A new false data injection attack detection model for cyberattack resilient energy forecasting

Ahmadi, A, Nabipour, M, Taheri, S, Mohammadi-Ivatloo, B and Vahidinasab, V ORCID: https://orcid.org/0000-0002-0779-8727, 2022. A new false data injection attack detection model for cyberattack resilient energy forecasting. IEEE Transactions on Industrial Informatics. ISSN 1551-3203

Preview

Text 1519769_Vahidinasab.pdf - Post-print Download (29MB) | Preview

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 on a more accurate 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 paper proposes a novel data-driven FDI attack detection mechanism to automatically detect the intrusions and thus enrich the reliability and resilience of the energy forecasting systems. The proposed mechanism is based on cross-validation and least-squares providing accurate detection with low computational cost and high scalability without utilizing the model and parameters of the system. Effectiveness of the proposed detector is corroborated through six representative tree-based wind power forecasting models including decision tree, bagging, random forest, boosting, gradient boosting, and XGboost. Experiments indicate that corrupted data is properly located and removed, whereby the accuracy and generalizability of the final forecasts is recovered.

Item Type:	Journal article
Publication Title:	IEEE Transactions on Industrial Informatics
Creators:	Ahmadi, A., Nabipour, M., Taheri, S., Mohammadi-Ivatloo, B. and Vahidinasab, V.
Publisher:	IEEE
Date:	15 February 2022
ISSN:	1551-3203
Identifiers:	Number Type 10.1109/TII.2022.3151748 DOI 1519769 Other
Rights:	© Copyright 2022 IEEE - All rights reserved. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions:	Schools > School of Science and Technology
Record created by:	Linda Sullivan
Date Added:	23 Feb 2022 10:58
Last Modified:	23 Feb 2022 10:58
URI:	https://irep.ntu.ac.uk/id/eprint/45741

Actions (login required)

Edit View

Statistics

Views

Downloads