研究生: |
吳宗軒 Chung-Hsuan Wu |
---|---|
論文名稱: |
再生能源高滲透孤島電網機組排程之研究 Study on Unit Commitment of an Islanded Power Network with High Renewable Energy Penetration |
指導教授: |
陳在相
Tsai-Hsiang Chen |
口試委員: |
辜志承
Jyh-Cherng Gu 許炎豐 Yen-Feng Hsu 黃維澤 Wei-Tzer Huang 楊念哲 Nien-Che Yang |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2018 |
畢業學年度: | 106 |
語文別: | 中文 |
論文頁數: | 110 |
中文關鍵詞: | 負載預測 、機組排程 、類神經網路 、基因演算法 |
外文關鍵詞: | load forecasting, unit commitment, neural network, genetic algorithm |
相關次數: | 點閱:251 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
電能是目前人類生活最重要的能源,更是國家經濟發展之重要基石。對於電力公司而言,電力負載預測在機組排程、電網安全分析及經濟調度上均扮演著極為重要的角色,精準的負載預測不僅可以達到降低運轉所需成本的目標,也可以使電力能穩定且可靠的供應,避免造成限電危機或資源的浪費。然而,未來大量的再生能源發電系統將併入公共電網運轉發電,為穩定系統運轉頻率及電壓,再生能源發電預測在未來將更為關鍵。
本論文根據研究標的系統的歷史負載、再生能源發電資料、溫度資料,分析各日負載曲線的相似性,將用電曲線相近的歷史資料歸納為同一類型,接著利用倒傳遞類神經網路以及線性回歸分析法進行負載預測、再生能源預測。所開發之預測模組可以預測日前24小時之負載需量、再生能源發電量,接著以實際的時間序列數據進行驗證,以確定所提預測方法之可用性與準確性,模擬結果顯示,本文所提之預測方法確實可以做為機組排程之依據。又機組排程為決定機組發電狀態與發電機起停優先順位的系統運轉重要議題,本論文在機組排程上採用兩種方法求解,其一為以安全穩定運轉為前提下之方法;另一為使用基因演算法以最經濟為前題之方法,模擬結果印證此兩種方法皆可以達到各自所期望的目的。本論文之研究結果有助電力調度人員在高滲透再生能源發電情況下,做出準確之調度作為。
Nowadays, the electric energy is the most important energy for human life and the foundation of economic development for a country. For an electric power company, load forecasting plays an extremely important role in unit commitment, security analysis, and economic dispatch. An accurate load forecasting can achieve not only the goal of reducing operating costs, but also enables stable and reliable power supply, and avoids the electricity restriction or wastes valued resources as well. However, a renewable energy generation forecasting will become more and more important in the near future due to high penetration renewable energy generation systems will be interconnected to and parallel operated with the public grid. In order to stable the frequency and voltage of a bulk power network, the renewable energy generation forecasting become essential for future power system operations.
The analysis of this thesis is based on the historical load data, power generation data, and related temperature data. Firstly, the similarity of various daily load curves was analyzed. Then, the back propagation neural network and regression analysis method were applied to perform the load forecasting and renewable energy generation forecasting. The proposed prediction model can predict load demand and renewable energy generation of the next 24 hours. Finally, an actual load data was used to validate the availability and accuracy of the proposed method. The simulation results show that the proposed method can provide the essential data for the unit commitment. Unit commitment is a critical issue for the system operation to determine the status of units and priority of operation of generators. In this thesis two methods were used to solve the unit commitment problem. One method is based on the consideration of secure and stable operation; and the other method applies a genetic algorithm to consider the most economical approach. The simulation results show that both proposed methods can achieve the original purpose of this thesis research. The research outcomes of this thesis are of value to assist the power dispatcher for making more accurate scheduling while the system with high penetration renewable energy generation systems.
[1] A. D. Papalexopulos and T. C. Hesterberg, “A Regressionbased Approach to Short-Term Load Forecasting,".IEEE Transmission on Power System., Vol.5, pp.1214-1221, 1990.
[2] 鍾柏彥,「負載預測及契約容量最佳化之研究」,碩士論文,國立台灣科技大學電機研究所,民國105年。
[3] P. A. Mastorocostas, J. B. Theocharis and A. G. Bakirtzis, “Fuzzy Modeling for Short Term Load Forecasting Using the Orthogonal Least Squares Method," IEEE Transactions on Power Systems, Vol.14, pp.29-36, 1999
[4] M. Chow and H. TRAM, “Application of Fuzzy Logic Technology for Spatial Load Forecasting," IEEE Transactions on Power System, Vol.12, pp. 1360-1366, 1997.
[5] Y. M Wi, S. K. Joo,K.B. Song, “Holiday Load Forecasting Using Fuzzy Polynomial Regression With Weather Feature Selection and Adjustment," IEEE Transactions on Power System,, Vol.27, pp596-603,2012
[6] 李允中、王小璠、蘇木春,模糊理論及其應用(精裝本) ,全華科技圖書股份有限公司,2012年1月。
[7] T. Haida and S. Muto, “Regression Based Peak Load Forecasting Using a Transformation Technique,” IEEE Transaction on Power System, Vol.9, pp.1788–1794, 1994.
[8] R. E. Brown, A. P. Hanson and D. L. Hagan, “Long Range Spatial Load Forecasting Using Non-Uniform Areas," IEEE Transmission and Distribution Conference Proceedings, Vol.1, pp.369-373, 1999.
[9] 江孟峰,專家系統-導論/工具/應用,松崗文魁資訊股份有限公司,2002年11月。
[10] K.Y. Lee, and J.H. Park, “Short-term Load Forecasting Using an Artificial Neural Network,” IEEE Transactions on Power Systems, vol.7, no.1, pp.124-131, 1992.
[11] S.K. Kiartzis, A.G. Bakirtzi, and V. Petridis, “Short-Term Load Forecasting Using Neural Networks,” Electric Power systems Research, vol.33, pp.1-6, 1995.
[12] T.W.S. Chow, and C.T. Leung, “Neural Network Based Short-Term Load Forecasting Using weather Compensation,” IEEE Transactions on Power Systems, vol.11, no.4, pp.1736-1742, 1996.
[13] J. Vermaak and E. C. Botha, “Recurrent Neural Networks for Short-Term Load Forecasting," IEEE Transaction on Power System, Vol.13, pp.126-132, 1998.
[14] 孫智超,「微型電網負載預測之研究」,碩士論文,國立台灣科技大學電機研究所,民國101年。
[15] 蘇木春、張孝德,機器學習:類神經網路、模糊系統以及基因演算法則,2016年。
[16] 葉怡成,類神經網路模式應用與實作,儒林圖書公司,2009年。
[17] 羅華強,類神經網路:MATLAB的應用,高立圖書,2011年。
[18] S. J. Watson, L. Landberg, and J. A. Halliday, “Application of wind speed forecasting to the integration of wind energy into a large scale power system,” IEEE Trans. Energy Conversion, vol. 141, no. 4, pp. 357-362, Jul. 1994.
[19] G. N. Kariniotakis, G. S. Stavrakakis, and E. F. Nogaret, “Wind power forecasting using advanced neural networks models,” IEEE Trans. Energy Conversion, vol. 11, no. 4, pp. 762-767, Dec. 1996
[20] S. Li, D. C. Wunsch, E. A. O’Hair, and M. G. Giesselmann, “Using neural networks to estimate wind turbine power generation,” IEEE Trans. Energy Conversion, vol. 16, no. 3, pp. 836-842, Sep. 2001.
[21] P. Pinson, and G. N. Kariniotakis, “Wind power forecasting using fuzzy neural networks enhanced with on-line prediction risk assessment,” IEEE Bologna Power Tech Conference, vol. 2, no. 8, Jun. 2003.
[22] T. H. M. El-Fouly, E. F. El-Saadany, M. M. A. Salama,“Grey Predictor for Wind Energy Conversion Systems Output Power Prediction,” IEEE Transactions on power systems, vol. 21, no. 3, august 2006.
[23] Muhammad Khalid, Andrey V. Savkin, “A Method for Short-Term Wind Power Prediction With Multiple Observation Points,” IEEE Transactions on power systems, vol. 27, no. 2, march 2012.
[24] J. P. S. Catalão, H. Pousinho, and V. M. F. Mendes, “Hybrid wavelet-PSO-ANFIS approach for short-term wind power forecasting in Portugal,” IEEE Trans. Sustain. Energy, vol. 2, no. 1, pp. 50–59,Jan. 2011.
[25] J. Shi, J. Guo, and S. Zheng, “Evaluation of hybrid forecasting approaches for wind speed and power generation time series,” Renew. Sustain. Energy Rev., vol. 16, no. 5, pp. 3471–3480, 2012.
[26] Lalia Miloudi, Dalila Acheli, “Prediction Global Solar Radiation and Modeling Photovoltaic Module Based on Artificial Neural Networks,” Control, Engineering & Information Technology (CEIT), 2015 3rd International Conference on
[27] Amit Kumar Yadav, Hasmat Malik and S.S. Chandel,” Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models,” ELSEVIER, vol. 31, 2014, pp. 509-519.
[28] Roham Torabi, Sandy Rodrigues, Nuno Cafofo, F. Morgado-Dias, “Development of an ANN Model to Predict the Electricity Produced by Small Scale Roof-top PV Systems in Madeira Island,” Energy and Sustainability in Small Developing Economies (ES2DE), 2017.
[29] S. H. Oudjana, A. Hellal, and I. H. Mahamed, “Short term photovoltaic power generation forecasting using neural network,” in Proc. Int. Conf. Environ. Electr. Eng., 2012, pp. 706–711.
[30] Rehman S, Mohandes M, “Estimation of diffuse fraction of global solar radiation using artificial neural networks,” Energy Sources, Part A 2009;31:974–84
[31] 莊嘉琛「太陽能工程-太陽電池篇」,全華圖書出版
[32] H. T Yang, C. M Huang, Y. C Huang“A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output,” IEEE Transactions on sustainable energy, Vol. 5, No. 3, JULY 2014
[33] Electrical Generation Unit Commitment Planning, Application survey© LINDO Systems, August 2008.
[34] R. M. Burns and C. A. Gibson, “Optimization of Priority Lists for A Unit Commitment Program”, Paper A 75 453-1 Presented at the IEEE/PES Summer Meeting, 1975.
[35] Yang Tingfan, T. O. Ting,“Methodological Priority List for Unit Commitment Problem”, 2008.
[36] T. Senjyu, K. Shimabukuro, K. Uezato and T. Funabashi, “A Fast Technique for Unit Commitment Problem by Extended Priority List”, IEEE Transactions on Power Systems Vol. 18, No. 2, May 2003.
[37] Snyder, Jr. W. L.,Powell, Jr. H. D.,and Rayburn, J. C., “Dynamic Programming Approach to Unit Commitment”, IEEE Transactions on Power Systems Vol. 2, May 1987.
[38] Z. Ouyang, S. M. Shahidehpour, “An Intelligent Dynamic Programming For Unit Commitment Application” IEEE Transactions on Power Systems, Vol.6, No.3, August 1991.
[39] S. Kirkpatrick, C. D. Gelatt, Jr., and M. P. Vecchi, “Optimization by simulated annealing,” Science, vol. 220, pp. 671-680, May 1983.
[40] D. Simopoulos and G. Contaxis, “Unit Commitment with Ramp Rate Constraints Using the Simulated Annealing Algorithm”, IEEE Melecon, May, 2004.
[41] F Li, “Genetic AIgorithm Approach to More Consistent and Cost Effective Unit Commitment”, 2000.
[42] S. Jalilzadeh, Y. Pirhayati, “An Improved Genetic Algorithm for Unit Commitment Problem with lowest cost”, IEEE Melecon,December 2009.
[43] Alma Ademovic, Smajo Bisanovic, Mensur Hajro, “A Genetic Algorithm Solution to the Unit Commitment Problem Based on Real-Coded Chromosomes and Fuzzy Optimization”, IEEE Melecon,April 2010.
[44] 廖國清,「最佳演算法應用於負載預測及機組排程問題」,博士論文,國立中山大學電機工程系,民國九十四年。
[45] 陳維德,「應用免疫演算法最佳化火力機組調派」,碩士論文,國立台北科技大學電機工程系,民國九十七年。
[46] G. Xiao, S. Li, X. Wang and R. Xiao. ”A solution to unit commitment problem by ACO and PSO hybrid algorithm,” Proceedings of the 6 th World Congress on Intelligent Control and Automation, Dalian, China, 2006, pp. 7475-7479.
[47] L. M. Gambardella and M. Dorigo. “Solving symmetric and asymmetric TSPs by ant colonies,” Proceeding of IEEE International Conference on Evolutionary Computation, Nagoya, Japan, 1996, pp. 622-627.
[48] J. A. Muckstadt and S. A. Koenig, “An application of Lagrangian relaxation to scheduling in power generation systems”, Operations Research, 25(3):387-403, May-June 1977.
[49] Samer Takriti, John R. Birge, Erik Long, “A Stochastic Model for the Unit Commitment Problem”, IEEE Transactions on Power Systems, Vol. 11, No. 3, August 1996
[50] J. H Holland, Adaptation in Naural and Artificial System,Cambridge:the MIT Press, 1992
[51] Senjyu, T., H. Yamashiro, K. Uezato and T. Funabashi. “A unit commitment problem by using genetic algorithm based on unit characteristic classification,” IEEE/Power Eng. Soc. Winter Meeting,Vol. 1, pp58-63, Jan.2002.
[52] Jeong-Do Park, Hyun-Jong Kook, Young-Hyun Moon, Chul-Gyun Shin,“Unit Commitment Algorithm Considering the Effects of Economic Dispatch”, IEEE/Power Eng. Soc. Winter Meeting, Conference Proceedings, Jan.2000.
[53] California ISO. “RENEWABLES WATCH”, May 13. 2017