Spatial-temporal compressed sensing based traffic prediction in cellular networks

In conventional cellular networks, base stations (B-Ss) usually suffer from severe power consumption since they are working to guarantee the coverage and QoS (quality-of-service) requirement according to the peak traffic load generated by the mobile cellular users Accordingly, how to precisely forecast the future traffic load to promote network cooperation and adaptive energy resource allocation in complying with the variation of spatial-temporal traffic load has been an emerged issue due to the significant energy exhaustion of BSs. In this paper, we propose a spatial-temporal compressed sensing based network traffic prediction method to solve this problem. We first construct a traffic matrix (TM) by using previously measured data and setting the data to be predicted as zeros, corresponding to the volume of traffic load. Then, compressed sensing approach with large scale and small scale temporal constraints as well as spatial constraints is employed to factorize the traffic matrix. By reuniting the results of traffic matrix factorization, we obtain the estimation of predicted traffic data. Numerical results have showed that this method can restrict the prediction error under 10% when dealing with real traffic load data.