Learning Decentralized Power Control in Cell-Free Massive MIMO Networks

This paper studies learning-based decentralized power control methods for cell-free massive multiple-input multiple-output (MIMO) systems where a central processor (CP) controls access points (APs) through fronthaul coordination. To determine the transmission policy of distributed APs, it is essential to develop network-wide collaborative optimization mechanism. address this challenge, we design cooperative learning (CL) framework which manages computation and coordination strategies CP APs using dedicated deep neural network (DNN) modules. build versatile structure, proposed CL carefully designed such that its forward pass calculations are independent number APs. end, adopt parameter reuse concept installs an identical DNN module at all Consequently, trained particular configuration can be readily applied arbitrary AP populations. Numerical results validate advantages over conventional non-cooperative approaches.