Identification of market power abuse in China's electricity market. Issue 1 (January 2020)

• Record Type: Journal Article
• Authors: Cheng, Ziyun; Li, Hao; Xu, Huihui; Dong, Li; Tao, Hongyuan; Hua, Huichun; Wang, Shenghua
• Is Part Of: IOP conference series. Volume 740:Issue 1(2020)
• Publication Date: 2020-01
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/740/1/012077
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: The goal of this paper is to find a method to identify violations, which is suitable for China's electricity market. Therefore the key problems in the process were discussed, that is, the trading rules and marketization degree which were different from those of foreign countries. So this article has done the following works to solve the problems. Firstly, this paper classifies and compares the identification indexes of market power abuse, and analyzes the advantages and disadvantages of each index, based on which an index system is proposed. Secondly, An intelligent identification algorithm based on support vector machine(SVM) is introduced and improved to solve the data imbalance problem. Also, the index system and the improved SVM were combined to cover the economic principle as well as improve the identification efficiency at the same time. Taking the simulation data as an example, the rate of violation recognition reaches 100%, which indicates that the method proposed in this paper is feasible and effective.