Machine Learning-Driven QoS Prediction in 6G Networks Under $\alpha-\eta-\mu$ Fading with Selection Combining and Co-Channel Interference Mitigation

In this paper, we study machine learning for resource utilization and QoS performance improvement in 6G networks under <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\alpha-\eta-\mu$</tex> fading and co-channel interference (CCI). We conduct extensive experiments in simulation comparing our proposal with previous work and showing substantial improvements for both throughput, latency and resource efficiency over traditional as well as deep reinforcement learning based approaches. Their adaptive nature enables real-time optimization, and they run well in both dynamic and complex network conditions. Our experimental results illustrate that machine learned models significantly outperform state-of-the-art baselines on the following dimensions prediction accuracy, resource management and QoS metrics. This work underscores the importance of machine learning as a core enabler for sustainable 6G networks and providing better performance in future wireless communication systems.