為了趨緩地球暖化的問題，國內各大企業開始實施節能減碳的運動，而IT數據機房是實施的重點之一，根據調查，大多數的IT數據機房，為加強散熱的效果，隨意擺放增加的散熱裝置，但熱區域依舊高溫不下，只是浪費更多的能源。為了避免能源的浪費，本研究將針對機櫃與空調的配置關係進行研究，尋找出最適當的排列方式，達到建立低耗能、高效能的數據機房。
本研究首先建立類神經系統所需的範例資料庫，利用FDS(Fire Dynamics Simulator)模擬數據機房散熱的情況，在空間中佈放虛擬之Thermocouple，獲取溫度數據建置成範例資料庫，放進類神經網路系統進行訓練，找出最佳化機櫃走道寬度，再將其結果回饋至FDS中驗證，了解機櫃與空調機之間複雜的影響關係，找到適當的空調機放置方式。
綜觀所有的研究結果可知，當數據機房內有完整的循環氣流時，數據機房會有比較好的散熱表現。適當的利用冷氣流下降及熱氣上升的原理，可以增加數據機房散熱的效果。相同的空調設定，會因為機櫃與冷氣位置擺放的方法不同，造成不同程度的散熱效果。

In order to ease the global warming problem, there were lots of companies started the green revolution in Taiwan. Most of the improvements were done in IT data center. According to the investigation, most of the IT data center placed additional air cooling in random ways. It couldn’t cool down the hot zone but wasted the energy instead. In order to avoid energy waste, this research used Artificial Neural Networks and FDS(Fire Dynamics Simulator) to deduce a better way to place air conditioners and venting exits. Such that the data center can be equipped with better cooling and performance.
The cases data base composed of FDS simulation data was created for artificial neural networks. In order to provide the simulation data, FDS computed the temperature distribution in the data center. Procedures in the case data center then trained and optimized the networks. The final results were fed into FDS again to verify and analyze the temperature variation in the data center.
The results showed that the circulated air stream enhanced the cooling effect. To improve cooling effect and reduce the loading of cooling systems, the heated air should be extracted from the upper part of the room since the warmer air was observed to accumulate in the region. Finally, the cooling effect would vary with different space arrangement even with the same air conditioner settings.

目錄			I
表目錄			IV
圖目錄			V
第一章	緒論		1
1.1	前言		1
1.2	文獻回顧		2
第二章	研究方法		7
2.1	數值方法		7
2.1.1	理論基礎		7
2.1.2	FDS簡介		7
2.1.3	統御方程式	8
2.1.4	紊流模式		10
2.1.5	網格與流場內物體的建立11
2.2	類神經最佳化[20]	12
2.2.1	類神經基本理論	12
2.2.2	基本人工神經元	12
2.2.3	網路系統架構	13
2.2.4	學習方式		14
2.2.5	倒傳遞類神經網路	15
2.2.6	倒傳遞網路演算法	15
第三章	類神經網路建制	19
3.1	FDS建模基本設定	19
3.2	範例庫應變設定	20
3.2.1	空調排列一	20
3.2.2	空調排列二	20
3.3	神經網路建構	21
3.3.1	網路參數最佳化	21
第四章	結果與分析	23
4.1	類神經訓練結果與分析23
4.1.1	空調空間排列一	23
4.1.2	空調空間排列二	24
4.2	FDS模擬結果與分析	24
4.2.1	空調空間排列一	24
4.2.2	空調空間排列二	25
4.3	天花板與迴風道之影響27
4.3.1	空調空間排列一	27
4.3.2	空調空間排列二	28
4.4	節能之效益	29
第五章	結論與建議	30
5.1.	結論		30
5.2.	未來研究建議	30
參考文獻	                32

表目錄
表 1：空調空間排列一之輸入值...........................................................34
表2：空調空間排列一範例庫之輸出值...............................................35
表3：空調空間排列二範例庫之輸入值...............................................36
表4：空調空間排列二範例庫之輸出值...............................................37
表5：空調空間排列一之最佳化輸入值...............................................37
表6：空調空間排列一之最佳化後輸出值...........................................38
表7：空調空間排列二之最佳化後輸出值...........................................38
表8：空調空間排列一之最佳化後模擬溫度值...................................38
表9：空調空間排列二之最佳化後模擬溫度值...................................38

圖目錄
圖 1：電信機房類用電比例...................................................................39
圖2：FDS運算流程...............................................................................40
圖3：生物神經元...................................................................................41
圖4：人工神經元...................................................................................41
圖5：網路分類(A)前饋式(B)回饋式.....................................................42
圖6：模型俯瞰示意圖...........................................................................42
圖7：網格參數示意圖...........................................................................43
圖8：風口與熱源示意圖.......................................................................43
圖9：THERMOCOUPLE設置示意圖........................................................43
圖10：氣流循環圖.................................................................................44
圖11：走道編號示意圖之一.................................................................44
圖12：空調空間排列一之CASE11走道寬度表示圖........................45
圖13：空調空間排列一之CASE21走道寬度表示圖........................45
圖14：空調空間排列一之CASE31走道寬度表示圖........................46
圖15：空調空間排列一之CASE41走道寬度表示圖........................46
圖16：空調空間排列一之CASE51走道寬度表示圖........................47
圖17：空調空間排列一之CASE61走道寬度表示圖........................47
圖18：空調空間排列一之CASE71走道寬度表示圖........................48
圖19：空調空間排列一之CASE81走道寬度表示圖........................48
圖20：走道編號示意圖之二.................................................................49
圖21：距天花板為0 M之示意圖.........................................................49
圖22：距天花板為0.2 M之示意圖......................................................49
圖23：距天花板為0.5 M之示意圖......................................................50
圖24：距天花板為0.8M之示意圖.......................................................50
圖25：距天花板為1.0 M之示意圖......................................................50
圖26：空調空間排列二示意圖.............................................................51
圖27：空調空間排列二之CASE11走道寬度表示圖........................51
圖28：空調空間排列二之CASE21走道寬度表示圖........................52
圖29：空調空間排列二之CASE31走道寬度表示圖........................52
圖30：空調空間排列二之CASE41走道寬度表示圖........................53
圖31：空調空間排列二之CASE51走道寬度表示圖........................53
圖32：空調空間排列二之CASE61走道寬度表示圖........................54
圖33：空調空間排列二之CASE71走道寬度表示圖........................54
圖34：空調空間排列二之CASE81走道寬度表示圖........................55
圖35：類神經網路建構流程圖.............................................................56
圖36：空調空間排列一之訓練相關性結果.........................................57
圖37：空調空間排列二之訓練相關性結果.........................................57
圖38：空調空間一之最佳化後CASE1 ...............................................58
圖39：空調空間一之最佳化後CASE2 ...............................................58
圖40：空調空間一之最佳化後CASE3 ...............................................59
圖41：空調空間一之最佳化後CASE4 ...............................................59
圖42：空調空間一之最佳化後CASE5 ...............................................60
圖43：空調空間一最佳化之比較圖.....................................................60
圖44：空調空間二之最佳化後CASE1 ...............................................61
圖45：空調空間二之最佳化後CASE2 ...............................................61
圖46：空調空間二之最佳化後CASE3 ...............................................62
圖47：空調空間二之最佳化後CASE4 ...............................................62
圖48：空調空間二之最佳化後CASE5 ...............................................63
圖49：空調空間二最佳化之比較圖.....................................................63
圖50：空調空間一CASE5與空調空間二CASE3之比較圖............64
圖51：空調空間排列一之溫度截圖.....................................................64
圖52：空調空間排列二之溫度截圖.....................................................65
圖53：空調空間排列一之CASE11~CASE15溫度比較圖................65
圖54：空調空間排列一之CASE21~CASE25溫度比較圖................66
圖55：空調空間排列一之CASE31~CASE35溫度比較圖................66
圖56：空調空間排列一之CASE41~CASE45溫度比較圖................67
圖57：空調空間排列一之CASE51~CASE55溫度比較圖................67
圖58：空調空間排列一之CASE61~CASE65溫度比較圖................68
圖59：空調空間排列一之CASE71~CASE75溫度比較圖................68
圖60：空調空間排列一之CASE81~CASE85溫度比較圖................69
圖61：空調空間排列一之天花板高度距離為0M時溫度截圖.........69
圖62：空調空間排列一之天花板高度距離為1M時溫度截圖.........70
圖63：空調空間排列二之天花板高度距離為0M時溫度截圖.........70
圖64：空調空間排列二之天花板高度距離為1M時溫度截圖.........71

[1] 聯合國氣候變化綱要公約參加國, 聯合國氣候變化綱要公約參加國會議,1997
[2] 台灣綠色生產力基金會,2009年非製造業能源查核年報,2010
[3] 韓選棠,徐嘉宏,汪孟欣,” 住宅建築利用熱緩衝空間對冷氣使用耗電量影響之                      研究-以台大綠房子為例”,農業工程學報,第56卷第2期,2000
[4] 許筱琪,”大樓建築自然通風效果模擬研究”,冷凍空調&能源科技,2011
[5] G. Carrilho da Graca, Q. Chen, L.R. Glicksman, L.K. Norford,”Simulation of wind-driven centilative cooling systems for an apartment building in Beijing and Shanghai”, Energy and Buildings, Vol.34,2002
[6] X. Lu, T. Lu, M. Remes, M. Viljanen, ”Energy Efficiency Assessment for Data Center in Finland：Case Study “, International Conference on Distributed Computing Systems Workshops, 2011
[7] C. E. Bash, C. D. Patel, R. K. Sharma , ”Dynamic Thermal Management of Air Cooled Data Centers “, Hewlett-Packard Laboratories, Palo Alto, CA
[8] U. Singh, A. K Singh, Parvez S, A. Sivasubramaniam, “CFD-Based Operational Thermal Efficiency Improvement of a Production Data Center,” Tata Consultancy Services Ltd., India
[9] 徐凡耘,”R公司之高效率資訊中心建置與節能探討”,國立中央大學資訊管理所,2011
[10]T. D. Boucher, D. M. Auslander, C. E. Bash, C. C. Federspiel, C. D. Patel, “Viability of Dynamic Cooliing Control in a Data Center Environment,” Inter Society Conference on Thermal Phenomena, 2004 
[11]B. Fakhim, M. Behnia, S.W. Armfield, N. Srinarayana, “Cooling Solutions in an Operational Data Centre：A case,” Applied Thermal Engineering, Vol.31, pp.2279-2291, 2011
[12]H. Shokouhmand, M. Ghazvini, J. Shabanian,” Performance Analysis of Using Nanofluids in Microchannel Heat Sink in Different Flow Regimes and its Simulation Using Artificial Neural Network,” Proceeding of the World Congress on Engineering 2008 Vol.III, 2008
[13]G.M. Stavrakakis, D.P. Karadimou, P.L. Zervas, H. Sarimveis, N.C. Markatos,” Selection of Window Sizes for Optimizing Occupational Comfort and Hygiene Based on Computational Fluid Dynamics and Neural Network,” Building and Environment Vol.46, pp.298-314, 2011
[14]陳正玲,”垂直導風板對室內自然通風效果影響之研究”,國立成功大學建築研究所(江哲銘), 2005
[15]梁青芳,“類神經網路簡化DOE程式對冷負荷計算之研究”,國立成功大學機械工程研究所, 2006
[16]廖俊傑,”燃燒爐之火災動態模擬”,淡江大學航空太空工程所,2006
[17] P. A. Friday, F. W. Mowrer , “Comparison of FDS Model Predictions with FM/SNL Fire Test Data,” Department of Fire Protection Engineering University of Maryland at College Park College Park, MD 20749, NIST.
[18] S. Ali, M. Shah,” A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability An alysis,” University of Central Florida, FL
[19]黃振禹,”高科技場迴風分析”, 淡江大學航空太空工程所,2009
[20]葉怡成,”應用類神經網路”,台北市,儒林圖書公司,第三版,2001
[21]F. Rosenblatt, “The Perceptron: A probabilistic model for information storage and organization in the brain,” Psychological Review, vol. 65, pp.386~408, 1958. 
[22] D. E. Rumelhart, J. L. McClelland,” An interactive activation model of context effects in letter perception: Part 2. The context enhancement effect and some tests and extensions of the model.” Psychological Review, Vol.89, pp. 60-94, 1982
[23]P. Blondeau, M. Sperandio, F. Allard,”Night Ventilation for Building Cooling in Summer,” Solar Energy, Vol.61, NO.5, pp.327-335,1997
[24]B. Zhao, X. Li, Q. Yan,” A Simplified System for Indoor Airflow Simulation,” Building and Environment, Vol.38, pp.543-552, 2003
[25]J. F. Karlsson, B. Moshfregh,” Investigation of Indoor Climate and Power Usage in A Data Center,” Energy and Buildings, Vol.37, pp.1075-1083, 2005
[26]C. O. Karacan,” Development and Application of Reservoir Models and Artificial Neural Networks for Optimizing Ventilation Air Requirements in Development Mining of Coal Seams,” International Journal Of Coal Geology, Vol. 72, Pp.221–239, 2007