Reinforcement learning optimization for base station sleeping strategy in coordinated multipoint (CoMP) communications

Recently, wireless communication has faced with “green” challenge. The emergence of the “green wireless communication” means environment protection and energy saving. A “green wireless communication” is aimed at energy conservation and emissions reduction on the basis of reducing communication radiation and ensuring the quality of communication in the wireless communication network. According to related statistics, the energy consumption of the base station accounts for more than 70% in wireless communication network. So, it is important to reduce the energy consumption of the base station to realize the energy saving of mobile communication system. As a result, the base station sleeping strategy in coordinated multipoint (CoMP) communication is a promising method to solve this problem. In the base station sleeping strategy, base station with the most light traffic is off, and the users in this cell are served by the surrounding base stations with CoMP communications. However, since the downlink performance is also important for users, we should save the energy as well as keeping a perfect downlink performance. This paper presents a control theory to study the base station sleeping strategy optimization issues with CoMP communications. Specifically, to make decisions for the base station sleeping strategy, we apply the threshold method and reinforcement learning (RL) algorithm. We develop the multi-step Q-learning of the RL algorithm to optimize the base station sleeping strategy. Simulation results are provided to show the process and effectiveness of the proposed scheme.