Icing load prediction for overhead power lines based on SVM

Abstract

The icing of overhead transmission lines is the main problem for the safety of power grid, It is necessary to establish the model of icing load prediction on overhead transmission lines. The prediction model utilizes the ambient temperature, humidity, wind speed, wind direction, sunlight and air pressure as training data of input, the icing load is the output of prediction model based on Support Vector Machine (SVM). According to the results of simulation, this model is available to the prediction of icing load, even in different process of icing in the same transmission line during a short time. So it is helpful for preventing the disaster of power grid and reducing of economic losses.