Medium and Long Term Load Forecasting of Regional Power Grid in the Context of Economic Transition

In allusion to the saturated trend of load growth in the context of economic transition, a saturated load forecasting method is proposed in this paper. In the proposed method, main indices which affect the power load growth are screened by gray correlation analysis and co-integration theory. According to these indices, regression model and support vector machine (SVM) are established. Then Logistic model and grey Verhulst model (GVM) are applied based on regional load growth. In order to improve the prediction precision, this paper proposes a combination forecasting model based on Multi-Attribute Decision-making and nonlinear programming algorithm. The comparison between the prediction result and the “13th Five-Year” planning report indicates that, the load growth forecast becomes gentle within a forecast range of the planning report, which proves the effectiveness of the proposed method.