A research on line loss calculation based on BP neural network with genetic algorithm optimization. Issue 1 (February 2021)

• Record Type: Journal Article
• Authors: Jin, Yukun; Li, Zeng; Han, Yipin; Li, Xiaopeng; Li, Pingting; Li, Guangdi; Wang, Hao
• Is Part Of: IOP conference series. Volume 675:Issue 1(2021)
• Publication Date: 2021-02
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/675/1/012155
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: In order to realize the calculation of the line loss of the distribution network with complex structure and low-voltage station area, this paper presents a line loss calculation method based on BP neural network with genetic algorithm optimization. The proposed method is based on the actual operation data of the distribution network. Firstly, build an error back propagation (BP) neural network model to compute the theoretical line loss of the distribution network, then use genetic algorithm (GA) to optimize the neural network and establish the GA-BP model. Based on the proposed model, the calculation demonstrates that the neural network line loss rate calculation model with genetic algorithm optimization shows better performance than the single BP neural network model, such as better nonlinear fitting ability and higher calculation accuracy. Therefore, the line loss calculation method proposed in this paper based on the BP neural network with the genetic algorithm optimization can improve the accuracy of the distribution network line loss rate calculation model.