# Online Anomaly Detection in HPC Systems

## TL;DR

This paper presents an automated anomaly detection method for HPC systems using autoencoders, achieving high accuracy and minimal performance impact, addressing scalability issues in fault detection.

## Contribution

Introduces a neural network-based anomaly detection approach deployed on HPC nodes, enabling scalable, real-time fault detection without performance degradation.

## Key findings

- Achieves 90-95% detection accuracy.
- Deploys on HPC nodes without performance loss.
- Effective in real-world HPC environments.

## Abstract

Reliability is a cumbersome problem in High Performance Computing Systems and Data Centers evolution. During operation, several types of fault conditions or anomalies can arise, ranging from malfunctioning hardware to improper configurations or imperfect software. Currently, system administrator and final users have to discover it manually. Clearly this approach does not scale to large scale supercomputers and facilities: automated methods to detect faults and unhealthy conditions is needed. Our method uses a type of neural network called autoncoder trained to learn the normal behavior of a real, in-production HPC system and it is deployed on the edge of each computing node. We obtain a very good accuracy (values ranging between 90% and 95%) and we also demonstrate that the approach can be deployed on the supercomputer nodes without negatively affecting the computing units performance.