Autonomous Radio Resource Provisioning in Multi-WAT Private 5G RANs based on DRL

Abstract

Multi-Wireless Access Technology (WAT) Radio Access Networks (RANs) are becoming a key enabler in 5G and beyond networks due to the public spectrum scarcity, the level of signal confinement and security offered by some wireless technologies (e.g., Light Fidelity (Li-Fi)), and the reduction of the deployment and operational costs. For instance, Wireless Fidelity (Wi-Fi) technology is cheaper and easier to manage than 5G, and leveraging their already deployed infrastructures contributes to capital expenditures saving. Developing autonomous radio resource provisioning (RRP) solutions is fundamental to cost-effectively achieve the zero-touch management in private 5G networks while fulfilling the service requirements. However, modelling the Key Performance Indicators of the radio interface in 5G and beyond is a complex task that requires high-domain knowledge. Furthermore, the resulting models, as well as solving the respective RRP optimization problem using exact methods usually offer a high computational complexity, especially in multi-WAT scenarios. In order to cope with these issues, in this work, we propose an initial design of a Deep Reinforcement Learning-assisted solution for the RRP in a multi-WAT private 5G network. Furthermore, we contex-tualize the solution in the Open RAN architecture framework. A simulation-based proof-of-concept validates the proposal’s proper design and operation considering a realistic private 5G network scenario.