A novel minimax probability machine for network traffic prediction

Network traffic prediction is important to network planning, performance evaluation and network management directly. A variety of machine learning models such as artificial neural networks (ANN) and support vector machine (SVM) have been applied in traffic prediction. In this paper, a novel network traffic one-step-ahead prediction technique is proposed based on a state-ofthe-art learning model called minimax probability machine (MPM). In the experiments, the predictive performance is tested on two different types of traffic data, Ethernet and MPEG4, at the same timescale. We find the predictions of MPM match the actual traffics accurately. Furthermore, we compare the MPM-based prediction technique to the SVM-based techniques. Results show that the predictive performance of MPM is competitive with SVM Key-Words: network traffic, minimax probability, support vector machine, prediction