Hybrid Data-Driven and Simulation-Driven Prediction of mmWave Network Performance

Millimeter wave (mmWave) links offer high-bandwidth connectivity for next-generation wireless networks but face challenges in interference management and performance prediction. This paper introduces DDS, a novel hybrid data-driven simulator that accurately predicts link throughput distribution in mmWave networks. DDS leverages readily available physical (PHY) layer measurements and employs a deep reinforcement learning (DRL) framework to interpret the PHY environment and determine appropriate parameters for subsequent simulations. The system integrates a DRL-based parameter tuner with a PHY and MAC layer simulator, bridging the gap between simulation and real-world performance. We conduct comprehensive evaluations of DDS, demonstrating its superior accuracy compared to its baselines. Our experiments validate DDS's effectiveness in enhancing network controller training and deriving optimal network configuration policies in dense mmWave deployments.