%0 Journal Article
%T ELECTRICITY LOAD FORECASTING WITH ARTIFICIAL NEURAL NETWORKS
%A H. Boraine
%A V.S.S. Yadavalli
%J South African Journal of Industrial Engineering
%D 2012
%I SAIIE
%X ENGLISH ABSTRACT: Artificial neural networks are powerful tools for time series forecasting. The problem addressed in this article is to do multi-step prediction of a stationary time series, and to find the associated prediction limits. Artificial neural network models for time series are non-linear. However, results that are applicable to linear models are sometimes mistakenly applied to non-linear models. One example where this is observed is in multi-step forecasting. A bootstrap method is proposed to calculate one- and multi-step predictions and prediction limits. The results are applied to an electricity load time series as well as to a pure autoregressive time series. AFRIKAANSE OPSOMMING: Kunsmatige neurale netwerke is kragtige instrumente vir tydreeksvoorspelling. In hierdie artikel word multistap-vooruitberaming van ¡®n stasion¨ºre tydreeks en die gepaardgaande vertroueinterval behandel. Resultate wat slegs geldig is vir line¨ºre modelle word soms verkeerdelik op neurale netwerkmodelle toegepas. ¡®n Voorbeeld hiervan kom in multistap-voorspelling voor. ¡®n Skoenlusmetode, word voorgestel waarvolgens eenstap- en multistap- voorspellings en vertroueintervalle bereken kan word. Die resultate word op ¡®n elektrisiteitslastydreeks en op ¡®n suiwer outoregressiewe tydreeks toegepas.
%U http://sajie.journals.ac.za/pub/article/view/263