For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
Power distribution network line loss rate is an important indicator for assessing power companies, which directly affects the economic benefits of power companies. Therefore, accurate detection of line loss anomalies becomes an urgent problem for power companies to solve. In this paper, a line loss rate prediction model based on long-short term memory neural network was proposed. Anomaly detection was carried out through the line loss rate residual between the predicted line loss rate and the actual line loss rate, and a set of comparative experiments were designed. The comparative prediction algorithm included BP neural network and Radial Basis Function neural network. Simulation test was made with distribution network under the jurisdiction of a city power company, and the results showed that the prediction accuracy of long-short term memory neural networks is higher than that of other neural networks in the case of large data sets.
Inspec keywords: power distribution lines; power engineering computing; recurrent neural nets; backpropagation; power distribution economics; radial basis function networks; design of experiments; electricity supply industry; losses
Subjects: Other topics in statistics; Other topics in statistics; Power system management, operation and economics; Power engineering computing; Distribution networks; Neural nets