Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

TL;DR

This paper develops and optimizes deep learning models for spacecraft telemetry anomaly detection, enabling effective on-board analysis on highly constrained edge devices with minimal hardware resources.

Contribution

It introduces a multi-objective neural architecture optimization approach for deploying accurate anomaly detection models within strict hardware limitations on spacecraft.

Findings

Forecasting & threshold achieves 92.7% CEF0.5 detection performance.

Optimized models reduce RAM usage by 97.1% to 59 KB.

Deployment viability shown with models requiring only 0.36-6.25% of CubeSat RAM.

Abstract

Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.