Threat Detection in Power Grid Based on Hierarchical Feature Cloud Computing Model

• Published in: IOP conference series. Materials Science and Engineering Vol. 750; no. 1; pp. 12157 - 12162
• Main Authors: Li, Jing, Huang, Jie, Liu, Fen
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.02.2020
• Subjects: Algorithms; Cloud computing; Cloud Computing Models; Feature Clouds; Feature extraction; Insider Threats; Mapping; Operators; Power Characteristics; Threats
• ISSN: 1757-8981; 1757-899X; 1757-899X
• DOI: 10.1088/1757-899X/750/1/012157

The extraction of subjective features such as the authority, purpose, and opportunity of power network operators has outstanding subjectivity. It is difficult to accurately quantify subjective features due to the subjective factors of operators, resulting in fuzzy subjective features. Traditional algorithms use subjective features to detect internal threats to the power grid. Once subjective factors interfere, they will cause the defects of fuzzy main features, leading to a decrease in the accuracy of threats to the internal power grid. This paper focuses on the detection of power grid internal threats based on a hierarchical feature cloud computing model. This paper proposes a power network internal threat detection method based on the hierarchical feature cloud mapping model; calculates the hierarchical mapping relationship based on the internal threat features to complete the internal threat detection of the power grid; experiments prove that the algorithm avoids subjective factors being affected by subject characteristics, and The ambiguity of features reduces the missed detection rate to below 15.3%.