Work

Descriptor: Power Systems Cascading Failure Analysis Synthetic Dataset (PowerCascade)

Year: 2025

Type: article

Abstract: The stability and reliability of power systems are critical concerns in modern energy infrastructure. However, as the power grid becomes more complex, the risk of cascading failures increases. To effectively address this challenge, we introduce a dataset designed to support research on the application of artificial intelligence (AI) for learning and analyzing the propagation of cascading failures. ThisPowerCascadedataset includes a large number of cascading events simulated using a realistic power grid model. Each event records a sequence of component failures under one of three predefined loading conditions, providing valuable insights into grid dynamics under varying operational scenarios. By offering comprehensive information on both static grid parameters and dynamic information of failure propagation, this dataset serves as a valuable resource for researchers aiming to enhance grid resilience and develop more effective strategies for predicting and mitigating cascading failures. Furthermore, we believe the dataset’s inherent characteristics can also inspire research in related fields such as computer science, particularly in applying AI to complex network systems using graph neural networks and techniques for imbalanced learning.

Source: IEEE data descriptions.

DOI: 10.1109/ieeedata.2025.3595833

Authors: Tingwei Chen, Zhenping Guo, Kaiyang Huang, Kai Sun

Institution: University of Tennessee at Knoxville

Language: English

Topic: Power System Optimization and Stability

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: hybrid

Estimated APC paid: $600