Prediction to Investment Demand of Power Grid Based on the Cuckoo Search and Support Vector Machine

Abstract

Prediction model based on support vector machine (SVM) optimized by cuckoo search algorithm (CS) is proposed to cope with the investment need of power grid. First of all, grey relational analysis was employed to select eight factors from various influencing factors of investment need of power grid as input to the prediction model. Then, the SVM was used to establish the prediction model of investment need, and the CS algorithm was introduced to optimize the parameters of SVM to improve the prediction accuracy of the model. Finally, a set of data is selected to test the prediction accuracy of model, and the results show that the prediction model has high prediction accuracy in short-term prediction of investment need of power grid. This method could provide reference for power grid enterprises to make scientific investment decisions.