Spatio-Temporal Ensemble Prediction on Mobile Broadband Network Data

Facing the huge success of mobile devices, network providers ceaselessly deploy new nodes (cells) to always guarantee a high quality of service. Nevertheless, keeping turned on all the nodes when traffic is low is energy inefficient. This has led to investigations on the possibility to turn off network nodes, fully or partly, in low traffic loads. To accomplish such a dynamic network optimization, it is crucial to predict very accurately low traffic periods. In this paper, we tackle this problem using data mining and propose Spatio-Temporal Ensemble Prediction (STEP). In a nutshell, STEP is based on the following two main ideas: (1) since traffic shows very different behaviors depending on both the temporal and the spatial contexts, several prediction models are built to fit these characteristics; (2) we propose an ensemble prediction technique that accurately predicts low traffic periods. We empirically show on a real dataset that our approach outperforms standard methods on the low traffic prediction task.