Assessment of Line Loss Rate in Low-Voltage Transformer District Based on BP Network Model Optimized by LM Algorithm
A novel method of assessing line loss rate in transformer district is presented and realized by programming, which is BP network model based on LM algorithm. The pretreatment of samples by K-Means clustering algorithm according to electric characteristics solves the numerical dispersion of line loss rate in transformer district. On this basis, each class is trained by BP network optimized by LM algorithm. BP network is adopted to map complex non-linear relation between line loss rate and electric characteristic parameters. Variation of transformer district line loss rate is obtained under different grid structures and load characteristic parameters. 601 transformer districts in a region as an example, simulation and calculation are performed to verify the accuracy of the proposed method. This method has the advantages of fast convergence and high accuracy, compared to standard BP neural network.
low voltage transformer district line loss rate electric characteristics BP network with LM algorithm
Li-ping LIU Ya LI Bai-qing LI Ze-zhong WANG Shi-ming TIAN
China Electric Power Research Institute,Haidian District,Beijing 100192 School of Electrical and Electronic Engineering,North China Electric Power University,Changping Dist
国际会议
西安
英文
1-5
2016-09-01（万方平台首次上网日期，不代表论文的发表时间）