Towards Implementing ML-Based Failure Detectors

TL;DR

This paper investigates the potential of machine learning, specifically LSTM neural networks, for failure detection, demonstrating promising accuracy and detection speed despite higher computational costs.

Contribution

It presents a prototype implementation of an ML-based failure detector using LSTM, showing its feasibility and performance with real data traces.

Findings

ML-based detector achieves high accuracy

Detection time is acceptable despite longer computation

Prototype demonstrates viability of ML in failure detection

Abstract

Most existing failure detection algorithms rely on statistical methods, and very few use machine learning (ML). This paper explores the viability of ML in the field of failure detection: is it possible to implement an ML-based detector that achieves a satisfactory quality of service? We implement a prototype that uses a basic long short-term memory neural network algorithm, and study its behavior with real traces. Although ML model has comparatively longer computing time, our prototype performs well in terms of accuracy and detection time.