Quantifying Robustness: A Benchmarking Framework for Deep Learning Forecasting in Cyber-Physical Systems
By: Alexander Windmann , Henrik Steude , Daniel Boschmann and more
Potential Business Impact:
Makes computer predictions more reliable in factories.
Cyber-Physical Systems (CPS) in domains such as manufacturing and energy distribution generate complex time series data crucial for Prognostics and Health Management (PHM). While Deep Learning (DL) methods have demonstrated strong forecasting capabilities, their adoption in industrial CPS remains limited due insufficient robustness. Existing robustness evaluations primarily focus on formal verification or adversarial perturbations, inadequately representing the complexities encountered in real-world CPS scenarios. To address this, we introduce a practical robustness definition grounded in distributional robustness, explicitly tailored to industrial CPS, and propose a systematic framework for robustness evaluation. Our framework simulates realistic disturbances, such as sensor drift, noise and irregular sampling, enabling thorough robustness analyses of forecasting models on real-world CPS datasets. The robustness definition provides a standardized score to quantify and compare model performance across diverse datasets, assisting in informed model selection and architecture design. Through extensive empirical studies evaluating prominent DL architectures (including recurrent, convolutional, attention-based, modular, and structured state-space models) we demonstrate the applicability and effectiveness of our approach. We publicly release our robustness benchmark to encourage further research and reproducibility.
Similar Papers
Data-Driven Falsification of Cyber-Physical Systems
Cryptography and Security
Finds hidden dangers in self-driving cars.
A review on modelling, evaluation, and optimization of cyber-physical system reliability
Systems and Control
Makes smart systems work without breaking.
Graph Analytics for Cyber-Physical System Resilience Quantification
Cryptography and Security
Finds weak spots in smart systems to stop attacks.