English  |  正體中文  |  简体中文  |  Items with full text/Total items : 888/888 (100%)
Visitors : 13638694      Online Users : 323
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://ccur.lib.ccu.edu.tw/handle/A095B0000Q/765

    Title: 以倒傳遞類神經網路演算法預測電力消費量 -以台灣地區為例;Prediction of Electric Power Consumption in Taiwan by Back Propagation Neural Network
    Authors: 李天傑;Li, Tien-Chiao
    Contributors: 通訊資訊數位學習碩士在職專班
    Keywords: 人工智慧;類神經網路;電力預測;電力消費量預測;neural network;electricity forecast;electricity consumption factor
    Date: 2017
    Issue Date: 2019-07-17 10:47:12 (UTC+8)
    Publisher: 通訊資訊數位學習碩士在職專班
    Abstract: 能源一直以來都是世界各國積極解決的主要問題,能源危機是未來各國都將面對的難題,台灣四面環海天然資源缺乏,有很多的能源必須由進口獲得,能源也將是台灣急需積極投入的戰場。電力是現代社會不可或缺的能源之一,多數資源用來產生電力,近年綠能產業的發展,解決了許多小區域的電力補償,但許多大城市的電力耗損及供需不均所導致的能源浪費還是存在,因此電力的配送、儲能轉換及供需調節等依然扮演重要的腳色。就本研究以電力消費的角度反觀與負載間存在的差異,運用各類型用電因子及負載以類神經網路進行電力消費預測,並從中分析各組合的預測值與實際電力消費間的誤差,了解其可能影響的用電行為。本論文運用倒傳遞類神經網路作為訓練架構,將各類用電因子分類及組合作為訓練參數,以3項主要用電因子,配合其他參考因子進行預測,所獲得誤差最低之變數組合列入主要用電因子,再搭配其他參考因子進行預測,直到獲得最佳變數組合,其中以平均溫度、平均相對溼度、平均負載、國內能源總消費量、平均日照時數及石油消費量組合獲得平均絕對百分比誤差(MAPE)1.90%為最佳預測準確度,並了解氣候變化及日照長短對於國人用電行為的改變有相當程度的影響,所改變的行為以石油原物料的使用及消費有關。
    Energy crisis will be a major problem for countries around the world in the future. The lack of resources has become an important issue for Taiwan. Taiwan will activly invest in seanding energy issues.Electricity is one of the indispensable energy sources of modern society. Most energy is used to generate electricity. Green energy industry in recent years solve the power compensation of many small areas. But many cities still have the energy waste and the demand uneven supply. So the power distribution, energy storage conversion and supply and demand regulation still plays an important role.This subject studied discrepancy between the electricity consumption and power load. This study used electricity consumption forecast by various types of power factor and load by Artificial Neural Network (ANN),and also analyzed discrepancy between predictive value and actual condition.This subject also found out the behavior of electrical using(behavior).We used the Back Propagation Neural Network (BPNN) to prediction by power consumption factor. We categorizied the electrical factors. And we used three main electrical factors to train BPNN with other reference factors. The best combination matched again to other reference factors to form 4 inputs, 5 inputs, 6 inputs and 7 inputs. Final we get a conclusion that the average temperature, average relative humidity, average load, total domestic energy consumption, average sunshine hours and oil consumption are the best combination for electricity consumption. The Mean Absolute Percent Error is 1.90%.
    Appears in Collections:[通訊工程研究所] 學位論文

    Files in This Item:

    File Description SizeFormat

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

    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback