Research Of Short-term Power Load Forecasting

In the field of energy, electric energy plays an important role. With the rapid development of the national economy and the demand for electricity increases, power system is facing increasing challenges. Power system short-term load forecasting is an important task of daily operation ang scheduling, it has great significance for the safe, stable and economic operation of power system. China is a large agricultural country, with the development of agricultural mechanization, rural power grows with each passing day. Reasonable modification and expansion of rural power system is the trend. Because of the changes of rural power load is greatly influenced by the change of load, and the change of load component directly affects the accuracy of short-term load forecasting,so short-term load forecasting can better reflect the change trend of the load components, therefore, in this paper, the power load in Hubei rural area as the research object, has been researched on short term power load forecasting.This paper introduces the current research situation of electric power load forecasting, describes the basic principle of load forecasting, by comparing the advantages and disadvantages of several classical methods, we choose the BP neural network. According to the characteristics of a rural historical load data, a BP neural network model was established. And we predicted the actual load, then analyzed and compared the errors of results,in the end,we proved the significance of this method.