期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：252
期号：3
页码：1-8
DOI：10.1088/1755-1315/252/3/032095
出版社：IOP Publishing
摘要：Due to the complex network structure of the low-voltage distribution network, the backwardness of electrical equipment and the large number of nodes, it is difficult to calculate the line loss rate accurately. The author established a simple linear loss rate prediction model with higher accuracy. Firstly, according to the actual power operation data, the typical characteristic parameters with great influence are obtained. Secondly, the K-means clustering algorithm is applied to classify each transformer district according to the different power consumption characteristics. Finally, the BP neural network model based on LM numerical optimization algorithm is designed and applied to predict line loss rate for data class of each transformer district. 1026 transformer district with complete power operation data in a region was selected as an example to verify the accuracy of the proposed prediction method, which provides data and theoretical basis for the loss reduction measures.
