Cybersecurity Assessment of Smart Grid Exposure Using a Machine Learning Based Approach
Mofe O. Jeje
TL;DR
The paper addresses escalating cyber threats to smart grids, focusing on secure, real-time assessment of disturbances in synchrophasor-enabled power systems. It deploys an XGBoost classifier with SHAP-based explanations on a Mississippi State University and Oak Ridge National Laboratory dataset to classify events into No-Events, Natural Events, and Attack Events. The methodology includes data preprocessing, 80/20 train-test splits, hyperparameter tuning, and a feature-importance-driven reduction to 10 features, achieving high accuracy across sub-datasets (e.g., 99% for Natural+No-Events, 85% for Attacks+Natural, and 97% for Attack+No-Events) with strong F1 scores. The work demonstrates the practicality of interpretable, data-driven cybersecurity assessment for smart grids and points to future work on expanding features and dataset size as well as speed-accuracy trade-offs.
Abstract
Given that disturbances to the stable and normal operation of power systems have grown phenomenally, particularly in terms of unauthorized access to confidential and critical data, injection of malicious software, and exploitation of security vulnerabilities in a poorly patched software among others; then developing, as a countermeasure, an assessment solutions with machine learning capabilities to match up in real-time, with the growth and fast pace of these cyber-attacks, is not only critical to the security, reliability and safe operation of power system, but also germane to guaranteeing advanced monitoring and efficient threat detection. Using the Mississippi State University and Oak Ridge National Laboratory dataset, the study used an XGB Classifier modeling approach in machine learning to diagnose and assess power system disturbances, in terms of Attack Events, Natural Events and No-Events. As test results show, the model, in all the three sub-datasets, generally demonstrates good performance on all metrics, as it relates to accurately identifying and classifying all the three power system events.