Mid-long Term Load Forecasting Of Shenyang Distribution Network

In today’s rapid development of science and technology, the load forecasting is more important for electricity production, scheduling and sales system. At the same time, it is an important research content of power system planning and running, and is premise for reliable supplying and economic running and also is the basis of power system planning and construction. Exact degree of load forecasting shall affect rationality of investment, network layout and running. Electric load has both regularity and random, and will be affected by many uncertain factors, there are a lot of linear and non-linear relations.Medium and long-term load forecasting belongs to stratagem forecasting. It makes the load of the whole planning region as forecasting object. Its results decide the urban demand for electric power and the supplying capacity of urban distribution network in the future. The results of load gross forecasting have important guidance significance for ascertaining the location of power supply and generating planning. It is the important basis of distribution network planning.First, this paper studies the domestic and foreign review about power load forecast. Second, there are the concepts, traits and classification of power load forecasting which are involved. The relevant theory neural network is studied, especially the structural design of it, choose to learning parameters and the type BP algorithm. We can built the model of the power load forecasting on the basis of standard type BP algorithm in order to realize the shortages of the model that we built through positive analysis. And then analyze the factors which influence the electrical load in Shenyang distribution network, and the shortages of the traditional methods forecasting electrical load. Combining the characteristics of power load in Shenyang area, the use of traditional load forecasting methods in BP neural network and based on the time series, establish the model, and then compare the two methods.