Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria
The purpose of this project is to study and develop an artificial neural network (ANN) model specifically for short term load prediction. A nonlinear load model is proposed and several structures of ANN for short term load prediction are tested. The outputs obtained were the predicted full day load...
Saved in:
主要作者: | |
---|---|
格式: | Thesis |
语言: | English |
出版: |
2012
|
在线阅读: | https://ir.uitm.edu.my/id/eprint/84796/1/84796.pdf |
标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
id |
my-uitm-ir.84796 |
---|---|
record_format |
uketd_dc |
spelling |
my-uitm-ir.847962024-01-12T09:16:14Z Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria 2012 Zakaria, Mohammad Tariq The purpose of this project is to study and develop an artificial neural network (ANN) model specifically for short term load prediction. A nonlinear load model is proposed and several structures of ANN for short term load prediction are tested. The outputs obtained were the predicted full day load demand for the next day or week. The ANN model has 4 layers; an input layer, two hidden layers and an output layer. The number of inputs was 6; while the number of hidden layer neurons was varied for different performance of the network. The output layer has 24 neurons. The ANN model was trained for over 5 weeks. A mean absolute percentage errors of 2.52% was achieved when the trained network was tested on random for one week's data. 2012 Thesis https://ir.uitm.edu.my/id/eprint/84796/ https://ir.uitm.edu.my/id/eprint/84796/1/84796.pdf text en public degree Universiti Teknologi MARA (UiTM) Faculty of Electrical Engineering Musirin, Ismail |
institution |
Universiti Teknologi MARA |
collection |
UiTM Institutional Repository |
language |
English |
advisor |
Musirin, Ismail |
description |
The purpose of this project is to study and develop an artificial neural network (ANN) model specifically for short term load prediction. A nonlinear load model is proposed and several structures of ANN for short term load prediction are tested. The outputs obtained were the predicted full day load demand for the next day or week. The ANN model has 4 layers; an input layer, two hidden layers and an output layer. The number of inputs was 6; while the number of hidden layer neurons was varied for different performance of the network. The output layer has 24 neurons. The ANN model was trained for over 5 weeks. A mean absolute percentage errors of 2.52% was achieved when the trained network was tested on random for one week's data. |
format |
Thesis |
qualification_level |
Bachelor degree |
author |
Zakaria, Mohammad Tariq |
spellingShingle |
Zakaria, Mohammad Tariq Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
author_facet |
Zakaria, Mohammad Tariq |
author_sort |
Zakaria, Mohammad Tariq |
title |
Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
title_short |
Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
title_full |
Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
title_fullStr |
Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
title_full_unstemmed |
Load prediction using artificial neural network (ANN) / Mohammad Tariq Zakaria |
title_sort |
load prediction using artificial neural network (ann) / mohammad tariq zakaria |
granting_institution |
Universiti Teknologi MARA (UiTM) |
granting_department |
Faculty of Electrical Engineering |
publishDate |
2012 |
url |
https://ir.uitm.edu.my/id/eprint/84796/1/84796.pdf |
_version_ |
1794192051845201920 |