A Line Loss Prediction Method Based on Neural Network

Line loss rate is a comprehensive technical and economic index to measure the level of operation and management of electric power enterprises, the prediction of line loss rate plays a pivotal role in strengthening the management of the electric power system. In this paper, a method for predicting 10kV line losses based on grey correlation analysis and neural networks is proposed, and a line loss prediction model based on neural network is established; the optimal number of electrical characteristic indexes and hidden layer nodes of neural network models of different distribution networks is determined, which improves the prediction ability of neural network models and reduces the prediction error. Finally, the accuracy and effectiveness of the proposed prediction method are verified by programming a real distribution network prediction example. It has certain reference value for the prevention and reduction of high line loss in distribution network.