Title :
Short-term load forecasting for electrical regional of a distribution utility considering temperature
Author :
De Aquino, Ronaldo R B ; Ferreira, Aida A. ; Lira, Milde M S ; Neto, Otoni Nóbrega ; Amorim, Priscila S. ; Diniz, Carlos F D ; Silveira, Tatiana M A da
Author_Institution :
Fed. Univ. of Pernambuco (UFPE), Recife, Brazil
fDate :
July 31 2011-Aug. 5 2011
Abstract :
This work deals with the application of Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) to provide the decentralized daily load short-term forecasting which is based on the average daily temperature. It is not an easy task to forecast the load demand of an electrical regional mainly because of the system reconfiguration either temporary (operational maneuvers) or permanent (creation of new regional). In this regard, ANN and ANFIS were chosen because they have robustness in their responses. Both models carry out the load forecasting for each electrical regional of CELPE distribution system in the period of 7 and 14 days ahead. The results were compared between each other and also with the PREVER software, demonstrating a considerable improvement in performance of the new models.
Keywords :
fuzzy neural nets; fuzzy reasoning; load forecasting; power distribution; power engineering computing; ANFIS; ANN; CELPE distribution system; PREVER software; adaptive neurofuzzy inference system; artificial neural network; average daily temperature; decentralized daily load short-term forecasting; electrical region; load demand; time 14 day; time 7 day; Artificial neural networks; Data models; Forecasting; Load forecasting; Load modeling; Predictive models; Training;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033471
