Amirhossein Ahmadi
A New False Data Injection Attack Detection Model for Cyberattack Resilient Energy Forecasting
Ahmadi, Amirhossein; Nabipour, Mojtaba; Taheri, Saman; Mohammadi-Ivatloo, Behnam; Vahidinasab, Vahid
Authors
Mojtaba Nabipour
Saman Taheri
Behnam Mohammadi-Ivatloo
Prof Vahid Vahidinasab V.Vahidinasab@salford.ac.uk
Professor
Abstract
As power systems are gradually evolving into more efficient and intelligent cyber–physical energy systems with the large-scale penetration of renewable energies and information technology, they become increasingly reliant upon more accurate and complex forecasting. The accuracy and generalizability of the forecasting rest, to a great extent, upon the data quality, which is very susceptible to cyberattacks. False data injection (FDI) attacks constitute a class of cyberattacks that could maliciously alter a large portion of supposedly protected data, which may not be easily detected by existing operational practices, thereby deteriorating the forecasting performance causing catastrophic consequences in the power system. This article proposes a novel data-driven FDI attack detection mechanism to automatically detect the intrusions and thus enrich the
reliability and resiliency of energy forecasting systems. The proposed mechanism is based on cross-validation, least squares, and z-score metric providing accurate detections with low computational cost and high scalability without utilizing either system’s models or parameters. The effectiveness of the proposed detector is corroborated through six representative tree-based wind power forecasting models. Experiments indicate that corrupted data injected into input, output, and input–output data is properly located and removed, whereby the accuracy and generalizability of the final forecasts are recovered.
| Journal Article Type | Article |
|---|---|
| Acceptance Date | Feb 4, 2022 |
| Publication Date | 2023-01 |
| Deposit Date | Feb 19, 2025 |
| Journal | IEEE Transactions on Industrial Informatics |
| Print ISSN | 1551-3203 |
| Publisher | Institute of Electrical and Electronics Engineers |
| Peer Reviewed | Peer Reviewed |
| Volume | 19 |
| Issue | 1 |
| Pages | 371-381 |
| DOI | https://doi.org/10.1109/tii.2022.3151748 |