Device-to-Device Resource Allocation Using Federated Learning: A Comprehensive Study

Abstract

Device-to-Device (D2D) communication is a crucial component of modern wireless networks, enabling direct communication between nearby devices. Efficient resource allocation in D2D communication is essential to optimize network performance. This paper presents a comprehensive study on D2D resource allocation using the innovative Federated Learning (FL) concept. We discuss the challenges of D2D resource allocation, propose a system model that incorporates FL, and present simulation results demonstrating the effectiveness of our proposed model. The results indicate that FL-based D2D resource allocation can significantly improve resource utilization and network performance.