Short-term hourly load forecasting using time-series modeling withpeak load estimation capability

摘要

This paper presents a new time series modeling for short term loadnforecasting, which can model the valuable experiences of the expertnoperators. This approach can accurately forecast the hourly loads ofnweekdays, as well as, of weekends and public holidays. It is shown thatnthe proposed method can provide more accurate results than thenconventional techniques, such as artificial neural networks ornBox-Jenkins models. In addition to hourly loads, daily peak load is annimportant problem for dispatching centers of a power network. Most ofnthe common load forecasting approaches do not consider this problem. Itnis shown that the proposed method can exactly forecast the daily peaknload of a power system. Obtained results from extensive testing on thenIran's power system network confirm the validity of the developednapproach