Study on Novel Algorithm Based on Time Series in Power System Load Forecasting

Because power load system was an uncertain, nonlinear, dynamic and complicated system, it was difficult to describe such a nonlinear characteristics of this system by traditional methods, so the load forecasting could not be accurately forecasted. An evolutionary Support Vector Machines (SVM) algorithm based on time sequence was brought forward in the paper. The algorithm avoided traditional model of SVM to control the kernel function and parameters and found the local and global optimization with Simplex-Niche-Genetic algorithm, which was more generalized and its dependence on experience was weakened. In the time sequence the trend component and periodical component were considered to make the load forecasting model more coincident with the features of power loads. Applying the presented method to actual load forecasting, the comparison among the forecasted results and the true shows that the presented method is inferior to none, feasible and effective.