of users' datasets and FL accuracy. We then propose dynamic cooperative FL with dedicated MAC schedulers (DCLM), exploiting the unique features of open radio access network (O-RAN) to execute FL. DCLM entails: 1) a hierarchical device-to-device (D2D)-assisted model training; 2) dynamic control decisions through dedicated O-RAN MAC schedulers; and 3) asymmetric user selection. We provide extensive theoretical analysis to study the convergence of DCLM and then aim to optimize its degrees of freedom (e.g., user selection and spectrum allocation) through a non-convex optimization problem. We develop a systematic and generic approach to obtain the solution for this problem. We finally show the efficiency of DCLM via numerical simulations and provide a series of future directions.