簡易檢索 / 詳目顯示

回結果列表
研究生： 林書豪
Patrick - Theofilus Pardamean
論文名稱： 支援展示空間能源管理資料分析架構之研究
Development of a data analysis framework to support energy management in exhibition spaces
指導教授： 周碩彥
Shuo-Yan Chou
郭伯勳
Po-Hsun Kuo
口試委員: 喻奉天
Vincent F. Yu
學位類別： 碩士
Master
系所名稱： 管理學院 - 管理研究所
Graduate Institute of Management
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 48
中文關鍵詞： 空調能耗 、能源管理 、數據分析 、數據分類 、異常檢測
外文關鍵詞： air conditioning energy consumption, energy management, data analysis, data classification, outlier detection
相關次數： 點閱：255  下載：3 
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

    • 在建築部門的能源消耗對能源的一個重要問題。在美國，建築物消耗已經產生的總發電量的近70％。暖氣，通風空調（HVAC）是照明旁邊建設最大的能源消費國。本研究擬建立一個數據分析框架，以支持能源管理的展覽空間。擬議的實驗框架採用描述性分析，數據分類使用分類和回歸樹（CART）和異常檢測方法，利用廣義極端偏離學生化（GESD）。案例研究通過收集空調能耗，發展資產管理策略在國立台灣科學教育中心進行。主要發現顯示，空調能耗有時會消耗更多的能量恰到好處之前和博物館的開幕式和閉幕式後。

    Energy consumption in buildings sector is an important issue about energy. In the US, buildings already consume almost 70% of total electricity generated. Heating, Ventilating & Air Conditioning (HVAC) is the biggest energy consumer in building beside lighting. This study proposed development a data analysis framework to support energy management in exhibition spaces. The proposed experimental framework is using descriptive analysis, data classification using classification and regression trees (CART), and outlier detection method using generalized extreme studentized deviate (GESD). A case study was conducted in National Taiwan Science Education Center by collecting air conditioning energy consumption and developing asset management strategy. The main finding show that the air conditioning energy consumption sometimes consume more energy just right before and after the opening and closing of the museum.

    ACKNOWLEDGEMENT i ABSTRACT ii LIST OF FIGURES v LIST OF TABLES vii 1. INTRODUCTION 1 1.1. Research Background 1 1.2. Research Objective 2 1.3. Research Scopes and Limitations 2 1.4. Research Methodology 3 1.5. Writing Structure 3 2. LITERATURE REVIEW 5 2.1 HVAC Systems 5 2.1.1 Description 5 2.1.2 Types of Air Conditioning System 6 2.1.3 Energy Saving Measures HVAC Systems 9 2.2 Data Mining 9 2.2.1 Classification and Regression Trees 10 2.2.2 Outlier Detection 10 3. METHODOLOGY 12 3.1 Research Methodology 12 3.2 Data Collection 13 3.3 Descriptive Analysis 14 3.4 Data Pre-processing 15 3.5 Identification of Abnormal Daily Energy Consumption 15 3.5.1 Classification and Regression Trees (CART) 16 3.5.2 Generalized Extreme Studentized Deviate (GESD) 18 3.6 Energy Management 19 4. CASE STUDY AND ANALYSIS 22 4.1 Building Description 22 4.2 Descriptive Analysis 25 4.2.1 Short Period Analysis 25 4.2.2 Long-Period Analysis 27 4.2.3 Seasonal Period Analysis 30 4.2.4 Occupancy Impact 32 4.3 Identification of Abnormal Energy Consumption 37 4.4 Managerial Implications 43 5. CONCLUSION AND FUTURE WORKS 45 5.1 Conclusion 45 5.2 Future Works 45 REFERENCES 47

    [1] T. Weng and Y. Agarwal, "From Buildings to Smart Buildings—Sensing and Actuation to Improve Energy Efficiency," IEEE Design & Test of Computers, vol. 29, no. 4, pp. 36-44, 2012.
    [2] DOE, "Energy Data Book," Maryland, 2008.
    [3] J. Wade, J. Pett and L. Ramsay, "Energy Efficiency in Offices: Assessing," The Association for the Conservation of Energy, London, 2003.
    [4] "Florida Solar Energy Center," Florida Solar Energy Center, [Online]. Available: http://www.fsec.ucf.edu/en/consumer/buildings/commercial/hvac.htm. [Accessed 13 April 2016].
    [5] T. T. Services, 1 May 2016. [Online]. Available: www.techtransfer.com.
    [6] M. Saleh and M. Fadzli, "Active improvement of air-conditioning system energy consumption with adaptive thermal comfort approach," Glasgow, 2013.
    [7] Y. He, "Energy Saving of Central Air-Conditioning and Control System," Varkaus, 2010.
    [8] X. Yu, F. Haghighat and B. C. M. Fung, "Advances and challenges in building engineering and data mining applications for energy-efficient communities," Sustainable Cities and Society, vol. 25, pp. 33-38, 2016.
    [9] L. Breiman, J. H. Friedman, R. A. Olshen and C. I. Stone, Classification and regression trees, Belmont: Wadsworth, 1984.
    [10] I. Khan, A. Capozzoli , S. P. Corgnati and T. Cerquitelli, "Fault Detection Analysis of Building Energy Consumption Using Data Mining Techniques," Energy Procedia, vol. 42, pp. 557-566, 2013.
    [11] C. Fan, F. Xiao and S. Wang, "Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques," Applied Energy, vol. 127, pp. 1-10, 2014.
    [12] T. Hong, L. Yang, D. Hill and W. Feng , "Data and analytics to inform energy retrofit of high performance," Applied Energy 126, pp. 90-106, 2014.
    [13] B. Iglewicz and D. C. Hoaglin, How to detect and handle outliers, Milwaukee: ASQ Quality Press, 1993.
    [14] J. Seem, "Using intelligent data analysis to detect abnormal energy consumption in buildings," Energy and Buuildings 39, pp. 52-58, 2007.
    [15] D. Gordic, M. Babic, N. Jovicic, V. Sustersic, D. Koncalovic and D. Jelic, "Development of energy management system - Case study of Serbian car manufacturer," Energy Conversion and Management, pp. 2783-2790, 2010.
    [16] N. T. S. E. Center, "Floor plan," 18 May 2016. [Online]. Available: www.ntsec.gov.tw.

    QR CODE