| Power short- term load forecasting related to the smooth scheduler of power systems. Load forecasting accuracy affects the economy and stability of power systems, smart grid load forecasting real-time requirements are also increasing. Therefore, domestic and foreign scholars have been the short-term power load forecasting as a research priority.The study found that the impact of meteorological factors and date on the load of the power system is the most significant. In this paper, the real load characteristics of a region are analyzed, and the data are preprocessed, and the influence of the meteorological factors on the load is discussed by the method of similarity.In recent years, artificial neural network as a kind of intelligent algorithm has been widely studied and applied in the short-term load forecasting of power system. But in the application, the BP neural network is adopted. As a static network, BP neural network is a dynamic process, and it is sure to have a problem with static model. The BP neural network is easy to fall into local minimum in load forecasting. The forecasting result is not satisfactory.In this paper, the grey Elman neural network load forecasting algorithm is proposed to solve the problem of local optimization of neural network, and genetic algorithm is used to optimize the gray Elman neural network. The results show that the effect is better than Elman neural network and gray Elman neural network.In recent years the development of power system intelligent leads to load data of large scale and high dimensional, load forecasting facing single computing resource shortage, poor predictive real-time. In this paper, the distributed genetic algorithm and grey Elman neural network are distributed, and the Elman neural network prediction algorithm is realized in the Spark cloud platform. The results show that the accuracy and real-time performance of the proposed model are better than the traditional load forecasting algorithm. |
PDF Full Text Request