Gaussian Process Regression Ensemble Model for Network Traffic Prediction

Abstract

Network traffic prediction is substantial for network optimization and resource management. However, designing an efficient predictive model considering different traffic characteristics, including periodicity, nonlinearity, and nonstationarity, is challenging. Recently, ensemble learning is attracting much attention from researchers in the machine learning community. Although ensemble learning has proven exceptional performance in modelling the intricate problems, it may not be able to handle varying patterns and chaotic behaviour, which are typical properties of traffic data (and many other time-series problems). For this reason, ensemble methods show a limited prediction accuracy in network traffic modelling. We address this issue by proposing an ensemble of learners for time-series prediction that considers the accuracy of individual learners as well as diversity among their outcomes. Each learner contributes to the optimization process by finding the optimal accuracy-diversity balance in a segment of feature space. This divideand-conquer approach avoids complicated objective functions with many local optimums while fitting the ensemble model on large datasets. Experimental results on the real traffic traces show our proposed method outperforms other state-of-the-art predictors with 12% on average in prediction accuracy for different datasets.

A Network Traffic Prediction Algorithm Based on Prophet-EALSTM-GPR

“…Du et al [18] proposed a data reconstruction prediction model based on empirical mode decomposition (EMD) and gated recursive unit (GRU) neural networks to address the lack of more accurate and comprehensive characterization of network traffic in existing studies. Bayati et al [19] designed an efficient prediction model considering different traffic characteristics, including periodic, nonlinear, and non-stationary. An ensemble of learners is proposed in which each learner is optimized by finding the optimal accuracy diversity balance in the feature space.…”

Network Traffic Modeling and Prediction Using Graph Gaussian Processes

“…In [21], a GP model is used to capture a quasi-periodic pattern. In [22], the authors developed an enesemble learning algorithm where each learner is modeled by a GP and the predictions of the GPs are combined to improve the prediction accuracy. In [23] the alternating direction method of multipliers (ADMM) algorithm is used for parallel hyper-parameter optimization to scale up the GP inference.…”

Gaussian Processes for Traffic Speed Prediction at Different Aggregation Levels

“…As one of the machine learning regression techniques, Gaussian Processes are fundamentally researched in may fields [3] especially wireless network traffic [4]. In traffic prediction problems, they are applied to flow prediction [5], [6].…”

“…However, with only spatial correlations and categorical tags, performances are very similar to K-means or other clustering algorithms. Most similar paper to this study is from wireless network prediction [4]. Authors compared GP-based regressions against time series and neural networks (NN) over different aggregation levels up to 30 minutes.…”