Power Saving Algorithms for Mobile Networks Using Classifiers Ensemble

The main objective of this paper is to tackle the energy consumption for cellular radio networks. The mobile telecomunications system are optimized for the maximum load. Therefore, in the low traffic moment, the system consume incredible amounts of energy, which is not used in any way. The solution, which we propose in this paper is based on automatic switching on and off the network elements, depending on the current state of the network and on the prediction of the next state. It is also shown, that with the predictions from the ensemble of classifiers, the energy consumption can be reduced dramatically and such approach is acting better than simply setting the threshold values. The biggest challenge is to maintain reliable service coverage and quality of service (QoS) in the specific cell in the network.