ML-Driven xApp for Network Slicing and Resource Optimization in 6G O-RAN Architecture

The increasing complexity and diversity of 6G applications, such as autonomous systems and massive IoT, pose significant challenges for current network slicing techniques in efficiently managing resources and meeting diverse quality of service (QoS) requirements. Traditional approaches struggle to adapt to the dynamic demands of multiple services with varying throughput, latency, and reliability needs. To address this, we propose a Network Slicing-based Control Mechanism (NSMG), which integrates Machine Learning (ML) within the Open Radio Access Network (O-RAN) framework to optimize resource allocation for 6G networks. Our solution ensures efficient resource distribution, improving overall network performance by reducing delay, maximizing throughput, and minimizing packet loss ratio (PLR). The simulation results validate the effectiveness of NSMG in terms of improving 6G network efficiency, making it a viable solution for future network deployments.