AI-Based Network Traffic Prioritization for Latency-Sensitive Applications in 6G Networks

This applies because the emergence of 6G networks brings new problems of controlling the growing and heterogonous traffic streams from different connected devices. An important gap refers to the difficulties of providing Quality of Service (QoS) for latency critical traffic like autonomous transportation, tele-operations, tele-surgey or augmented reality. Conventional approaches to QoS do not fit well within the dynamics and variability of 6G traffic, then require additional and more versatile methods of managing the given traffic. This paper focuses on the deployment of Artificial Intelligence enabled traffic prioritization for latency critical applications in the 6G networks. Powered by deep learning models; convolutional neural networks (CNN) and recurrent neural networks (RNN), the proposed system predicts the traffic conditions and responds by proper resource allocation. When the concept of network slicing is combined with AI, the system is even more capable of meeting the needs of the various applications. The performance evaluation from experimental results, conducted by using real traffic datasets in combination with synthetic datasets, reveals that the presented AI-based system offers less latency, better bandwidth utilization and less packet drop rates than other conventional QoS algorithms. Further, the proposed approach based on AI improves energy consumption making the future 6G networks more sustainable. As shown in this research, through AI, the limitations that may be incurred in the management of network traffic for highly latency-sensitive applications in 6G are managed efficiently and on a large scale.