Village electrical load prediction by genetic algorithm and SVR

Prediction of village electrical load is very important to manage village electrical load efficiently. Support vector regression (SVR) is a new learning algorithm based on statistical learning theory, which has a good time-series forecasting ability. As the choice of the best parameters of support vector regression is an important problem for support vector regression, and this problem will directly affect the regression accuracy of support vector regression model. Therefore, the GA-SVR predicting model is developed to predict village electrical load. The comparison results show that the new GA-SVR model can successfully gain the lowest prediction error values in electricity load forecasting.