Application of SVM Method with Meteorological Factors in Power Load Forecasting

Scientific load forecasting is of great significance for smart grid to improve energy utilization efficiency and power supply reliability. At the same time, with the improvement of people's living conditions and the large number of applications of heating and refrigeration equipment, the proportion of meteorological load in the total load is increasing, and the influence of meteorological factors on the power load is also more significant. Therefore, to study the relationship between meteorology and load and improve the accuracy of short-term load prediction has become a hot and difficult issue for scholars in the industry. As a new data mining technology, support vector machine (SVM) has attracted more and more attention in many research fields. In this paper, a short term load forecasting method of power system based on support vector machine is studied by taking advantage of the excellent nonlinear learning and forecasting performance of support vector machine, aiming at the nonlinear characteristics of various influencing factors in short term load forecasting. The prediction examples show that the support vector machine method considering meteorological factors can improve the prediction accuracy and improve the disaster resistance ability of power grid effectively.