Congestion Control in 5G/6G Networks: An Efficient Multi‐Relational Skeleton Graph Attention Networks With Greater Cane Rat Optimization Algorithm

Abstract

The emergence of 5G and the imminent deployment of 6G networks have revolutionized wireless communication by enabling ultra‐reliable low‐latency communication, enhanced mobile broadband, and massive machine‐type communication. While these diverse applications foster increasingly complex congestion scenarios due to highly dynamic traffic patterns, diverse requirements of different services, and ultra‐dense deployments of the network, efficient congestion control has become a pressing challenge. Conventional methods cannot address the nonlinear and multi‐relational characteristics of data traffic. Therefore, with the rapid scaling of connected devices with heterogeneous service demands, bottlenecks will be experienced, which leads to packet loss, increased latency, and poor QoS. Given the above challenges, this paper introduces an advanced congestion control framework developed on top of intelligent graph‐based learning and optimization strategies. The input data is from the DeepSense 6G dataset and preprocessed using Z‐score and min–max normalization to enhance the stability and uniformity of the preprocessed data. The feature selection is further fine‐tuned through the Orchard Algorithm (OA), ensuring highly relevant feature selection. An innovative combination of Multi‐Relational Skeleton Graph Attention Networks is proposed to cater to the challenge of understanding multiple relational behaviors in data traffic. Furthermore, the performance of the integrated model is optimized with the Greater Cane Rat Optimization Algorithm to enhance learning efficiency and the precision of congestion control. Experimental analysis demonstrates an outstanding accuracy of 99.9%, ensuring the proposed approach effectively mitigates congestion in 5G/6G networks.