Power Short-term Load Forecasting Based On Neural Network Algorithm Applied Research In Xinglong Electric Power Company

Since the second industrial revolution,the power resources have been the fundamental of the stability,construction and development of all countries in the world.In recent years,with the rapid development of China's economy,the demand for electricity in various regions and departments has increased year by year.Therefore,how to reasonably allocate and predict the power resources has attracted more and more attention of the society in recent years.With the advent of the era of intelligence,in the analysis and prediction of power resources,all kinds of intelligent algorithms based on the actual engineering application background,generally have achieved good application value.In this paper,Chengde City,Hebei Province,North China Power Co.,Ltd.,as the background of the power supply company,through the neural network algorithm for the region's short-term load forecasting.Earlier,through the research on the load characteristics,all kinds of users grid prediction period of the analysis,and combining the specific situation of prosperous county power supply company,carried out a large number of real and effective data transfer.Then,the weighted least square method,recursive least square method,orthogonal function least square method and the least square method are compared and analyzed in the data preprocessing stage.The final selection of a small array of least squares method to achieve the data by working.In the classification algorithm selection,this paper compares the BP neural network and Elman neural network algorithm,through theoretical and experimental analysis of the Elman neural network algorithm has achieved the expected good results in classification and identification.In addition,through the above algorithm and the regional power grid prediction analysis system shows that Elman neural network algorithm in the load of power grid has a better ability to predict characterization,can provide reference for the short-term prediction of power grid area to a certain extent.Hope that the better for the local economic construction,people's life to make more,better,greater contribution.