Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction

碩士 === 清雲科技大學 === 電子工程研究所 === 95 === Photovoltaic (PV) is one of the most widely used devices among the renewable energies. It is important to operate PV energy conversion systems near the maximum power point (MPP) to increase the output efficiency of PV arrays. The radial basis function (RBF) netwo...

Full description

Bibliographic Details
Main Authors: Bo-Hong Li, 李柏宏
Other Authors: Chiung-Chou Liao
Format: Others
Language:zh-TW
Published: 2008
Online Access:http://ndltd.ncl.edu.tw/handle/44401792914894235977
id ndltd-TW-096CYU00428050
record_format oai_dc
spelling ndltd-TW-096CYU004280502015-11-30T04:02:51Z http://ndltd.ncl.edu.tw/handle/44401792914894235977 Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction 應用基因演算法結合K階均值分類演算法於輻狀基底函數網路之太陽能最大功率點預測 Bo-Hong Li 李柏宏 碩士 清雲科技大學 電子工程研究所 95 Photovoltaic (PV) is one of the most widely used devices among the renewable energies. It is important to operate PV energy conversion systems near the maximum power point (MPP) to increase the output efficiency of PV arrays. The radial basis function (RBF) network, which is considered as a good candidate for approximating problems for its faster learning capability compared with other networks. In traditional RBF networks, the k-means algorithm (KMA) is one of the most popular methods to classify the input patterns in the first stage of RBF network. In the second stage, a network adjusts iteratively parameters of each node by minimizing the least squares criterion according to gradient descent algorithm. Although the KMA has an ability to classify the training patterns rapidly, it usually converges to a local minimum and can be oversensitive of randomly initial partitions. To solve these significant problems, a hybrid algorithm with KMA and Genetic Algorithm (GA) called GKA is proposed to improve the effectiveness of the clusters from the training patterns by avoiding being trapped in a local minimum solution during the k-means searching process and being taken a large amount of time to converge the global minimum solution with GA. Besides, the proposed GKA based clustering approach can overcome the problem of oversensitivity of randomly initial partitions with the existing KMA. By precise clustering of the training patterns, the aims at approximating the MPP of PV system can be accurately and rapidly reached with the least squares criterion in RBF network. Also, this thesis employed the actual data obtained from the practical PV energy conversion systems and the developed MPP prediction method was proven to be effective. Chiung-Chou Liao 廖烔州 2008 學位論文 ; thesis 74 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 清雲科技大學 === 電子工程研究所 === 95 === Photovoltaic (PV) is one of the most widely used devices among the renewable energies. It is important to operate PV energy conversion systems near the maximum power point (MPP) to increase the output efficiency of PV arrays. The radial basis function (RBF) network, which is considered as a good candidate for approximating problems for its faster learning capability compared with other networks. In traditional RBF networks, the k-means algorithm (KMA) is one of the most popular methods to classify the input patterns in the first stage of RBF network. In the second stage, a network adjusts iteratively parameters of each node by minimizing the least squares criterion according to gradient descent algorithm. Although the KMA has an ability to classify the training patterns rapidly, it usually converges to a local minimum and can be oversensitive of randomly initial partitions. To solve these significant problems, a hybrid algorithm with KMA and Genetic Algorithm (GA) called GKA is proposed to improve the effectiveness of the clusters from the training patterns by avoiding being trapped in a local minimum solution during the k-means searching process and being taken a large amount of time to converge the global minimum solution with GA. Besides, the proposed GKA based clustering approach can overcome the problem of oversensitivity of randomly initial partitions with the existing KMA. By precise clustering of the training patterns, the aims at approximating the MPP of PV system can be accurately and rapidly reached with the least squares criterion in RBF network. Also, this thesis employed the actual data obtained from the practical PV energy conversion systems and the developed MPP prediction method was proven to be effective.
author2 Chiung-Chou Liao
author_facet Chiung-Chou Liao
Bo-Hong Li
李柏宏
author Bo-Hong Li
李柏宏
spellingShingle Bo-Hong Li
李柏宏
Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
author_sort Bo-Hong Li
title Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
title_short Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
title_full Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
title_fullStr Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
title_full_unstemmed Genetic K-Means Algorithm Based RBF Network for PV Generation Maximum Power Point Prediction
title_sort genetic k-means algorithm based rbf network for pv generation maximum power point prediction
publishDate 2008
url http://ndltd.ncl.edu.tw/handle/44401792914894235977
work_keys_str_mv AT bohongli genetickmeansalgorithmbasedrbfnetworkforpvgenerationmaximumpowerpointprediction
AT lǐbǎihóng genetickmeansalgorithmbasedrbfnetworkforpvgenerationmaximumpowerpointprediction
AT bohongli yīngyòngjīyīnyǎnsuànfǎjiéhékjiējūnzhífēnlèiyǎnsuànfǎyúfúzhuàngjīdǐhánshùwǎnglùzhītàiyángnéngzuìdàgōnglǜdiǎnyùcè
AT lǐbǎihóng yīngyòngjīyīnyǎnsuànfǎjiéhékjiējūnzhífēnlèiyǎnsuànfǎyúfúzhuàngjīdǐhánshùwǎnglùzhītàiyángnéngzuìdàgōnglǜdiǎnyùcè
_version_ 1718139499363434496