A method of evaluating 10kV Distribution Network Line Losses Based on Intelligent Algorithm

摘要

To estimate the level of 10kV distribution network line losses more integrally and precisely, an evaluation method based on BP neural network (BPNN) improved by particle swarm optimization (PSO) has been proposed. Making full use of existing data resources in the State Grid Corporation of China, the relevant information in the process of10 kV distribution network line and line loss has been collected and integrated, to formulate the power grid equipment data and operation data in the process of power distribution and utilization. Firstly, the electrical characteristic indices have been selected and established to reflect the structure and operation state of 10kV distribution network. Secondly, the inertia weight and the acceleration coefficient of PSO have been dynamically adjusted so that the weights and biases of BPNN are searched more effectively. Then nonlinear relation between electrical characteristic indexes and line losses is fitted through the learning of training sample sets so as to predict the line losses of test sample sets. Finally, the PSO-BPNN is proved to be effective and proper through an actual 10kV distribution network sample data.