Research on support vector machine model based on grey relation analysis for daily load forecasting

Regarding to the daily load forecasting, the sample selection and data preprocessing are crucial to its precision. In this paper, the grey relation analysis method is adopted to search the historical data points whose variation trends are the same as the predict point. The variation trend of each point is represented by load values of the neighboring points. As no influencing factors are used in this process, the model is both simple and practical. Finally a support vector machine model is created on the basis of the selected data points. Due to their similar trends of the selected points, the forecasting precision is raised greatly. The present method synthesizes the advantages of grey relation analysis and support vector machine. The practical examples show that the model established in this paper is feasible and effective. Compared with other models, it has a better precision performance and a higher computing speed.