June 23, 2023
Conference Paper

Leveraging High-Fidelity Datasets for Machine Learning-based Anomaly Detection in Smart Grids

Abstract

Data-driven intrusion detection systems are increasingly becoming essential for protecting critical cyber-physical infrastructure, such as the power grid, against the growing number of sophisticated cyber-attacks. The development of such tools is reliant on the availability of high-fidelity cyber-physical datasets that cover a diverse variety of potential cyber events. In this work, a high-fidelity smart grid platform is utilized to develop an extensive dataset, which is used to train and test a machine learning-based intrusion detection system. The evaluation of the developed IDS shows robust performance even when tested with statistically diverse test data not used in training.

Published: June 23, 2023

Citation

Hyder B., A. Ahmed, P.T. Mana, T.W. Edgar, and S. Niddodi. 2023. Leveraging High-Fidelity Datasets for Machine Learning-based Anomaly Detection in Smart Grids. In 11th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems (MSCPES 2023), May 9, 2023, San Antonio, TX, 1-6. Piscataway, New Jersey:IEEE. PNNL-SA-182076. doi:10.1109/MSCPES58582.2023.10123428

Research topics

Grid Resilience and Decarbonization
Grid Cybersecurity
Advanced Metabolomics