Cooperative Sleep and Energy-Sharing Strategy for a Heterogeneous 5G Base Station Microgrid System Integrated with Deep Learning and an Improved MOEA/D Algorithm

With the rapid growth of heterogeneous fifth-generation (5G) communication networks and a surge in global mobile traffic, energy consumption in mobile network systems has increased significantly. This underscores the need for energy-efficient networks that lower operational costs and carbon emissions, leading to a focus on microgrids powered by renewable energy. However, accurately predicting base station traffic demand and optimizing energy consumption while maximizing green energy usage—especially concerning quality of service (QoS) for users—remains a challenge. This paper proposes a cooperative sleep and energy-sharing strategy for heterogeneous 5G base station microgrid (BSMG) systems, utilizing deep learning and an improved multi-objective evolutionary algorithm based on decomposition (MOEA/D). We present a reference scenario for a 5G BSMG system comprising a central and sub-base station microgrid. A prediction model was developed, integrating a convolutional neural network with a dual attention mechanism and bidirectional long short-term memory to determine the operational status of BSMGs. Our cooperative strategy addresses QoS requirements and uses the enhanced MOEA/D to improve performance. Numerical results indicate that our approach achieves significant energy savings while ensuring accurate predictions of BSMG energy demands through a multi-objective evolutionary algorithm based on decomposition.