Energy Saving through a Learning Framework in Greener Cellular Radio Access Networks
Recent papers have validated the possibility of energy efficiency improvement in Radio Access Networks (RAN), depending on dynamically turn on/off some Base Stations (BSs). In this paper, the authors extend the research over BS switching operation, matching up with traffic load variations. However, instead of depending on the predicted traffic loads, which is still quite challenging to precisely forecast, they formulate the traffic variation as a Markov Decision Process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, they adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, they evaluate their proposed scheme by extensive simulations under various practical configurations and prove the feasibility of significant energy efficiency improvement.