Hourly power consumption prediction for New Zealand residential houses using artificial neural network models

Loading...
Thumbnail Image
Supplementary material
Other Title
Authors
Ahmad, Aziz
Anderson, T.N.
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2014-12
Supervisors
Type
Conference Contribution - Oral Presentation
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
power consumption
Levenberg-Marquardt
load prediction
neural networks
New Zealand
residential housing
Citation
Ahmad , A., and Anderson, T. (2014, December). Hourly power consumption prediction for New Zealand residential houses using artificial neural network models. Paper presented at Asia Pacific Solar Research Conference, NSW Sydney, Australia, NSW Sydney, Australia.
Abstract
In this study several Artificial Neural Network (ANN) models were experimented to predict electricity consumption for a residential house in New Zealand. The effect of day of the week and weather variables on electricity consumption was analyzed. Each model has been constructed using different structures, learning algorithms and transfer functions in order to come up with the best model which has better generalizing ability. Further each model has been experimented with different number of neurons in the hidden layers and different number of delays in the tapped layers, and their effect on prediction accuracy was analyzed. Subsequently the most accurate ANN model was used to study the effects of weather predictor variables on the electricity consumption. Actual input and output data were used in the training, validation and testing process. A comparison among the developed neural network models was performed to find the most suitable model. Finally the selected ANN model has been used to predict 24 hours in advance electricity consumption for a residential house in New Zealand.
Publisher
Australia PV Institute
Link to ePress publication
DOI
Copyright holder
Authors
Copyright notice
All rights reserved
Copyright license
This item appears in: