Identification of Path Congestion Status for Network Performance Tomography using Deep Spatial-Temporal Learning

TL;DR

This paper proposes a deep learning framework combining adversarial autoencoders and LSTM networks to accurately identify and quantify congestion status in network links, improving over traditional threshold-based methods.

Contribution

It introduces the Additive Congestion Status concept and a novel deep learning approach for more precise congestion detection and localization in network tomography.

Findings

Enhanced congestion localization accuracy

Improved performance inference of network links

Effective categorization of congestion levels

Abstract

Network tomography plays a crucial role in assessing the operational status of internal links within networks through end-to-end path-level measurements, independently of cooperation from the network infrastructure. However, the accuracy of performance inference in internal network links heavily relies on comprehensive end-to-end path performance data. Most network tomography algorithms employ conventional threshold-based methods to identify congestion along paths, while these methods encounter limitations stemming from network complexities, resulting in inaccuracies such as misidentifying abnormal links and overlooking congestion attacks, thereby impeding algorithm performance. This paper introduces the concept of Additive Congestion Status to address these challenges effectively. Using a framework that combines Adversarial Autoencoders (AAE) with Long Short-Term Memory (LSTM) networks, this approach robustly categorizes (as uncongested, single-congested, or multiple-congested) and quantifies (regarding the number of congested links) the Additive Congestion Status. Leveraging prior path information and capturing spatio-temporal characteristics of probing flows, this method significantly enhances the localization of congested links and the inference of link performance compared to conventional network tomography algorithms, as demonstrated through experimental evaluations.