AoA-Based Pilot Assignment in Massive MIMO Systems Using Deep Reinforcement Learning

In this letter, the problem of pilot contamination in a multi-cell massive multiple input output (M-MIMO) system is addressed using deep reinforcement learning (DRL). To end, assignment strategy designed that adapts to channel variations while maintaining tolerable effect. Using angle arrival (AoA) information users, cost function, portraying reward, presented, defining effects system. Numerical results illustrate DRL-based scheme able track changes environment, learn near-optimal assignment, and achieve close performance optimum performed by exhaustive search, low computational complexity.