Study Based On Artificial Neural Networks And Rough Set To Forecast Short Term Load

Short term load forecasting(STLF) is an important task of power utilities, which is wildely used in the dispatching and operation planning of power systems, and the accurate load forecasting is helpful to the security and stability of power systems as well as to reducing the generation casts. With the establishment and development of the power market, STLF will play more and more important role in power systems.In order to improve the accuracy and correlative of the historical data, to reduce the redundance of the input vectors of a neural network, and to optimize the structure of a neural network, the composing and characters of electric load are discussed, the influences of the correlative factors for STLF are analized, and the actuality and the existing problems of STLF are studied in this paper, put forward a subsection model which based on artificial neural networks and rough set to forecast short term load. Firstly, There are so many factors that influenced STLF. How to justify and select the correlative factors is the key to improve the performance of load forecasting, This article combine neural network and rough set, by using the attribute reduction algorithm in the rough sets to eliminates the redundant attributes, math reasoning confirm neural network input resolve the lack of selecting by experience and avoid the blindness. Secondly, this article analysis the composing and characters of electric load of one province, educe that load have the cycle of day. week and year , daily load also have the same trend, basically divided into several segments by apex and vale. So depending this law , this article divide the daily load into several segments to minish the dimensions of neural network , thereby improve the forecast precision.Depend on the date of one province , compare the forecast model of this article with single neural network model ,the result show that the presented method possesses more accurate.