Study On Medium-Long Term Power Load Forecasting Based On Baotou

With the adjustment of electric power industry and national economy structure, electric power market has changed very greatly, the contradiction between supply and demand is prominent increasingly, electric power load forecasting is more and more important, the accuracy requirement of predicting is also more and more high. The power system load forecasting is becoming more and more important, demanding on higher accuracy. Of course, as a basic for network planning, using year as the unit, the mid-long term load forecasting need in-depth researched and analysis, which is the premise of ensuring the reliability and economic operation of the power system. The accuracy of mid-long term load forecasting will directly affect the rationality of investment, network layout and operation.There are many methods for load forecasting. In the past, during the actual network planning traditional forecasting methods were used, such as the average growth rate method, time series method, etc. With increasing demands for load forecasting, a number of modern technologies are applied in the actual load forecasting. The focus of this paper is the using of a variety of forecasting methods on the load of Baotou area in 2010-2015. Combination forecasting is an effective way to improve the accuracy. Based on the actual data of Baotou area, this paper carries out the research on mid-long term load forecasting. In the first, several single load forecasting methods are described, taking into account the characteristics of the load in Baotou, then, the appropriate method of load forecasting is selected for combination, obtaining a fitting model of single forecasting method and combination method. Both methods are tested on load forecasting for Baotou. The experimental results demonstrate that the combination method is better than the single method in scientificity and practicability.