Cooperative Resource Allocation Using Optimized Heterogeneous Context-Aware Graph Convolutional Networks in 5G Wireless Networks

Abstract

Wireless personal communication is becoming more and more popular due to the rapid development of 5G communication networks. Modern wireless personal communication systems can be difficult to optimize due to the criteria for transmission speed and quality of service. In this manuscript, a cooperative resource allocation using optimized heterogeneous context-aware graph convolutional networks in 5G wireless networks (CRA-HCAGCN-5GWN) is proposed. Here, the cooperative resource allocation is used for channel information on a small scale rather than typical resource allocation when the channel environment is rapidly changing. HCAGCN fails to specify optimization techniques to identify optimal parameters for accurate cooperative resource allocation. Therefore, the Giant Trevally Optimizer (GTO) is employed to optimize the HCAGCN, which accurately optimizes resource allocation. The proposed CRA-HCAGCN-5GWN is implemented, and the performance metrics, like mean square error (MSE), minimum mean square error (MMSE), mean absolute error (MAE), root mean square error (RMSE), throughput, energy efficiency, and consumption time, are analyzed. The performance of the CRA-HCAGCN-5GWN approach attains 17.20%, 25.81%, and 32.18% lower mean square error; 16.40%, 28.81%, and 30.18% higher throughput; and 18.30%, 25.41%, and 31.08% lower energy efficiency when analyzed with existing methods.