A New Method Based on Symbolic Regression to Detect The Probability of False Data Injection Attacks on PV Generation

Created by W.Langdon from gp-bibliography.bib Revision:1.7656

@InProceedings{Moradpour:2023:SGC,

• author = "Amir Mohammad Moradpour and Mohammad Hossein Alizadeh and Hamed Delkhosh",
• booktitle = "2023 13th Smart Grid Conference (SGC)",
• title = "A New Method Based on Symbolic Regression to Detect The Probability of False Data Injection Attacks on {PV} Generation",
• year = "2023",
• abstract = "The increasing penetration of renewable energy resources, such as photovoltaic (PV) systems, has caused significant concerns in power systems. As one of theses concerns, the escalating number of reported cyber-attacks worldwide raises major issues about the operation of PV systems, as it may potentially jeopardize the operation of their connected power systems, especially during contingencies. One attack that seriously threatens cyber-physical systems is False Data Injection (FDI). This paper examines and analyses the detection of data manipulation in a PV power plant using Genetic Programming (GP), where a data-driven symbolic regression-based power generation forecasting is used and a hybrid probability-based FDI attack detection method is proposed. This method effectively enhances the FDI attack detection speed without sacrificing the accuracy. The presented method has been implemented on the real data set of a PV power plant, and the results show the effectiveness of the proposed model.",
• keywords = "genetic algorithms, genetic programming, Photovoltaic systems, Training, Renewable energy sources, Prediction algorithms, Hybrid power systems, Photovoltaic, Cyber Attack, False Data Injection Attack",
• DOI = "doi:10.1109/SGC61621.2023.10459279",
• ISSN = "2572-6927",
• month = dec,
• notes = "Also known as \cite{10459279}",

}

Genetic Programming entries for Amir Mohammad Moradpour Mohammad Hossein Alizadeh Hamed Delkhosh

Citations