Line loss is inherent in transmission and distribution stages, which can cause certain impacts on the profits of power-supply corporations. Thus, it is an important indicator and a benchmark value of which is needed to evaluate daily line loss rates in low voltage transformer regions. However, the number of regions is usually very large, and the dataset of line loss rates contains massive outliers. It is critical to develop a regression model with both great robustness and efficiency when trained on big data samples. In this case, a novel method based on robust neural network (RNN) is proposed. It is a multi-path network model with denoising auto-encoder (DAE), which takes the advantages of dropout, L2 regularization and Huber loss function. It can achieve several different outputs, which are utilized to compute benchmark values and reasonable intervals. Based on the comparison results, the proposed RNN possesses both superb robustness and accuracy, which outperforms the testing conventional regression models. According to the benchmark analysis, there are about 13% outliers in the collected dataset and about 45% regions that hold outliers within a month. Hence, the quality of line loss rate data should still be further improved.

The system architecture and method for monitoring and statistical analysis of the line losses of the transformer region are introduced. The statistical method for the current system is adopted to determine the functional relationship between the statistical line loss, statistical line loss rate, and gateway power supply of the transformer region. Moreover, the trend of the parameters in a typical residential area is analyzed. Based on the analysis, the three reasons for the formation of transformer regions with a reasonable rate of line loss and the measures for the unreasonable rates are summarized. It is recommended that the line loss monitoring and analysis system should include the functions of approval, examination, and verification, as well as automatic identification. The transformer region without any abnormality in the line loss should be exempt from the review. For the transformer region with a residential elevator, however, the statistical rules should be modified to calculate the actual line loss rate. Finally, the challenges in the management of the transformer region with a negative line loss rate are presented. It is concluded that the application of transformer–customer relationship automatic identification technology and artificial intelligence abnormality diagnosis can significantly improve the efficiency of line loss management.

No abstract

No abstract

No abstract