RobustSTL and Machine-Learning Hybrid to Improve Time Series Prediction of Base Station Traffic

Abstract

Green networking is currently becoming an urgent compulsion applied for cellular network architecture. One of the treatments that can be undertaken to fulfill such an objective is a traffic-aware scheme of a base station. This scheme can control the power consumption of the cellular network based on the number of demands. Then, it requires an understanding of estimated traffic in future demands. Various studies have undertaken experiments to obtain a network traffic prediction with good accuracy. However, dynamic patterns, burstiness, and various noises hamper the prediction model from learning the data traffic comprehensively. Furthermore, this paper proposes a prediction model using deep learning of one-dimensional deep convolutional neural network (1DCNN) and gated recurrent unit (GRU). Initially, this study decomposes the network traffic data by RobustSTL, instead of standard STL, to obtain the trend, seasonal, and residual components. Then, these components are fed into the 1DCNN-GRU as input data. Through the decomposition method using RobustSTL, the hybrid model of 1DCNN-GRU can completely capture the pattern and relationship of the traffic data. Based on the experimental results, the proposed model overall outperforms the counterpart models in MAPE, RMSE, and MAE metrics. The predicted data of the proposed model can follow the patterns of actual network traffic data.