本研究使用複迴歸(本論文簡稱MR)及倒傳遞類神經網路(本論文簡稱BPNN)，預測對本案例冰水主機建立耗電量模型，並且比較此兩種方法在整年度冰水主機耗電量樣本數，經過資料收集及刪除不合理數據預測夏季6至9月份尖峰負載用電。
另外為了達到冰水主機耗能效果，將6至9月份冰水出水溫度提高0.5度，其他月份提高1度，再利用MR模型演算法及BPNN模型演算法預測冰水主機耗電量，比較耗能前後冰水主機耗能效率。最後以冰水主機負載耗電量來分析負載因數及需量因數，比較耗能前後負載利用率。

This study uses multiple regression and back propagation neural network, predict the establishment of power consumption model for the water chiller unit system in this case. and compare the number of samples of the power consumption of the water chiller nuit system in the whole year by these two methods. after data collection and deletion of unreasonable data,
The peak load electricity consumption in summer form June to September is predicted.
In addition, in order to achieve the energy consumption effect of the water chiller unit system,Increase the ice water outlet temperature from June to September by 0.5 , and increase by 1 in other months, prediction of power consumption of the water chiller unit system by using multiple regression and back propagation neural network, comparing the energy consumption efficiency of the water chiller unit system before and after energy saving. Finally, the load factor and demand factor of the water chiller unit system load power consumption are analyzed to compare the load utilization before and after energy consumption .

[1] 經濟部能源局，”台灣能源統計年報”。一零八年。
[2] 台灣綠色生產力基金會，”空調系統管理與節能手冊”。一零七年。
[3] 經濟部能源局，”能源轉型白皮書”。一零八年。
[4] 陳清良，”應用類神經網路與粒子群演算法於冰水主機負載分配最佳化”。國立臺北科技大學能源與
冷凍空調工程系博士論文，台北市大安區忠孝東路三段1號。一零三年一月。
[5] J. E. Braun, S. A. Klein, J. W. Mitcell and W. A. Beckman, “Applications of
Optimal Control to Chilled Water Systems without Storage”,ASHRAE Transactions
vol. 95(1) , pp.663-675, 1989.
[6] J. E. Braun, “Methodologies for the design and control of central of cooling
plants,” Ph.D. Dissertation, University of Wisconsin.
[7] R. J. Hackner, J. W. Mitcell and W. A. Beckman, “HVAC System Dynamics and
Energy Use in Buildings-Part I”,ASHRAE Transactions ,vol.90, pp.523-
535,1984.
[8] 黃明德，”半導體廠空調系統節能效益分析~以12吋DRAM廠為例”。國立交通大學工學院永續環境科
技學程碩士論文，新竹市東區大學路1001號。一零一年四月。
[9] T. T. Chow, Z. Lin, C. C. Song and G. Q. Zhang, “Applying Neural Network and
Genetic Algorithm in Chiller System Optimization”,Building Simulation,Seventh
International IBPSA Conference,pp.1059-1066,2001.
[10] 呂思賢，”以支持向量回預測空調主機支性能分析”。國立臺北科技大學能源與冷凍空調工程系碩
士論文，台北市大安區忠孝東路三段1號。一零四年六月。
[11] 陳森煌，”以現場實用測量結果作冰水主機部分負載性能分析”。國立臺北科技大學冷凍與低溫科
技研究所碩士論文，台北市大安區忠孝東路三段1號。九十年六月。
[12] 江彩绮，”冰水主機之性能提升及節能分析”。國立臺北科技大學能源與冷凍空調工程系碩士論
文，台北市大安區忠孝東路三段1號。一零二年六月。
[13] 江衍德，”結合模糊演算法之PLC控制系統應用於空調系統舒適度之研究”。國立臺北科技大學能源
與冷凍空調工程系碩士論文，台北市大安區忠孝東路三段1號。一零零年六月。
[14] 王文博，”冷凍工程”，大中國圖書公司。八十三年八月。
[15] ”分享冷凍循環系統四大主件功能與認識” http://www.coolaler.com/threads/72927/
[16] 經濟部能源局，中華民國90年9月12日經(90)能字第09004619170號公告之我國空調系統”冰水主
機能源效率標準”。九十年。
[17] 經濟部能源局，中華民國108年5月14日經(108)經受能字10805006700號公告之我國空調系統”
冰水主機能源效率標準”。一零八年。
[18] AHRAE Handbook,Supervisory Control Strategies and Optimization, 2003.
[19] 蕭明哲、沈志秋，”空調設備”，全華科技圖書公司。一零零年。
[20] 張永宗、陳清良，”變頻器於空調之節約能源應用”。國立臺北科技大學能源與冷凍空調工程系技
術簡報。
[21] ASHRAE Handbook, Liquid Chilling Systems, 2002, CH43.
[22] 蔡騰龍，”工業冷卻水處理概論”，正文出版社。八十五年九月。
[23] 許守平，”冷凍空調工程與原理”，全華科技圖書公司。九十五年七月。
[24] 方世榮、張文賢，”統計學導論”，華泰文化。一零七年八月。
[25] 陳順宇、鄭碧娥，”統計學”，華泰書局。九十三年三月。
[26] 蘇木春、張孝德，”機械學習：類神經網路、模糊系統以及基因演算法則”，
全華科技圖書公司。一零五年五月。
[27] 羅華強，”類神經網路 MATLAB 的應用”，高立圖書。一零零年十二月。
[28] P. Tenti, “Forecasting foreign exchange rates using recurrent neural
networks,”Applied Artificial Intelligence, vol.10, no.6, pp.567-582,1996.
[29] Jang, J.S.R., Sun, C.T and Mizutani,E.,“Neuro-Fuzzy and Soft Computing:A
Computational Approach to Learning and Machine Intelligence,”Prentice Hall,
1997.
[30] 張斐章、張麗秋，”類神經網路導論：原理與應用”，滄海書局。九十九年一月。
[31] Simon Haykin, “Neural Networks：A Comprehensive Foundation,” Prentice Hall,
International Editions, 1999.
[32] ”多層感知機” http://cilab.csie.ncu.edu.tw/course/nn/nn3.ppt
[33] 羅欽煌，”工業配電”，全華科技圖書公司。一零五年三月。
[34] 薛小生、黃郁東，”工業配電”，弘揚圖書。九十五年十一月。
[35] 王柏浤，”應用Information Entropy於冰水主機之排程改善”，國立臺北科技大 學能源與冷
凍空調工程系碩士論文，台北市大安區忠孝東路三段1號。一零四年六月。
[36] Oscar L. Olvera Astivia and Bruno D. Zumbo,“Heteroskedasticity in Multiple
Regression Analysis: What it is, How to Detect it and How to solve it with
Applications in R and SPSS.”Practical Assessment, Research & Evaluation,
vol. 24, no. 1, January 2019.
[37] Rupeh Kumar and Hyunkyoung Shin,“Thrust estimation of a flapping foil
attached to an elastic plate using multiple regression analysis.”
International Journal of Nava Architecture and Ocean Engineering, vol. 11,
pp. 824-834, February. 2018.
[38] Jing Wang, Jiandong Fang and Yvdong Zhao,“Visual prediction of gas diffusion
concentration based on regression analysis and BP neural network.”The Joural
of Engineering, vol. 2019, no. 13, pp. 19-23, November. 2018.
[39] Ali Jahani,“Forest landscape aesthetic quality model (FLAQM): A comparative
study on landscape modelling using regression analysis and artificial neural
networks.” Journal of Forest Science, vol. 65, no. 2, pp. 61-69, February.
2019.
[40] Paul R. Yarnold,“Multiple Regression vs. Novometric Analysis of a
Contingency Table.”Journal of Optimal Data Analysis, vol. 8, pp. 48-52,
February. 2019.
[41] Murat Sari, and arahed A. Ahmad,“Anemai Modelling Using the Multiple
Regression Analysis.”International Journal of Analysis and Applications,
vol. 17,no. 5, pp. 838-849, September. 2019.
[42] Md. Ismail Hossain, Md. Kamruzzaman, Abu Sayed Md. Al Mamun, Md. Nurul Islam
and Md. Golam Hossain,“Factors Influencing Nutritional Status of School
Going Children in Rural Area of Rajshahi District, Bangladesh: Multiple
Regression Analysis.”
International Journal of Statistical Sciences, Vol. 17, pp. 145-157, March.
2019.
[43] Zhaoyang Yea and Moon Keun Kimb,“Predicting electricity consumption in a
building using an optimized backpropagation and Levenberg–Marquardt back-
propagation neural network: Case study of a shopping mall in China.” Journal
of Sustainable Cities and Society, vol. 42, pp. 176-183, October. 2018.
[44] Zahraa Naser Shahweli, Ban Nadeem Dhannoon and Rehab S. Ramadhan,“ In Silico
Classification of breast and prostate Cancers using Back Propagation Neural
Network.” Journal of Cancer Biology, vol. 7(3), pp. 1-7, January. 2017.
[45] Jianbo Shen, Zongda Hu, Ram P. Sharma, Gongming Wang, Xiang Meng, Mengxi
Wang, Qiulai Wang and Liyong Fu,“Modeling Height–Diameter Relationship for
Poplar Plantations Using Combined-Optimization Multiple Hidden Layer Back
Propagation Neural Network.” Journal of forests, vol. 11, no. 442, pp. 1-19,
April. 2020.
[46] C. Bao, Y. Pu, and Y. Zhang,”Fractional-Order Deep Backpropagation Neural
Network.” Journal of Computational Intelligence and Neuroscience, vol. 2018,
Article ID 7361628, pp. 1-10, July. 2018.
[47] Harish Kumar Ghritlahre and Radha Krishna Pras,“Modelling of back
propagation neural network to predict the thermal performance of porous bed
solar air heater.” Journal of archives of thermodynamics, vol. 40, no. 4,
pp. 103-128, 2019.
[48] V. P. Ramesh, Priyanga Baskaran, Aarthika Krishnamoorthy, Divya Damodaran,
and Preethi Sadasivam,“Back propagation neural network based big data
analytics for a stock market challenge.” Journal of Communications in
Statistics, vol. 00, no. 0, pp.1-21, May. 2018.
[49] Xuebin Feng, Peijun He, Huaxi Zhang, Wenqing Yin, Yan Qian, Peng Cao and Fei
Hu,“Rice seeds identification based on back propagation neural network
model.”Journal of Int J Agric & Biol Eng, vol. 12, no. 6, pp. 122-128,
November. 2019.
[50] Tyler W. Hughes, Momchil Minkov, Yu Shi, and Shanhui Fan,“Training of
photonic neural networks through in situ backpropagation and gradient
measurement.” Journal of Optica, vol. 5, no. 7, pp. 864-871, July. 2018.
[51] Suman Khokhar and Satya Verma,“Content Based Image Retrieval with Multi-
Feature Classification by Back-propagation Neural Network.” Journal of
Computer Applications Technology and Research, vol. 6, no. 7, pp. 278-284,
2017.
[52] Siddharth Rawat,“Face Recognition Using Back Propagation Neural Network.”
Journal of Innovations in Engineering and Technology, vol. 10, no. 4, pp.
125-132, July. 2018.
[53] Dr. S. Senthil and B. Ayshwarya,“ Lung Cancer Prediction using Feed Forward
Back Propagation Neural Networks with Optimal Features.” Journal of Applied
Engineering Research, vol. 13, no. 1, pp. 318-325, Number. 2018.
[54] Falin Wang , Zhinong Li, Xuepeng Guo and Wenhe Liao,“Quality prediction and
control of cable harness wiring using extension theory and a backpropagation
neural network.” Journal of Advances in Mechanical Engineering, vol. 12, no.
5, pp. 1-19, March. 2020.