Short-term Load Forecasting Based On Wavelet-package Transform

Power short-term load forecasting is an important routine for power dispatch department. Especially with the foundation and the development of power market, short-term load forecasting will bring into play a more and more important role. Its precision directly influences power system's security, profit and quality. Therefore, how to improve the forecasting precision is the emphasis on the study of short-term load forecasting.It greatly improves the forecasting precision that the wavelet transform theory is applied into the area of power short-term load forecasting. On the basis of the study of the foregoing method, this paper brings forward a new method of the short-term load forecasting based on the wavelet-package transform theory, PAR model and ANN for the first time. In this method, the original-load-serial is decomposed into child-load-serials on different scales in the first instance. Afterward, according to respective characteristic of child-load-serials, PAR method is used to forecast the periodicity child-load-serials while ANN method is used to forecast the randomicity child-load-serials. Lastly, the final forecasting result is attained via the wavelet-package recomposition of all child-load-serials forecasting results . Because the wavelet-package transform subdivides the high frequency parts that the wavelet transform doesn't decompose, it can separate the periodicity child-load-serials from the high frequency parts more effectively, Especially for the high frequency part of the first floor of the wavelet transform method, which is as a whole and randomicity load in the forecasting process of the wavelet transform method, wavelet-package can separate the periodicity child-load-serial from this part. Since the result of the forecasting to periodicity load is exacter than that to randomicity load, the wavelet-package transform...