Proceedings ArticleDOI
Evaluation of network traffic prediction based on neural networks with multi-task learning and multiresolution decomposition
Melinda Barabas,Georgeta Boanea,Andrei Bogdan Rus,Virgil Dobrota,Jordi Domingo-Pascual +4 more
- pp 95-102
TLDR
Comparisons of predictions produced by different types of neural networks with forecasts from statistical time series models show that nonlinear prediction based on NNs is better suited for traffic prediction purposes than linear forecasting models.Abstract:
Network traffic exhibits strong correlations which make it suitable for prediction. Real-time forecasting of network traffic load accurately and in a computationally efficient manner is the key element of proactive network management and congestion control. This paper compares predictions produced by different types of neural networks (NN) with forecasts from statistical time series models (ARMA, ARAR, HW). The novelty of our approach is to predict aggregated Ethernet traffic with NNs employing multiresolution learning (MRL) which is based on wavelet decomposition. In addition, we introduce a new NN training paradigm, namely the combination of multi-task learning with MRL. The experimental results show that nonlinear prediction based on NNs is better suited for traffic prediction purposes than linear forecasting models. Moreover, MRL helps to exploit the correlation structures at lower resolutions of the traffic trace and improves the generalization capability of NNs.read more
Citations
More filters
Posted Content
A Long Short-Term Memory Recurrent Neural Network Framework for Network Traffic Matrix Prediction
Abdelhadi Azzouni,Guy Pujolle +1 more
TL;DR: This paper proposes a LSTM RNN framework for predicting short and long term Traffic Matrix (TM) in large networks and validates the framework on real-world data from GEANT network, showing that the LSTm models converge quickly and give state of the art TM prediction performance for relatively small sized models.
Proceedings ArticleDOI
NeuTM: A neural network-based framework for traffic matrix prediction in SDN
Abdelhadi Azzouni,Guy Pujolle +1 more
TL;DR: NeuTM as mentioned in this paper is a LSTM RNN-based framework for predicting traffic matrix in large networks, which is well suited to learn from data and classify or predict time series with time lags of unknown size.
Proceedings ArticleDOI
Applying deep learning approaches for network traffic prediction
TL;DR: This work uses various RNN networks to leverage the efficacy of RNN approaches towards traffic matrix estimation in large networks, and finds LSTM has performed well in comparison to the other RNN and classical methods.
Posted Content
NeuTM: A Neural Network-based Framework for Traffic Matrix Prediction in SDN
Abdelhadi Azzouni,Guy Pujolle +1 more
TL;DR: NeuTM as mentioned in this paper is a LSTM RNN-based framework for predicting traffic matrix in large networks, which is well suited to learn from data and classify or predict time series with time lags of unknown size.
Journal ArticleDOI
Deep Learning for Network Traffic Monitoring and Analysis (NTMA): A Survey
TL;DR: In this paper, a comprehensive review on applications of deep learning in network traffic monitoring and analysis (NTMA) applications is provided, where the authors discuss key challenges, open issues, and future research directions for using deep learning for NTMA applications.
References
More filters
Journal ArticleDOI
Introduction to Time Series and Forecasting.
TL;DR: A general approach to Time Series Modelling and ModeLLing with ARMA Processes, which describes the development of a Stationary Process in Terms of Infinitely Many Past Values and the Autocorrelation Function.
Proceedings ArticleDOI
Study on network traffic prediction techniques
Huifang Feng,Yantai Shu +1 more
TL;DR: This work compares the performance of traffic predictors with MSE, NMSE and computational complexity by simulating the predictors on four wireless network traffic traces and decides the most suitable network traffic predictor based on acceptable performance and accuracy.
Proceedings ArticleDOI
Internet Traffic Forecasting using Neural Networks
TL;DR: A neural network ensemble (NNE) for the prediction of TCP/IP traffic using a time series forecasting (TSF) point of view and is competitive when compared with other TSF methods (e.g. Holt-Winters and ARIMA).
Journal ArticleDOI
Real-time VBR video traffic prediction for dynamic bandwidth allocation
TL;DR: It is shown that neural network traffic predictor trained through the multiresolution learning (called multiresolutions learning NN traffic predictor) can successfully predict various real-world VBR video traffic up to hundreds of frames in advance, which then lays a solid foundation for predictive dynamic bandwidth control and allocation mechanism.
Journal ArticleDOI
Improving signal prediction performance of neural networks through multiresolution learning approach
Yao Liang,Xu Liang +1 more
TL;DR: This paper presents systematically new analytical and experimental results on the multiresolution learning approach for training an individual neural network model, demonstrates the integral solution on neural network learning efficacy, and illustrates the significant improvements on neural networks' generalization performance and robustness for nonlinear signal predictions.
Related Papers (5)
NeuTM: A neural network-based framework for traffic matrix prediction in SDN
Abdelhadi Azzouni,Guy Pujolle +1 more