Digital twin application for attach detection and mitigation of PV-based smart systems using fast and accurate hybrid machine learning algorithm. (15th January 2023)

• Record Type: Journal Article
• Authors: Shen, Zhongjie; Xu, Wenqing; Li, Weikai; Shi, Yaoyao; Gao, Fan
• Is Part Of: Solar energy. Volume 250(2023)
• Page Start: 377
• Page End: 387
• Publication Date: 2023-01-15
• Subjects: Cyber security -- Hybrid microgrids -- Sequential hypothesis testing; Solar energy -- Periodicals; Solar engines -- Periodicals; 621.47
• DOI: 10.1016/j.solener.2023.01.007
• Languages: English
• ISSNs: 0038-092X

Abstract

Highlights: An analysis of the system's effectiveness and the attacks' impacts from both a financial and social standpoint has been presented. Wald's Sequential hypothesis testing (SHT) process is used to propose a straightforward approach for detecting DIA. SHTs are widely used in the manufacturing sector to detect defective parts. Abstract: Microgrids (MG) is originally designed to make Smart Grids more energy-efficient and reliable. The MG represents a complex cyber-physical system whose functioning is driven by the interaction of physical actions and computational elements, making it vulnerable to many forms of malicious cyber-attack. This study considers the effect of data integrity attack (DIA) on the performance of hybrid MGs, an important cyber threat to microgrids (MGs). Further, this paper develops a new process using sequential hypothesis testing (SHT) for detecting DIA on renewable energy resources and improving the security of information in hybrid MGs. By using a binary sample generated from the suggested approach, an analysis statistic is computed and afterward compared to 2 thresholds for deciding between the 3 options. On the measured energy production of renewable energy sources such as wind turbines, DIAs of various severity levels have been conducted for assessing the impact of DIAs on hybrid MG security. A standard IEEE test system has been used to evaluate the efficiency of the suggested process.