A transient fault data management algorithm for low-voltage station based on overall situation power big data

• Published in: Applied nanoscience 2023-03, Vol.13 (3), p.2463-2471
• Main Authors: Zheng, Sida, Cheng, Jie, Xiong, Hongzhang, Wang, Yanjin, Wang, Yuning
• Format: Article
• Language: English
• Subjects: Algorithms; Big Data; Chemistry and Materials Science; Data management; Data mining; Electrical surges; Fault detection; Mapping; Materials Science; Membrane Biology; Nanochemistry; Nanotechnology; Nanotechnology and Microengineering; Optimization; Original Article
• ISSN: 2190-5509; 2190-5517
• DOI: 10.1007/s13204-022-02347-3

In view of the problem that the transient fault data in low-voltage area is easily affected by objective noise because of the large number of redundant mapping values and external interference, this paper proposes an algorithm for transient fault data management in low-voltage area based on overall situation power big data. This paper divides the global large data of transient fault in low-voltage station into line loss data and other data, and applies the big data mining algorithm to analyze the abnormal situation of voltage, current and instrument, to standardize the transient fault data in low-voltage station and filter the adaptive optimization, to ensure the attribute function dependence and reference constraint goal of data aggregation and to complete the transient fault data management in low-voltage station. The test results show that, the range of the value mapping is always between 0 and 1, which significantly alleviates the influence degree of low-voltage transient fault data affected by noise, improves the data access speed, and ensures the effectiveness of low-voltage transient fault detection.