GAN for Load Estimation and Traffic-Aware Network Selection for 5G Terminals

Abstract

In the face of the user-centric access network architecture adopted by the fifth-generation (5G) mobile communication network terminals, the communication capability of terminals faces significant challenges. In this case, the combination of 5G and artificial intelligence (AI) has become a significant trend to meet the various communication needs of terminal devices. Toward the problem that the data analysis and decision making for cell load estimation are primarily accomplished on the access side of the network, terminals can only passively access the network, but cannot predict the load estimation on the access side of the network in advance and cannot make network selection decisions in real time. In this article, we propose a cell load estimation algorithm based on a generative adversarial network (GAN) for 5G mobile communication networks, which considers estimating the cell load according to the wireless information measured by the terminals. The algorithm effectively estimates the cell load at the terminal side, which reflects the intelligence of the terminals and solves the problems of low data transmission rate, high signaling cost, and time delay in the existing techniques for load estimation schemes at the network side, assisting users in making a real-time decision. The performance is evaluated through the system-level simulation, and the results indicate that the proposed model improves load estimation accuracy, simultaneously improving the network throughput and reducing the packet queuing delay, suitable for different heterogeneous network scenarios.