文章基本信息

标题：Development of New Algorithms for Power System Short-Term Load Forecasting
本地全文：下载
作者：Esa Aleksi Paaso ; Yuan Liao
期刊名称：International Journal of Computer and Information Technology
印刷版ISSN：2279-0764
出版年度：2013
卷号：2
期号：2
页码：201
出版社：International Journal of Computer and Information Technology
摘要：Load forecasting allows for the utilities to plan their operations to serve their customers with more reliable and economical electric power. With the developments in computer and information technology new techniques to accurately forecast power system loading are emerging. This research culminates in development of modified algorithms for short-term load forecasting (STLF) of a utility grade power system. The three proposed methods include: Modified Recursive Least Squares parameter estimation for online load foresting, Modified Kalman Filter based parameter estimation for online load forecast, and Artificial Neural Fuzzy Interference System approach. The load forecast performance of each new algorithm is validated with past utility data. The method performance is compared, and conclusions are drawn.
关键词：component; ; Short-Term Load Forecast; Least ; Squares; Kalman Filter; Parameter Estimation; Artificial ; Neural Fuzzy Interference System ; ; ANFIS