Title :
Comprehensive evaluation of power quality based on meaningful classification
Author :
Zejun, Ding ; Yongqiang, Zhu ; Caihong, Chen
Author_Institution :
Sch. of Electr. & Electron. Eng., North China Electr. Power Univ., Beijing, China
Abstract :
In a liberalized electricity market, it is not surprising that different customers need different power quality levels with different price. So how to achieve the synthetic grading evaluation of power quality becomes a concerned problem. In this paper, the idea of classified evaluation of power quality is emphasized, and the major differences between the continuous and event-based power quality problems both in the characteristics and time scales are analyzed. In addition, least squares support vector machine (LSSVM) theory is applied to the comprehensive evaluation of continuous power quality. Meanwhile, power supply reliability index is introduced to evaluate the overall quality level of the event-based power quality. On this basis, subjective weighting method is used to achieve the comprehensive evaluation of two types of power quality problems. Comprehensive evaluation of power quality based on meaningful classification not only highlights the two types of power quality problems, but also achieves the overall level of power quality.
Keywords :
least squares approximations; power engineering computing; power markets; power supply quality; power system reliability; support vector machines; least squares support vector machine; liberalized electricity market; meaningful classification; power quality; power supply reliability index; subjective weighting method; synthetic grading evaluation; Biological system modeling; Economics; Power quality; Reliability; Support vector machines; Voltage fluctuations; Meaningful classification; comprehensive evaluation; least squares support vector machine; power quality; power supply reliability;
Conference_Titel :
Critical Infrastructure (CRIS), 2010 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-8080-7
DOI :
10.1109/CRIS.2010.5617506
