AI-Assisted Multi-Operator RAN Sharing for Energy-Efficient Networks

Abstract

Recent times have seen a significant rise in interest from mobile operators, vendors, and research projects toward achieving more energy-efficient and sustainable networks. Not surprisingly, it comes at a time when higher traffic demand and more stringent and diverse network requirements result in diminishing benefits for operators using complex AI-driven network optimization solutions. In this paper, we propose the idea of tower companies that facilitate radio access network (RAN) infrastructure sharing between operators and evaluate the additional energy savings obtained in this process. In particular, we focus on the RAN-as-a-Service (RANaaS) implementation, wherein each operator leases and controls an independent logical RAN instance running on the shared infrastructure. We show how an AI system can assist operators in optimizing their share of resources under multiple constraints. This paper aims to provide a vision, a quantitative and qualitative analysis of the RANaaS paradigm, and its benefits in terms of energy efficiency. Through simulations, we show the possibility to achieve up to 75 percent energy savings per operator over 24 h compared to the scenario where none of the energy-saving features are activated. This is an additional 55 percent energy savings from sharing the RAN infrastructure compared to the baseline scenario where the operators use independent hardware.

Keywords

• Multi-operator RAN sharing
• energy efficiency
• radio resource management
• hierarchical reinforcement learning
• network optimization