English  |  正體中文  |  简体中文  |  Items with full text/Total items : 25444/26039 (98%)
Visitors : 6412459      Online Users : 223
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ksu.edu.tw/handle/987654321/3743


    Title: 配電系統快速復電之計算機輔助決策系統
    A Computer-Based Assistance System for Fast Restoration of Distribution System
    Authors: 黃昭明
    許哲豪
    曾昱翰
    Keywords: 系統復電
    模糊因果網路
    徑向基函數神經網路
    垂直最小平方法
    混合粒子群最佳化方法
    service restoration
    fuzzy cause-effect network
    radial basis function neural network
    orthogonal least squares method
    hybrid particle swarm optimization
    Date: 2007-08-31
    Issue Date: 2009-08-15 19:24:20 (UTC+8)
    Abstract: 本計畫建立一套配電系統快速復電之計算機輔助決策系統,當配電系統遭受意外事故時,用以輔助系統調度員進行最適之復電規劃。計畫中首先利用模糊因果網路模式建立配電系統在不同分歧負載及饋線容量情況下之多目標復電規劃,並據以建立網路訓練用資料集,再藉本計畫所提出之徑向基函數神經網路進行學習訓練。徑向基函數神經網路具有架構簡單及非線性輸入/輸出映射的特性,故非常適合於求解配電系統之復電問題。該網路中隱藏層中心節點神經元的數目及隱藏層至輸出層間的權值為決定網路學習效果的重要參數。本計劃中首先利用垂直最小平方演算法決定網路中隱藏層中心節點神經元的數目,以精減網路架構,再藉混合粒子群最佳化方法調整網路中隱藏層至輸出層間的連結權值,以快速、有效地求解配電系統之復電問題。當模式訓練完成,操作者能非常快速獲得復電規劃。本計畫以一典型台電配電系統為例進行研究,所提出的方法亦與類神經網路方法進行比較,以驗證其在實際應用上的有效性。The project aims at establishing a computer-basedassistance system to help the dispatchers achieve anadequate restoration plan when the system sufferscontingent events. To set up the training data, the fuzzycause-effect network (FCEN) is first used to build up themulti-objective restoration plans based on diverse lateralloads and feeder capacity. A radial basis function neuralnetwork (RBFNN) is then proposed to train the obtainedtraining data. Since the RBFNN has the characteristics ofsimple structure and nonlinear input-output mapping, it isvery adequate to solve the problem of service restoration.The parameters of the node number in the hidden layer andweights between hidden layer and output layer areimportant for constructing the networks. To quickly solvethe restoration plans reasonably and effectively, this projectadopts the orthogonal least squares (OLS) algorithm todetermine the number of center in hidden layer, which cansimplify the network structure. Then the hybrid particleswarm optimization (HPSO) approach is used to tune theweights between hidden layer and output layer. Once theRBFNN is trained properly, the dispatcher can quicklyacquire the restoration plans as soon as the inputs are given. The proposed approach has been tested on a typicalTaipower distribution system. To verify the effectiveness ofthe proposed networks, comparison has been made to theexisting artificial neural networks (ANN) method.
    Appears in Collections:[電機工程系所] 研究計畫

    Files in This Item:

    File Description SizeFormat
    952221E168044.pdf243KbAdobe PDF277View/Open


    All items in KSUIR are protected by copyright, with all rights reserved.


    本網站之所有圖文內容授權為崑山科技大學圖書資訊館所有,請勿任意轉載或擷取使用。
    ©Kun Shan University Library and Information Center
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback