(University of Texas at Dallas) This dataset is part of the PowerBench benchmark suite designed to support machine learning research in resilient and secure power distribution networks. It includes two out of the three types of cyberattacks modeled on IEEE 34-bus, 123-bus, and 8500-node test feeders: Sensor Attacks and PV Attack. Sensor attacks include dversarial manipulation of voltage measurements from grid sensors and supports time series anomaly detection, graph classification, and sensor-level localization. PV Attacks include adversarial manipulation of the control system associated with grid-connected PV systems and false data injection on the point of common coupling (PCC) meters and enables detection of cyberattacks and localization of compromised PV systems. Each attack dataset contains .pkl simulation files, .gml grid topology, and scenario metadata. All simulations were generated using OpenDSS via OpenDSSDirect.py.
Link to Dataset
PowerBench Dataset – Part 2: Cyber Attacks on PVs and Sensors
Date last updated: May 14, 2025