Realtime mobile bandwidth prediction using LSTM neural network and Bayesian fusion

With the increasing popularity of mobile Internet and the higher bandwidth requirement of mobile applications, user Quality of Experience (QoE) is particularly important. For applications requiring high bandwidth and low delay, such as video streaming, video conferencing, and online gaming, etc., if the future bandwidth can be estimated in advance, applications can leverage the estimation to adjust their data transmission strategies and significantly improve the user QoE. In this paper, we focus on accurate bandwidth prediction to improve user QoE. Specifically, We study realtime mobile bandwidth prediction in various mobile networking scenarios, such as subway and bus rides along different routes. The primary method used is Long Short Term Memory (LSTM) recurrent neural network. In individual scenarios, LSTM significantly improves the prediction accuracy of state-of-the-art prediction algorithms, such as Recursive Least Squares (RLS) by 12% in Root Mean Square Error (RMSE) and by 17% in Mean Average Error (MAE). We further developed Multi-Scale Entropy (MSE) to analyze the bandwidth patterns in different mobility scenarios and discuss its connection to the achieved accuracy. For practical applications, we developed Model Switching and Bayes Model Fusion to use pre-trained LSTM models for online realtime bandwidth prediction.