Energy Conservation by Traffic Switching Process in Cellular Radio Access Networks

The mobile telecommunication is one of the major contributors to energy consumption and greenhouse gas emission. In a typical cellular system, the base stations (BSs) contribute 60%-80% of the energy consumption of the whole network. Improving the energy-efficiency of the BSs can significantly reduce both the operational cost and carbon footprint. Therefore, to reduce the cost and the amount of energy conseved in cellular network, the reinforcement method is used. This project is mainly proposed for improving the energy conservation of base stations in cellular radio access networks by Markov decision process along with reinforcement learning approach. Here the traffic is calculated through the online processing by Markov decision process. To speed up the ongoing learning peocess, a transfer actor-critic algorithm is used. The process which is mentioned above is completed successfully. Further process of this project is to consider the influence of fast fading effect and noise.