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...

全面介绍

Saved in:

书目详细资料
主要作者:	Abdullah, Muhamad Faizol Adli
格式:	Thesis
语言:	English
出版:	2010
主题:	TK Electrical engineering Electronics Nuclear engineering
在线阅读:	https://ir.uitm.edu.my/id/eprint/79028/1/79028.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.79028
record_format	uketd_dc
spelling	my-uitm-ir.790282024-07-28T15:57:54Z Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah 2010 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 https://ir.uitm.edu.my/id/eprint/79028/ https://ir.uitm.edu.my/id/eprint/79028/1/79028.pdf text en public degree Universiti Teknologi Mara (UiTM) Faculty of Electrical Engineering Herman, Sukreen Hana
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Herman, Sukreen Hana
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
qualification_level	Bachelor degree
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
granting_institution	Universiti Teknologi Mara (UiTM)
granting_department	Faculty of Electrical Engineering
publishDate	2010
url	https://ir.uitm.edu.my/id/eprint/79028/1/79028.pdf
_version_	1811768663025385472

Forecasting of photovoltaic output using hybrid particle swarm optimization-artificial neural network model / Muhamad Faizol Adli Abdullah

相似书籍