Energy Saving for Cell-Free Massive MIMO Networks: A Multi-Agent Deep Reinforcement Learning Approach

TL;DR

This paper introduces a multi-agent deep reinforcement learning method for energy-efficient control in cell-free massive MIMO networks, enabling autonomous, distributed optimization of antenna configurations and sleep modes under dynamic traffic.

Contribution

It presents a novel MADRL framework that allows distributed, real-time energy management in CF mMIMO networks, outperforming traditional and non-learning approaches.

Findings

Reduces power consumption by 56.23% compared to no energy-saving scheme.

Achieves 30.12% power savings over non-learning sleep mode methods.

Maintains low drop ratio with similar power savings to DQN-based methods.

Abstract

This paper focuses on energy savings in downlink operation of cell-free massive MIMO (CF mMIMO) networks under dynamic traffic conditions. We propose a multi-agent deep reinforcement learning (MADRL) algorithm that enables each access point (AP) to autonomously control antenna re-configuration and advanced sleep mode (ASM) selection. After the training process, the proposed framework operates in a fully distributed manner, eliminating the need for centralized control and allowing each AP to dynamically adjust to real-time traffic fluctuations. Simulation results show that the proposed algorithm reduces power consumption (PC) by 56.23% compared to systems without any energy-saving scheme and by 30.12% relative to a non-learning mechanism that only utilizes the lightest sleep mode, with only a slight increase in drop ratio. Moreover, compared to the widely used deep Q-network (DQN) algorithm, it achieves a similar PC level but with a significantly lower drop ratio.