An Optimal Algorithm for Resource Optimization in 5G Networks Based on Machine Learning

Abstract

A 5G network enabling technology to meet multi-gabit data demands is mmwave D2D communications. As a result of their directional coverage and high data rate connectivity, mmwave networks are well suited for the delivery of proximity services via D2D communications. In a dense D2D pair network situation, the directional features at the mmwave band reduce interference between D2D pairs. To evaluate the impact of the integration of D2D and mmWave communication, this paper proposed a novel algorithm. The main idea is to maximize the total system throughput through optimal objective function. The linear correlation method is used to select the admission set of D2D users. Then, the optimal transmit power is determined through a power control mechanism. Finally, the resources are allocated to the D2D users using a multi-phase matching algorithm. Simulation results show that the proposed algorithm has better performance as compared with existing algorithms.