Study On Electric System Short-term Load Forecasting

With the development of our national electric industry, the management of electrified wire netting is more and more modernized. People pay more attention to the study on electric system load forecasting than ever. It has become one of the important tasks in the study on modern electric system. It is the important foundation of the study on electric system planning problem, economical running and dispatcher automation.Firstly, the paper studies the characters and sorts of load and analyses the influence factors of load, for example, the region component of load, temperature, rainfall and holiday and so on. On the basis of the deep analysis to load characters, the paper puts forward a method of corporation forecasting which selects one or a few effective load forecasting methods from many methods according to the factual influence elements. Gray theory, neural network and so on are used in the paper. The influence of some factors is also considered enough. Since the policy of "charging on time" was put into practice, the influence of electric energy's price to load appears in the short term. The paper studies load forecasting aimed to this new circumstance and puts forward the solution. Considering forecasting error of former method is satisfied but the error fluctuates wildly under the abrupt incident circumstances, the paper puts forward the associative method of lengthways load forecasting and transverse error revise with error-corrected model in the last method of corporation forecasting. The method not only make the error little but also make the error steady.The arithmetic example of forecasting method is analyzed and suitedscope of every forecasting method is raised. Finally software of load forecasting is developed. The pressure of forecasting work is relieved effectively and the accuracy of forecasting is improved.