Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah
Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perception (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome these problems, Particle Swarm...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/79028/1/79028.pdf https://ir.uitm.edu.my/id/eprint/79028/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uitm.ir.79028 |
|---|---|
| record_format |
eprints |
| spelling |
my.uitm.ir.790282024-07-28T15:57:54Z https://ir.uitm.edu.my/id/eprint/79028/ Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah Abdullah, Muhamad Faizol Adli TK Electrical engineering. Electronics. Nuclear engineering Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perception (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome these problems, Particle Swarm Optimization (PSO) has been used to determine optimal value for BP parameters such as learning rate and momentum rate and also for weighting optimization. In Backpropagation Neural Network (BPNN), there are many elements to be considered such as the number of input, hidden and output nodes, learning rate, momentum rate, bias, minimum error and activation/transfer functions. These entire elements will affect the speed of natural network learning. In this study, the optimization algorithm, PSO is chosen and applied in feedforward neural network to enhance the learning process. Two model have been develop: Classical Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) for the prediction of total AC power output from a grid connected photovoltaic system. The result showed that the prediction of the total AC power output of grid connected photovoltaic system could be optimized and accelerated using PSO-ANN. 2010 Thesis NonPeerReviewed text en https://ir.uitm.edu.my/id/eprint/79028/1/79028.pdf Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah. (2010) Degree thesis, thesis, Universiti Teknologi Mara (UiTM). |
| institution |
Universiti Teknologi Mara |
| building |
Tun Abdul Razak Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Mara |
| content_source |
UiTM Institutional Repository |
| url_provider |
http://ir.uitm.edu.my/ |
| language |
English |
| topic |
TK Electrical engineering. Electronics. Nuclear engineering |
| spellingShingle |
TK Electrical engineering. Electronics. Nuclear engineering Abdullah, Muhamad Faizol Adli Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| description |
Backpropagation (BP) algorithm is widely used to solve many real world problems by using the concept of Multilayer Perception (MLP). However, major disadvantages of BP are its convergence rate is relatively slow and always being trapped at the local minima. To overcome these problems, Particle Swarm Optimization (PSO) has been used to determine optimal value for BP parameters such as learning rate and momentum rate and also for weighting optimization. In Backpropagation Neural Network (BPNN), there are many elements to be considered such as the number of input, hidden and output nodes, learning rate, momentum rate, bias, minimum error and activation/transfer functions. These entire elements will affect the speed of natural network learning. In this study, the optimization algorithm, PSO is chosen and applied in feedforward neural network to enhance the learning process. Two model have been develop: Classical Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) for the prediction of total AC power output from a grid connected photovoltaic system. The result showed that the prediction of the total AC power output of grid connected photovoltaic system could be optimized and accelerated using PSO-ANN. |
| format |
Thesis |
| author |
Abdullah, Muhamad Faizol Adli |
| author_facet |
Abdullah, Muhamad Faizol Adli |
| author_sort |
Abdullah, Muhamad Faizol Adli |
| title |
Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| title_short |
Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| title_full |
Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| title_fullStr |
Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| title_full_unstemmed |
Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah |
| title_sort |
forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / muhamad faizol adli abdullah |
| publishDate |
2010 |
| url |
https://ir.uitm.edu.my/id/eprint/79028/1/79028.pdf https://ir.uitm.edu.my/id/eprint/79028/ |
| _version_ |
1806422053383831552 |
| score |
13.211869 |