Big data analytics for price forecasting in smart grids

Demand side management (DSM) is a key mechanism to make smart grids cost efficient using electricity price forecasting issue. Price forecasting method takes the big price data into account, and gives estimates of the future electricity price. However, most of existing price forecasting methods cannot avoid redundancy at feature selection and lack of an integrated framework that coordinates the steps in forecasting. To address this issue, we first propose a new electricity price forecasting framework. It is significant to design a system tool chain based on big data analytics for ensuring that the users can make appropriate decisions. To this end, three algorithms are proposed integratedly. First, feature redundancy elimination is implemented by the fusion of Grey Correlation Analysis (GCA) and ReliefF algorithm. Second, a combination of Kernel function and Principle Component Analysis (KPCA) is designed to achieve dimensionality reduction. Finally, Support Vector Machine (SVM) optimization algorithm based on differential evolution (DE) is proposed to forecast price classification. These three modules jointly power the price forecasting system. Simulation results show the superiority of our proposed framework.