Automating Network Error Detection using Long-Short Term Memory Networks

TL;DR

This paper explores using Long-Short Term Memory networks to improve network error detection by providing intelligent message clustering and temporal causality understanding, achieving 70% classification accuracy.

Contribution

It demonstrates that LSTMs outperform K-Means in classifying and clustering network messages, enabling proactive error warning capabilities.

Findings

LSTMs achieve 70% accuracy in error classification.

LSTMs provide meaningful temporal clustering of messages.

LSTMs enable visualization of temporal causality.

Abstract

In this work, we investigate the current flaws with identifying network-related errors, and examine how K-Means and Long-Short Term Memory Networks solve these problems. We demonstrate that K-Means is able to classify messages, but not necessary provide meaningful clusters. However, Long-Short Term Memory Networks are able to meet our goals of providing an intelligent clustering of messages by grouping messages that are temporally related. Additionally, Long-Short Term Memory Networks can provide the ability to understand and visualize temporal causality, which unlocks the ability to warn about errors before they happen. We show that LSTMs have a 70% accuracy on classifying network errors, and provide some suggestions on future work.