Research On The Analysis And Forecast Of Electric Power Load In The Datong Area

Short-term power load forecasting (STLF) is important for electricity production, scheduling and sales system in today. And it is to maintain power system security and an important guarantee of economic operation, effective short-term load forecasting algorithm, can improve the prediction results accuracy. Electric load has both regularity and randomicity. Load of next period has close relation to historical load, current operation status, meteorologic factor of forecasting period and date type, in which there are a lot of linear and non-linear relations.This paper analyzed the factors which influenced the electrical load, and emphasized the influence caused by wind power combined to the grid. This paper analyzed the characters of the power load, studied the traditional forecasting theories. Combining the characteristics of power load in Datong area, the use of traditional load forecasting methods in BP neural network, the establishment of the model. Most important of all, this paper studied BP (backProPagation) neural network which is the most mature algoritllill at present was selected.In the data preprocessing, though methods such as mathematical statistics deviate from the calculation of the rate of load capacity to carry out abnormal data pretreatment, and then, the raw data sequence become reasonable. On this basis, construct a BP neural network to determine the BP network model parameters, with the establishment of the BP neural network model, on the Datong area of power daily load forecast, forecasting results show that this method in wind power conditions remain relatively high prediction accuracy.