台電為了舒緩興建電廠的急迫性及減輕供電壓力推行需量反應及需量競價，期望透過強化需求端負載管理使用戶能自主節電，而本研究即站在能源使用者的角色評估了成大電機參與需量反應的效益。
本研究利用歷史用電資料與歷史溫溼度訓練以一般回歸類神經為基礎的預測模型，預測電機大樓冷氣斷電後的用電量，再將預測之冷氣斷電後用電量輸入至基因演算法求解冷氣斷電最佳化排程，計算出最佳抑低量以及冷氣斷電策略以參加台電的需量反應方案，並在2018年6月份執行，由此結果評估參與需量反應的效益。

In order to relieve urgent need of new power plants as well as the pressure of power shortage, Taipower has promoted demand response (DR) program and biding options to consolidate demand side load management. This study evaluates the benefit for NCKU EE to partici-pate in the DR program.
The proposed methodology uses historical power consumption, temperature, and humidity statistics as training data to develop a general regression neural network (GRNN) model, so that it can predict the power consumption of the NCKU EE building after shedding its indi-vidual air conditioning (A/C) loads. The predicted power consumption after shedding air conditioning load is further used as input for the genetic algorithm to come up with optimal commitment of A/C load shedding. The proposed strategy was applied in June 2018 to check the benefit of joining the DR program.

[1]台電需量反應減少用電措施: https://www.taipower.com.tw/up load/135/2017110817314269395.pdf
[2]陳文瑞、張文奇,“自動需量反應用於空調冰水主機降載之研究,”研究計畫, 台灣電力股份有限公司,民國一百零六年一月.
[3]成大電機系能源網站: http://140.116.49.241/power/#/welcome
[4]董道廷,“電力系統短期負載預測,” 碩士論文,國立中山大學,民國一百零六年八月
[5] Kwang-Ho Kim, Jong-Keun Park, Kab-Ju Hwang and Sung-Hak Kim, "Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems," in IEEE Transactions on Power Systems, vol. 10, no. 3, pp. 1534-1539, Aug. 1995.
[6] A.Torzhkov, P. Sharma, C. Li, R. Toso and A. Chakraborty, "Chiller plant optimization - an integrated optimization approach for chiller sequencing and control," 49th IEEE Conference on Decision and Control (CDC), Atlanta, GA, 2010, pp. 2741-2746.
[7]邵時俊,“最佳化廣義回歸類神經網路於預測模型,”碩士論文,國立台北科技大學,民國一百年七月
[8]黃詩婷,“使用基因演算法進行微電網前一日機組排程,” 碩士論文, 國立臺灣海洋大學, 民國一百年六月
[9]葉育如,“最佳化函數設定於微型電網下電力調度之研究,”碩士論文,國立成功大學,民國一百零三年六月
[10]M. Aunedi, D. Skrlec, and G. Strbac, "Optimizing the operation of distributed generation in market environment using genetic algo-rithms," in The 14th IEEE Mediterranean Electrotechnical Confer-ence MELECON'08, pp. 780-785, May 2008.
[11]J. J. Grefenstette, "Optimization of Control Parameters for Genetic Algorithms," in IEEE Transactions on Systems, Man, and Cyber-netics, vol. 16, no. 1, pp. 122-128, Jan. 1986.
[12]Y. You, Z. Zhang, C. Liang and C. Guo, "Load prediction and op-timal control for green buildings with ice storage systems," 2014 9th IEEE Conference on Industrial Electronics and Applications, Hangzhou, 2014, pp. 1227-1230.
[13]Jui-Kun Lin “Optimum Chiller Load Distribution Using Genetic Algorithm” Master Dissertation, National Taipei University of Technology, 2003
[14]羅華強，「類神經網路-MATLAB的應用⸥，高立圖書有限公司
[15]R.G. Steadman, “A Universal Scale of Apparent Temperature,” Journal of Climate and Applied Meteorology, Vol. 23, No. 12, 1984. pp. 1674-1687.
[16]觀測資料查詢系統: https://ppt.cc/fMBtTx
[17]中央氣象局鄉鎮預報: https://ppt.cc/fn1rSx
[18]體感溫度預報服務 : https://ppt.cc/fnvp2x
[19]智慧型控制:分析與設計,全華科技圖書股份有限公司,2008年
[20]D. F. Specht , “A general regression neural network,” in IEEE Trans actions on Neural Networks, vol. 2, no. 6, pp. 568-576, Nov 1991.doi: 10.1109/72.97934
[21]葉怡成,“類神經網路模式應用與實作,”儒林圖書公司,台灣,民國八十九年
[22]成大電機系場地租借系統
[23]蘇木春、張孝德，「類神經網路、模糊系統、基因演算法法則⸥，全華科技圖書股份有限公司,2006年3月
[24]台灣電力公司,“詳細電價”:https://www.taipower.com.tw/upload/238/2018032911372895293.pdf