跳到主要內容

臺灣博碩士論文加值系統

(35.172.223.251) 您好!臺灣時間:2022/08/11 21:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:尹居才
研究生(外文):Chu-Tsai Yin
論文名稱:以自迴歸式建模倒傳遞網路為基礎之即時用電需量預測研究
論文名稱(外文):Very Short-Term Electric Demand Forecasting Based on Back-Propagation Network with Autoregressive Modeling
指導教授:姚文隆姚文隆引用關係
指導教授(外文):Wen-Long Yao
學位類別:碩士
校院名稱:國立高雄第一科技大學
系所名稱:機械與自動化工程所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:87
中文關鍵詞:需量控制類神經網路自迴歸模式滾動建模田口法
外文關鍵詞:Artificial neural networkAuOn-demand control
相關次數:
  • 被引用被引用:21
  • 點閱點閱:617
  • 評分評分:
  • 下載下載:198
  • 收藏至我的研究室書目清單書目收藏:1
由於天然資源缺乏,台灣有超過95%的能源必須仰賴國外之進口。電力事業為了更經濟地提供高品質的電力,有效的調度供電機組,如何掌握未來用電趨勢以求供電的穩定與可靠,是其基本的課題。另一方面,為了因應全球化之競爭,很多企業開始利用各種方法減少無謂的電費開銷,以提升本身的競爭力;其中藉由電能監控系統配合電力需量預測之機制監控電力使用情形,以提升系統負載率,已經十分普遍。
自90年代開始即有大量以類神經網路(Artificial Neural Network;ANN)預測電力負載之研究。但在這些研究當中,大多是以相關影響變因建立類神經網路訓練資料,以預測每天的尖峰用電負載或總用電負載量,以確保高品質的電力負載與快速調度供電機組的能力,甚少以用電者的觀點來討論。而此種建模方式在電力劇烈變化的即時用電需量預測(Very Short-term Electric Demand Forecasting;VSTEDF),難以得到精準的預測結果。本研究提出以自迴歸滾動建模之方式建立倒傳遞網路的訓練資料,預測本校每隔兩分鐘之用電需量。實驗結果,整體的平均絕對百分誤差低於3%,並與傳統建模的倒傳遞網路模式和灰預測模式進行比較,顯示了本研究提出的機制具有較高的準確度。
Because of the lack of natural energy resources, over 95 percent of energy consumed in Taiwan are imported from overseas. In order to supply high-quality and inexpensive electric power to the consumer economically and assess electricity efficiently, tracking electric load generation at all times and knowledge of the future load is basic requisite in the operation of power facility. Besides, due to the growth of economy and global market competition, enterprises are concerned with the means to use electricity efficiently and avoid penalty. Therefore, the practice of demand control of electric system has drawn a lot of attentions from consumers.
The usage of artificial neural network (ANN) for electric demand forecasting has been proposed in many studies. Among these studies, the daily peak load or total load with weather consideration was mostly predicted in order to dispatch high-quality electricity or assess electric load efficiently for power utilities. However, the load demand forecasting at the standpoint view of consumers is seldom discussed. With the global marketing competition, enterprises have utilized more instruments in order to cut down large electricity bill of operation. Preliminary study showed that the traditional ANN training model is unable to deal with the volatile load pattern, especially in a very short-term load demand forecasting (VSTEDF). In this paper, we present a rolling training method of ANN for VSTEDF. By using this proposed rolling training model, the electric load demand is predicted precisely in the interval of every 2 minutes. The forecasting error is smaller than 3%. Compare to the conventional ANN model and Grey model, the recurrent ANN based predictor has better accuracy in VSTEDF.
摘要i
Abstractii
致謝iii
目錄iv
圖目錄vi
表目錄viii
符號說明ix
第一章 緒論1
1.1 研究背景與動機1
1.2 研究目的3
1.3 內容架構4
第二章 文獻探討5
第三章 方法論14
3.1 類神經網路簡介14
3.1.1 生物神經元與人工神經元模型16
3.1.2 類神經網路種類18
3.2 倒傳遞類神經網路19
3.3 類神經網路應用評估與規劃24
第四章 類神經網路即時用電需量預測30
4.1校園即時用電需量監控系統簡介30
4.2問題闡述33
4.3自迴歸模式與滾動建模38
4.4 VSTEDF網路之建立與規劃42
第五章 實驗結果與討論55
5.1預測結果55
5.2討論64
第六章 結論與未來展望68
6.1 結論68
6.2 未來展望69
參考文獻71
附錄一76
附錄二85
[1]http://www.taipower.com.tw/[2]G. A. Oluwande, 2001, "Exploitation of advanced control techniques in power generation," Computing & Control Engineering Journal, Vol.12, pp.63 —67.[3]S. J. Hepworth, A. L. Dexter, 1994, "Neural control of non-linear HVAC plant," The 3rd IEEE Conference on Control Applications, Glasgow, UK, 24-26 Aug., Vol.3, pp.1849-1854.[4]江金山等,1998,灰色理論入門,高立圖書有限公司,台北。[5]林茂文,1992,時間數列分析與預測,華泰書局,台北。[6]林惠玲、陳正倉,1999,統計學─方法與應用,雙葉書廊有限公司,台北。[7]林真真、鄒幼涵,1990,迴歸分析,華泰書局,台北。[8]X. Q. Liu, B. W. Ang, T. N. Goh, 1991, "Forecasting of electricity consumption: a comparison between an econometric model and a neural network model," 1991 IEEE International Joint Conference on Neural Networks, Singapore, 18-21 Nov., Vol.2, pp.1254-1259.[9]Y. H. Fung, V. M. Rao Tummala, 1993, "Forecasting of electricity consumption: a comparative analysis of regression and artificial neural network models," The 2nd International Conference on Advances in Power System Control, Operation and Management, Hong Kong, Vol.2, pp.782 —787.[10]D. Srinivasan, A. C. Liew, J. S. P. Chen, 1991, "Short term forecasting using neural network approach," The 1st International Forum on Applications of Neural Networks to Power Systems, Seattle, USA, 23-26 July, pp.12 —16.[11]P. Caire, G. Hatabian, C. Muller, 1992, "Progress in forecasting by neural networks," International Joint Conference on Neural Networks, Baltimore, USA, 7-11 June, Vol.2, pp. 540 —545.[12]E. Doveh et al, 1999, "Experience with FNN models for medium term power demand predictions," IEEE Transactions on Power Systems, Vol.14, No.2, pp.538-546.[13]T. M. Peng, N. F. Hubele, G. G. Karady, 1990, "Conceptual approach to the application of neural network for short-term load forecasting," IEEE International Symposium on Circuits and Systems, New Orleans, USA, 1-3 May, Vol.4, pp.2942 —2945. [14]C. N. Lu, H. T. Wu, S. Vemuri, 1993, "Neural network based short term load forecasting," IEEE Transactions on Power Systems, Vol.8, No.1, pp.336-342.[15]A. G. Bakirtzls et al, 1996, "A neural network short term load forecasting model for the Greek power system," IEEE Transactions on Power Systems, Vol.11, No.2, pp.858-863.[16]A. Khotanzad et al, 1995, "An artificial neural network hourly temperature forecaster with applications in load forecasting," IEEE Transactions on Power Systems, Vol.11, No.2, pp.870-876.[17]A. Khotanzad, R. Afkhami-Rohani, D. Maratukulam, 1998, "ANNSTLF — artificial neural network based short term load forecaster — generation three," IEEE Transactions on Power Systems, Vol.13, No.4, pp.1413-1422.[18]S. J. Kiartzis, A. G. Bakirtzis, V. Petridis, 1995, "Short-term load forecasting using neural networks," Electric Power Systems Research 33, pp.1-6.[19]T. W. S. Chow, C. T. Leung, 1996, "Neural network based short-term load forecasting using weather compensation," IEEE Transactions on Power Systems, Vol.11, No.4, pp.1736-1742.[20]H. B. Gooi et al, 1993, "Adaptive short-term load forecasting using artificial neural networks," IEEE Region 10 Conference on Computer, Communication, Control and Power Engineering, Beijing, China, 19-21 Oct., Vol.2, pp.787 —790.[21]曾燕明,1995,類神經網路於配電系統負載預測及饋線開關操作之應用,國立中 山大學電機工程所,博士論文。[22]M. Tamimi, R. Egbert, 2000, "Short term electric load forecasting via fuzzy neural collaboration," Electric Power Systems Research 56, pp.243-248.[23]L. D. Voss, M. M. A. Salama, J. Reeve, 1995, "A practical approach to electric load forecasting using artificial neural networks with corrective filtering," Canadian Conference on Electrical and Computer Engineering, Montreal, Canada, 5-8 Sept., Vol.1, pp.370-373.[24]K. Liu et al, 1996, "Comparison of very short-term load forecasting techniques," IEEE Transactions on Power Systems, Vol.11, No.2, pp.877- 882.[25]W. Charytoniuk, M. S. Chen, 2000, "Very short-term load forecasting using artificial neural networks," IEEE Transactions on Power Systems, Vol.15, No.1, pp.263-268.[26]P. Shamsollahi et al, 2001, "A neural network based very short term load forecaster for the interim ISO New England electricity market system," The 22nd IEEE Power Engineering Society International Conference on Industry Computer Applications, Sydney, Australia, 20-24 May, pp.217-222.[27]Q. Chen et al, 2001, "Implementation and performance analysis of very short term load forecaster based on the electronic dispatch project in ISO New England," 2001 Large Engineering Systems Conference on Power Engineering, Halifax, Canada, 11-13 July, pp.98-104.[28]邱寬旭 ,2000 ,"類神經網路簡介",機電整合雜誌, 26 期,頁58-62,10 月。[29]葉怡成,2000,類神經網路模式應用與實作,儒林圖書,台北。[30]王進德、蕭大全,1999,類神經網路與模糊控制理論入門,全華科技圖書,台 北。[31]L. H. Tsoukalas, R. E. Uhrig, 1997, Fuzzy and neural approaches in engineering, John Wiley & Sons, New York.[32]N. K. Bose, P. Liang, 1996, Neural network fundamentals with graphs, algorithms, and applications, McGraw-Hill, Singapore.[33]古瓊景,1999,EMC類神經網路IC原理及應用,全華科技圖書,台北。[34]葉怡成,2000,應用類神經網路,儒林圖書,台北。[35]郭鑑瑩、黃基華,2001,遠端遙控之電能監控系統,國立高雄第一科技大學機械 與自動化工程所,學士論文。[36]W. L. Yao, J. H. Sun, C. H. Ku, 2000, "Design and implementation of automated monitoring and control electric systems," The 6th National Conference on AUTOMATION Technology, May 2000, Taipei, ROC, Vol.1, pp.179-185.[37]I. Drezga, S. Rahman, 1998, "Input variable selection for ANN-based short-term load forecasting," IEEE Transactions on Power Systems, Vol.13, No.4, pp.1238-1244.[38]S. Makridakis, S. C. Wheelwright, R. J. Hyndman, 1998, Forecasting Methods and Applications, 3rd Edition, John Wiley & Sons, New York.[39]胡坤德,1991,統計學,華泰書局,台北。[40]羅華強,2001,類神經網路-MATLAB的應用,清蔚科技,新竹。[41]吳菁菁,1993,類神經網路應用於短期用電量之預測,元智大學工業工程所,碩 士論文。[42]羅錦興,1999,田口品質工程指引,中國生產力中心,台北。[43]周至宏,2001,品質工程講義,國立高雄第一科技大學機械與自動化工程所品質 工程課程講義。[44]Delurgio,1999,預測的原則與應用,許純君譯,台灣西書出版社,台北。[45]Edgar E. Peters, 1991, Chaos and order in the capital markets, John Wiley & Sons, New York.[46]陳建宏,2001,應用灰色理論與模糊控制建構及時電力需量控制系統,國立高雄 第一科技大學機械與自動化工程所,碩士論文。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
1. 9.賴英照,證券交易法逐條釋義,第二冊,實用稅務出版社,民國81年
2. 2.王志誠,「公司事前監控制度與公司立法之國際化」,會計研究月刊第165期,民國88年6月,頁143。
3. 4.李啟賢,我國公司治理政策發展與現況-以政府角度觀察,實用月刊91年1月及91
4. 7.吳樂群,從金融風暴省思監察人制度的興與革,會計研究月刊第159期。
5. 8.吳明偉,「淺談內部稽核部門」,塑膠資訊,第5期,民國85年4月,頁76-77。
6. 10.林柄滄,「內部稽核與經營管理」,華信金融季刊,第1期,民國87年3 月,頁129。
7. 11.林柄滄,安隆破產事件引發的會計危機,會計研究月刊第195期。
8. 12.林幸宜,「美國金融機構如何實施自行查核工作」,彰銀資料,第47卷第4期,民國87年4月,頁24。
9. 13.林寬照,「建立內部稽核提升管理品質」,品質管制月刊,第34卷第11期,民國87年11月,頁74。
10. 14.林嬋娟、林囿成,由安隆案看分析師過度樂觀預測之後果,會計研究月刊第197期。
11. 16.柯承恩,我國公司監理體系之問題與改進建議(上)(下),會計研究月刊,173及174期,89年3月及4月。
12. 19.陳依蘋,「透明度與企業價值」,會計研究月刊第200期,2002年7月,頁50。
13. 20.黃華淋,「如何扮演一位稱職的內部稽核人員」,元大期貨,第7期,民國88年7月,頁67。