Sequential Data Learning, Scalable Models And Adversarial Regularization

This thesis proposes a novel method of predicting mobile network traffic using neural networks based on conditional probability modeling between adjacent data windows in the time series sequence. A pre-processing method is developed to aggregate the raw traffic log data and sample the aggregated time series to adjacent data windows, as training samples. Neural networks are used to parameterize the conditional probability between adjacent data windows and estimate the probability by training the neural networks with sampled data. Experiments are conducted to compare the prediction performance among the models with different seasonality, sample size and number of hidden layers, and the proposed schemes achieve better prediction accuracy than state-of-the-art.