By Topic

Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $33
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
A. A. El Desouky ; Dept. of Electr. & Electron. Eng., Bath Univ., UK ; M. M. Elkateb

Different neural-network configurations with an adaptive learning algorithm are designed for prediction of monthly load demand. The importance of the load forecast for Jeddah city, Saudi Arabia, is considered to justify development of new hybrid adaptive techniques, The techniques utilise the available nine years' information for both load and temperature. The first seven years' data are used for training the artificial neural network (ANN) while the performance of the ANN is verified from the forecast of two years ahead and then comparing with the true last two years' data. As the trend of the load is an important factor, several methods of extracting the load-demand trend have been examined to ensure the enhancement in forecast accuracy. Different network learning cases are pursued using ANN and a hybrid ARIMA/ANN to arrive at a suitable model, The results of both the ANN and the hybrid ARIMA/ANN forecasting were most promising compared with corresponding forecasts produced using the established time-series method

Published in:

IEE Proceedings - Generation, Transmission and Distribution  (Volume:147 ,  Issue: 4 )