The short term load forecasting is very important to the security and stability operation of power systems. The prediction precision will influence the quality of power supply and the operation cost of power grid. In this paper, on the basis of the introduction and analysis of the existing short term load forecasting models, PSO-GM and PSO-SVM is applied to construct regional grid short term load combination forecasting model, which is useful to avoid the single forecasting risk and improve the prediction precision by taking all kinds of information in the system and reducing the random error. The experiment result shows that the presented forecasting method in this thesis is useful for the regional power grid both in theory and in practice.
|