Energy Efficiency Optimization in 5G and 6G Networks Using Machine Learning: A Comprehensive Review

Abstract

Cellular technologies have evolved continuously from the 1st to the 5th generation (5G) to meet the exponentially growing needs for bandwidth, throughput, and latency. However, energy consumption has risen proportionally with each generation, driven by the need for new hardware to support additional applications. Notably, 5G, which already consumes four times more energy than 4G, is expected to cause a significant spike in energy consumption. This paper focuses on energy consumption at the base station and access network levels, which together account for approximately 80% of energy consumption in mobile networks. The application of machine learning techniques to improve energy efficiency in these components is explored. Specifically, efficient base station deployment strategies, adaptive operational modes, and access network technologies such as massive MIMO and millimeter waves, which employ machine learning to enhance energy efficiency, are reviewed in depth. The paper also proposes a framework combining efficient base station deployment methods with machine learning-based switching between different operational modes based on traffic load. Additionally, an adaptive beamforming methodology involving the identification of hotspots, user association, sub-channel, and power allocation in heterogeneous networks is discussed.