The Calculation Of Energy Loss In Distribution Systems Based On Improved Support Vector Machines

As the terminal of an electric network, the distribution network is directly connected with the users. It is characterized with wide spread line, low voltage level, many devices on the line. Energy Loss of distribution takes up considerable ratio in the general network. Picking out the potential is very important to the efficiency of supply enterprises.Firstly, the paper does much research on the characteristic of Energy Losses in Distribution Systems. Then the Energy Losses in Distribution Systems model of Support Vector Machines(SVM) which parameters are determined by across-validation is studied, and its such defects as hard sledding, time-consuming, blindness, unable to select the parameters automatically and so on are found. The influence of features selection of samples to calculate accuracy is also studied.To aim at the defects of parameters selection of SVM with across validation, finally, the paper solves the problem of automatically selection of SVM parameters. A Energy Losses in Distribution Systems model based on SVM is presented in which the parameters in SVM are optimized by Particle Swarm Optimizer (PSO). The experimental results prove its more excellent accuracy than ordinary SVM load forecasting method.