GRAPH NEURAL NETWORK BASED LEARNING FOR DYNAMIC SPECTRUM ACCESS

Over the past decade, we have witnessed tremendous technology development and societal benefits for various wireless devices, such as smartphones, smart wearable devices, and the Internet of Things (IoT), among others. To meet the traffic demands from these devices and provide a higher quality of experience (QoE) for users, wireless communication systems have exploited more and more radio spectrum. Although the capacity of the radio spectrum is fairly large, the shortage problem is imminent due to the dramatic proliferation of wireless devices. Dynamic spectrum access (DSA) is proposed as one of the most promising solutions to the spectrum shortage problem. The general objective of DSA is to allocate the spectrum resources to users dynamically and efficiently, which involves several control, coordination, and optimization problems. However, with the huge increment of wireless users, our wireless communication systems are much more complex than ever before and traditional DSA solutions can be low efficient or even impractical. Recent breakthroughs achieved by the advanced neural network based machine learning algorithms have demonstrated their great potentials in solving complex large-scale problems. This dissertation focus on developing neural network based machine learning algorithms and models for problems involved in DSA. This work majorly depends on two machine learning techniques: graph neural network (GNN) and reinforcement learning (RL), which are utilized to solve different optimization, coordination, and control problems related to DSA, such as spectrum sensing, interference estimation, and dynamic spectrum allocation. The proposed algorithms and models are validated by numerous simulation studies.