Green O-RAN Operation: a Modern ML-Driven Network Energy Consumption Optimisation
Xuanyu Liang, Ahmed Al-Tahmeesschi, Swarna Chetty, Hamed Ahmadi
TL;DR
The paper tackles energy inefficiency in dense O-RAN deployments by optimizing RU sleep modes using a twin-critic TD3-based DRL approach implemented as an xApp in the Near-RT RIC. It formulates RU sleep decisions as an MDP with a continuous action space to avoid combinatorial explosion and balances energy use with QoS via a carefully designed reward. Empirical results show the TD3 method achieves over 50% energy savings compared to an always-on baseline and outperforms two DQN baselines by up to 6%, with improved stability and faster convergence, especially in larger networks where discrete-action methods become infeasible. The work demonstrates the practicality and scalability of ML-driven energy optimization in Open RAN and points toward future enhancement via Federated Learning for distributed deployment.
Abstract
The increasing energy demand of next-generation mobile networks, especially 6G, is becoming a major concern, particularly due to the high power usage of base station components RU, which often remain active even during low traffic periods. To tackle this challenge, our study focuses on improving energy efficiency in O-RAN systems using intelligent control strategies. TD3 leverages a continuous action space to overcome the limitations of traditional discrete-action methods like DQN. By avoiding exponential growth in action space, TD3 enables more precise control of RU sleep modes in dense and large radio environments. Simulation results show that our approach consistently achieves over 50% energy savings compared to the always-on baseline, with TD3 outperforming DQN-based methods by up to 6%, while also offering better stability and faster convergence.