Deep Learning Models For Aggregated Network Traffic Prediction

Aggelos Lazaris, Viktor K. Prasanna

In Proc. of the 15th International Conference on Network and Service Management (CNSM), Halifax, Canada, October 2019

PDF BibTeX

Overview

Predicts link-level throughput across a backbone network seconds ahead using LSTMs trained on statistics that SDN controllers or SNMP already collect.

Key contributions

• Analysis of how well LSTMs model aggregated traffic at different aggregation levels and short time scales.
• Prediction framework deployable on production SDN or legacy networks without extra instrumentation.
• Per-link LSTMs train in about 30 seconds and cut error by up to 2x compared with ARIMA baselines on Tier-1 ISP traces.

Abstract

The ability to generate network traffic predictions at short time scales is crucial for many network management tasks such as traffic engineering, anomaly detection, and traffic matrix estimation. However, building models that are able to predict the traffic from modern networks at short time scales is not a trivial task due to the diversity of the network traffic sources. In this paper, we present a framework for network-wide link-level traffic prediction using Long Short-Term Memory (LSTM) neural networks. Our proposed framework leverages link statistics that can be easily collected either by the controller of a Software Defined Network (SDN), or by SNMP measurements in a legacy network, in order to predict future link throughputs. We implement several variations of LSTMs and compare their performance with traditional baseline models. Our evaluation study using real network traces from a Tier-1 ISP illustrates that LSTMs can predict link throughputs with very high accuracy outperforming the baselines for various traffic aggregation levels and time scales.

Cite this paper

@article{lazariscnsm,
	author    = {Aggelos Lazaris and Viktor K. Prasanna},
    title={Deep Learning Models For Aggregated Network Traffic Prediction},
  	booktitle = {Proceedings of the 15th International Conference on Network and Service Management {CNSM}, Halifax, Canada, 21-25 October 2019}, 
    year      = {2019},
}