本論文旨在運用類神經網路進行再生能源發電及負載需量預測，並利用預測結果求解微電網故障後復電重構最佳化問題。本論文利用溫度、濕度、太陽能發電量及負載需量等歷史資料進行太陽能發電及負載需量之預測，並使用多種指標評估預測能力，如RMSE、MSE、MAPE等。再以粒子群優演算法實現在多目標非線性函數與相關限制條件下，得到滿足微電網故障後復電線路重構的理想配置組合。最後本論文使用測試系統進行一系列模擬分析，藉以驗證本論文所提方法之可行性，模擬結果顯示，其預測精準度將影響後續排程與即時調度，由此可知再生能源發電與負載預測，對於微電網運轉極為重要。本論文所提方法確實可有效地進行再生能源發電及負載之預測，並應用於求解微電網故障後復電重構最佳化問題。

The main purpose of this thesis is to forecast renewable energy generations and load demand using artificial neural network, and the predictions were used to solve the optimal network reconfiguration of microgrids after fault occurred. In this thesis, the historical data of temperature, humidity, power generations of photovoltaic, and load demands were used to forecast the future power generations and load demands, and the indicators, such as RMSE, MSE, and MAPE were used to assess the forecasting capabilities. Furthermore, the particle swarm optimization algorithm was used to solve the multi-objective nonlinear function and related constraints of the optimal reconfiguration problem. In this thesis, a series of simulation analysis was carried out by using the test system to verify the feasibility of the proposed method. The simulation results demonstrated that the prediction accuracy affected the subsequent scheduling and real-time dispatch. Consequently, the accuracy of renewable energy power generation and load demand forecasting were extremely important for microgrids operations. The method proposed in this thesis can effectively predict the renewable energy generation and load demands. Moreover, it can be applied to solve the reconfiguration problem of microgrids after fault occurred.

摘要 I
Abstract II
謝誌 III
圖目錄 VII
表目錄 X
第一章緒論 1
1.1研究動機與背景 1
1.2文獻回顧 4
1.3研究方法與步驟 8
1.4論文架構 10
第二章再生能源發電及負載特性 11
2.1前言 11
2.2太陽光電發展現況 12
2.3負載特性探討與分析 19
2.4結語 33
第三章預測方法及誤差評估指標介紹 34
3.1前言 34
3.2類神經網路 35
3.3迴歸分析法 41
3.4內核法 49
3.5預測能力之評估指標 52
第四章程式模擬結果分析與探討 55
4.1前言 55
4.2資料彙整及格式設定 55
4.3類神經網路輸入因子選擇說明 56
4.4類神經網路流程規劃 57
4.5太陽能發電預測 58
4.6負載需量預測 62
4.7預測能力評估 66
4.8結語 72
第五章以預測結果為基礎之微電網最佳化故障復電模擬分析 73
5.1前言 73
5.2故障恢復策略及多目標非線性函式 75
5.3故障復電求解流程規劃 76
5.4測試系統與模擬情境說明 77
5.5微電網系統併網運轉模式 80
5.6微電網系統孤島運轉模式 84
5.7結語 88
第六章結論與未來研究方向 89
6.1結論 89
6.2未來研究方向 89
參考文獻 90

[1] R. H. Lasseter and P. Piagi, "Microgrid: A conceptual solution," in Proc. 35th PESC, Aachen, Germany, vol. 6, pp. 4285-4290, June 2004
[2] Renewable Microgrids: Profiles From Islands and Remote Communities across the Globe,http://www.rmi.org/Content/Files/RMI-Islands-RenewableMicrogrids-FINAL-20151103.pdf (accessed on 16/7/2016).
[3] J. Liu, W. Fang, X. Zhang and C. Yang, “An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data,” IEEE Transactions. Sustainable Energy, vol. 6, no. 2, pp. 434-442, Feb. 2015.
[4] Ye Ren, P. N. Suganthan, N. Srikanth, “Ensemble Methods for Wind and Solar Power Forecasting – AState-of-the-Art Review,”Renewable and Sustainable Energy Reviews, Volume 50, October 2015, Pages 82–91.
[5] C. Yang, A. Thatte, L. Xie, “Multitime-Scale Data-Driven Spatio-Temporal Forecast of Photovoltaic Generation,” IEEE Transactions. Sustainable Energy, vol. 6, no. 1, pp. 104-112, Nov. 2014.
[6] A. Bracale, P. Caramia, G. Carpinelli, A. R. D. Fazio and P. Varilone, “A Bayesian-Based Approach for a Short-Term Steady-State Forecast of a Smart Grid,” IEEE Transactions. Smart Grid, vol. 4, no. 4, pp. 1760-1771, Dec. 2013.
[7] L. Wu, M. Shahidehpour, “A hybrid model for integrated day-ahead electricity price and load forecasting in smart grid,”IET Generation. Transmission & Distribution,vol. 8, no. 12, pp. 1937-1950, Dec. 2014.
[8] C. Guan, P. B. Luh, L. D. Michel and Z. Chi, “Hybrid Kalman Filters for Very Short-Term Load Forecasting and Prediction Interval Estimation,” IEEE Transactions. Power Systems, vol. 28, no. 4, pp. 3806-3817, June. 2014.
[9] A. Khosravi, S. Nahavandi, “Load Forecasting Using Interval Type-2 Fuzzy Logic Systems: Optimal Type Reduction,” IEEE Transactions. Industrial Informatics, vol. 10, no. 2, pp. 1055-1063, Oct. 2013.
[10] E. G. Kardakos, M. C. Alexiadis, S. I. Vagropoulos, C. K. Simoglou, P. N. Biskas, and A. G. Bakirtzis, (2013,Sept). “Application of time series and artificial neural network models in short-term forecasting of PV power generation,” Power Engineering Conference (UPEC), 2013 48th International Universities, Dublin.
[11] H. Kebriaei, B. N. Araabi and A. R. Kian, “Short-Term Load Forecasting With a New Nonsymmetric Penalty Function,” IEEE Transactions. Power Systems, vol. 26, no. 4, pp. 1817-1825, May. 2011.
[12] J. Xie, T. Hong, J. Stroud, “Long-Term Retail Energy Forecasting With Consideration of Residential Customer Attrition,” IEEE Transactions.
Smart Grid, vol. 6, no. 5, pp. 2245-2252, Aug. 2015.
[13] G. Capizzi, C. Napoli and F. Bonanno, “Innovative Second-Generation Wavelets Construction with Recurrent Neural Networks for Solar Radiation Forecasting,” IEEE Transactions. Neural Networks and Learning Systems, vol. 23, no. 11, pp. 1805-1815, Oct. 2012.
[14] W. L. Jiao, H. L. Gao, G. F. Zhu, and T. Y. Li, "A service restoration method based on load balance expectation searching for smart distribution grid," in 2014 China International Conference on Electricity Distribution (CICED) Shenzhen 2014, pp. 1830-1833.
[15] J. Li, X. Y. Ma, C. C. Liu, and K. P. Schneider, "Distribution System Restoration With Microgrids Using Spanning Tree Search," IEEE Transactions on Power Systems, vol. 29, pp. 3021-3029, Nov 2014.
[16] D. Chen, X. Chen, and J. Liu, “Service restoration study of distribution system with distributed generators based on particle swarm optimization,” Advanced Power System Automation and Protection (APAP), 2011 International Conference on, 16-20 Oct. 2011.
[17] L. Zhao, and W. Z. Song, “A new multi-objective microgrid restoration via semidefinite programming,” Performance Computing and Communications Conference (IPCCC), 2014 IEEE International, 5-7 Dec. 2014.
[18] Y. Tian Y. Tian, and T. Lin, “A new strategy of distribution system service restoration using distributed generation,” in Proc. Int. Conf. Sustainable Power Generation and Supply, 2009, pp. 1027-1040.
[19] M.R. Kleinberg, K. Miu, and H. Chiang, “Improving service restoration of power distribution systems through load curtailment of in-service customers,” IEEE Trans. Power Syst., vol. 26, pp. 1110–1117, Aug. 2011.
[20] B. Ansari, S. Mohagheghi, “Electric Service Restoration using Microgrids,” in Proc. IEEE PES, 2014.
[21] B. Zhao, Y. Shi, X. Dong, W. Luan, and J. Bornemann, “Short-Term Operation Scheduling in Renewable-Powered Microgrids: A Duality- Based Approach,” IEEE Transaction on Sustainable Energy, 2014.
[22] S.Tan, J. Xu, and S.K. Panda, “Optimization of Distribution Network Incorporating Distributed Generators: An Integrated Approach,” IEEE Transaction on Power Systems, 2013.
[23] H. Wu, X. Liu, and M. Ding, “Dynamic economic dispatch of a microgrid: Mathematical models and solution algorithm,” Elsevier Electrical Power and Energy Systems, 2014.
[24] W. Wei, M. Sun, R. Ren, and Y. Wang, “Service restoration of distribution system with priority customers and distributed generation,”in Proc. ISGT, 2012.
[25] A. Khodaei and M. Shahidehpour, “Microgrid-Based Co-Optimization of Generation and Transmission Planning in Power Systems,” IEEE Transaction on Power Systems, 2013.
[26] 戴雯琪(2013)。再生能源在台灣之發展與現況─環境基本法十週年的省思。全國律師，3944，25-39。
[27] 張四立(2004)，我國電力部門再生能源發展之經濟與環境效益評估，碩士論文，國立臺北大學資源管理研究所。
[28] M. A. Green, K. Emery, Y. Hishikawa, W. Warta, and E. D. Dunlop, Solar cell efficiency tables (version 43), (wileyonlinelibrary.com), 2014; 22:1–9.
[29] 蔡進譯(2005)。超高效率太陽電池－從愛因斯場的光電效應談起(電子版)。物理雙月刊，5(27)，p.701。
[30] 維基百科，太陽能電池，https://zh.wikipedia.org/wiki/太陽能電池。
[31] 胡劭德(2013)。全球太陽光電產業的市場環境變遷趨勢及台灣太陽光電產業的因應策略，碩士論文，國立交通大學高階主管管理學程碩士班。
[32] 陳朝順、黃鐘慶、康渼松、黃佳文、林素真及楊海鵬，台電系統負載特性調查分析研究第三期計畫，台電工程月刊，92年1月，653期，73-91頁。
[33] 黃鶯玲、楊鐘亮及董金蓮，各主要行業用電負載特性分析，台電工程月刊，91年9月，650期，14-33頁。
[34] 陳以彥、許炎豐、劉志放、林建廷，三相不平衡背景值量測與負載不平衡特性分析，台灣電力公司電力綜合研究所研究發展專題報告，83年6月。
[35] 配電規劃需求功能整合應用研究完成報告，台灣電力股份有限公司101年度研究計畫，2012/9。
[36] 成政田(1999)，配電系統個別相負載計算技巧及其應用，博士論文，國立臺灣科技大學電機工程系。
[37] 負載管理年報，97年至101年台電業務處。
[38] 資料來源：https://gordoncheng.wordpress.com/2010/09/06/電力系統負載曲線load-curve/。
[39] 邵承矩(1993)，能源應用，東華書局出版。
[40] 葉怡成(2009)，類神經網路模式應用與實作，儒林。
[41] Neter, John(1998)，非線性迴歸與相關分析，華藝數位股份有限公司。
[42] 吳宗正(1996)，迴歸分析，三民書局股份有限公司。
[43] 王清標(2008)，迴歸分析應用在面板廠整合製造系統效能預測，碩士論文，國立成功大學工程科學系。
[44] 唐莎莉，商業軟體應用(二)，國立中央大學教學網，經濟系教材http://webclass.ncu.edu.tw/~tang0/。
[45] 李文偉(2002)，應用多元迴歸建立營建工程工率評估模式之研究
[46] 劉錦蕙(1999)，乾、濕季時間序列分析，碩士論文，逢甲大學。
[47] 孫嘉鴻(2004)，灰預測與演化式類神經網路應用於台指選擇權之研究，碩士論文，朝陽科技大學。
[48] Lewis, C.D. (1982), International and Business Forecasting Methods, London: Butterworths.
[49] T. W. S. Chow, C. T. Leung, 1996, “Neural network based short-term load forecasting using weather compensation,” IEEE Transactions on Power System, Vol.11, No.4, pp.1736-174(3-3)
[50] 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.
[51] 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。
[52] M. Tamimi, R. Egbert, 2000, “Short term electric load forecasting via fuzzy neural collaboration,” Electric Power Systems Research 56, pp.243-248.
[53] L. D. Voss, M. M. A. Salama, 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.
[54] Taylor, J. W. and Buizza, R, 2002, “Neural Network Load Forecasting with Weather Ensemble Predictions,” IEEE Transactions on Power Systems, Vol. 17, Issue 3, Aug., pp. 626-632.
[55] 陳竑廷(2016)，運用粒子群優演算法於主動配電網最佳重構與負載平衡之研究，碩士論文，國立彰化師範大學工業教育與技術學系。