Machine Learning for Cyber-Physical Event Detection in Smart Grids

Modern power grids combine electrical infrastructure with communication and control systems. This creates new risks: cyber attacks can mimic real grid disturbances. In this project, you will use machine learning to distinguish normal operation, faults, and cyber events using publicly available industrial control system datasets.

What you’ll do

• Reproduce a published ML pipeline (literature-based baseline) [1][2]
• Train and evaluate classifiers for event detection
• Analyze explainability (e.g., feature importance / SHAP-style reasoning)
• Extend the baseline (robustness, new models, better evaluation)

What you’ll learn

• Applied machine learning on real-world energy system data
• Smart grid cybersecurity basics (ICS / OT perspective)
• Reproducible research workflows and evaluation