Short-term load prediction method for power system

The invention relates to a short-term load prediction method for a power system, and the method comprises the steps: collecting a short-term load curve of the power system and a related impact factor historical data curve; decomposing the short-term load curve and the related influence factor historical data curve of the power system for n times, and obtaining n components for each signal; calculating a function expression of each component of the short-term load of the power system based on a support vector machine (SVM), calculating the weight of each component according to a least square method, and constructing a short-term load prediction model of the power system; and (3) collecting temperature, humidity and dew point data curves of the short-term load of the power system in the next 24 hours, carrying out n-time decomposition, inputting into the step (3), and outputting a result through the short-term load prediction model of the power system. According to the method, the short-term load of the power s