English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27106/27702 (98%)
Visitors : 15896246      Online Users : 475
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/987654321/6979

    Title: 應用徑向基函數神經網路於即時電力調度之研究
    Real-Time Power Dispatch Using Radial Basis Function Neural Network
    Authors: 黃昭明
    Keywords: 即時電力調度
    Real-Time Power Dispatch
    Particle Swarm Optimization
    Artificial Neural Network
    Radial Basis Function Neural Network
    Orthogonal Least Squares
    Date: 2005-07-31
    Issue Date: 2009-12-31 16:40:17 (UTC+8)
    Abstract: 本計畫應用徑向基函數神經網路於求解多目標即時電力調度問題,計畫中首先於離線時段建立同時考慮燃料成本、代輸成本及污染排放量之電力調度資料庫,再藉以粒子群最佳化方法為基礎之徑向基函數神經網路進行學習訓練。另外,爲精減徑向基函數神經網路之架構,本計劃利用垂直最小平方演算法選取最佳之中心節點數。粒子群最佳化方法為一模擬生物群體活動的人工智慧演算法,此方法由於採整體搜尋及具有快速收斂的特性,因此非常適合於做為網路訓練工具。當模式訓練完成,操作者能非常快速獲得電力調度解。為達成上述之即時調度目標,本計畫以IEEE 30 個匯流排、六部發電機組、41 條傳輸線系統為例進行研究,結果顯示,本計劃所提出之以PSO 為基礎之徑向基函數神經網路在測試誤差及收斂特性上均優於傳統類神經網路方法及徑向基函數神經網路方法。
    This project presents the use of radial basis function neural network (RBFNN) to the problem of real-time power dispatch. In the project, the training sets of power dispatch considering fuel cost, wheeling cost, and emissions during generating power on the off-line circumstance are collected first. Then the particle swarm optimization (PSO) based radial basis function neural network is adopted to search for the optimal parameters of network. PSO has been developed through simulation of simplified social models. Besides, in order to simplify the structure of RBFNN, the orthogonal least squares (OLS) algorithm was adopted to select the optimal nodes of hidden layer. Taking the advantages of global search and fast convergence, the PSO is very appropriate to tune the controlled parameters for the RBFNN. Once the networks are trained properly, it can produce the required outputs as soon as the inputs are given. The proposed approach has been be tested on the IEEE 30-bus, 6-generator, and 41-transmission line system. The comparisons of average absolute error and learning speed verify that the proposed PSO-based RBFNN approach outperforms the conventional artificial neural network(ANN) and RBFNN methods.
    Appears in Collections:[電機工程系所] 研究計畫

    Files in This Item:

    File Description SizeFormat
    932213E168014.pdf476KbAdobe PDF557View/Open

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

    ©Kun Shan University Library and Information Center
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback