Electric Load Forecasting Use a Novelty Hybrid Model on the Basic of Data Preprocessing Technique and Multi-Objective Optimization Algorithm

Power load forecasting has an influence of great signification on improving the operational efficiency and economic benefits of the power grid system. Aiming at improving forecast performance, a substantial number of load forecasting models are proposed. However, these models have disregarded the limits of individual prediction models and the necessity of data preprocessing, resulting in poor prediction accuracy. In this article, a novelty hybrid model which combines data preprocessing technology, individual forecasting algorithm and weight determination theory is presented for obtaining higher accuracy and forecasting ability. In this model, an effective data preprocessing method named SSA is adopted to extract the load data characteristics and further improve the prediction performance. In addition, a combined forecasting mechanism composed of BP, SVM, GRNN and ARIMA is successfully established using the weight determination theory, which exceeds the limits of individual prediction models and comparatively improves prediction accuracy. And the thought of combine linear and nonlinear model together can further take the advantage of two kinds of models to forecast power load more effectively. To assess the validity of the combined model, four datasets of 30-minutes power load from Australia are selected for research. The experimental results show that the established model not only has obvious advantages over other individual models, but also can be applied as an available technology for electrical system programming.