Deep Reinforcement Learning for Reconfigurable Intelligent Surfaces and UAV Empowered Smart 6G Comm

This co-authored book explores the many challenges arising from real-time and autonomous decision-making for 6G by covering crucial advanced signal control and real-time decision-making methods for UAV- and RIS-assisted 6G wireless communications including the serious constraints in real-time optimisation problems. Massive multiple-input multiple-output (MIMO), device-to-device (D2D) communication, reconfigurable intelligent surface (RIS) and heterogeneous cellular networks have increased the demand for quality-of-service (QoS) in wireless networks as they are facing challenges such as limited spectrum, processing time constraints, and cooperative requirements. Unmanned aerial vehicles (UAVs) have drawn considerable attention due to their agile mobility and cost-effectiveness to overcome bottlenecks and reaching remote areas. Reconfigurable intelligent surface (RIS) technology, which is low-cost, energy efficient and easy to deploy, can intelligently reconfigure the wireless propagation environment and customize wireless channels based on design objectives. Deep reinforcement learning (DRL) algorithms are used to maximise network performance, reduce power consumption, and improve the processing time to help UAVs and RIS work fully autonomously, reduce energy consumption and operate optimally in unexpected environments. This co-authored book explores the many challenges arising from real-time and autonomous decision-making for 6G by covering crucial advanced signal control and real-time decision-making methods for UAV- and RIS-assisted 6G wireless communications including the serious constraints in real-time optimisation problems.