Design and Evaluation of Deep Reinforcement Learning for Energy Saving in Open RAN

Next-generation wireless systems, already widely deployed, are expected to become even more prevalent in the future, representing challenges in both environmental and economic terms. This paper focuses on improving the energy efficiency of intelligent and programmable Open Radio Access Network (RAN) systems through the near-real-time dynamic activation and deactivation of Base Station (BS) Radio Frequency (RF) frontends using Deep Reinforcement Learning (DRL) algorithms, i.e., Proximal Policy Optimization (PPO) and Deep Q-Network (DQN). These algorithms run on the RAN Intelligent Controllers (RICs), part of the Open RAN architecture, and are designed to make optimal network-level decisions based on historical data without compromising stability and performance. We leverage a rich set of Key Performance Measurements (KPMs), serving as state for the DRL, to create a comprehensive representation of the RAN, alongside a set of actions that correspond to some control exercised on the RF frontend. We extend ns-O-RAN, an open-source, realistic simulator for 5G and Open RAN built on ns-3, to conduct an extensive data collection campaign. This enables us to train the agents offline with over 300,000 data points and subsequently evaluate the performance of the trained models. Results show that DRL agents improve energy efficiency by adapting to network conditions while minimally impacting the user experience. Additionally, we explore the trade-off between throughput and energy consumption offered by different DRL agent designs.