簡易檢索 / 詳目顯示

回結果列表
研究生： 周寶玉
Karijadi - Irene
論文名稱： 資料探勘於建築物內部能源消耗異常的偵測分析
Anomaly Detection Analysis for Building Energy Consumption Using Data Mining Technique
指導教授： 周碩彥
Shuo-Yan Chou
口試委員: 郭伯勳
Po-Hsun Kuo
喻奉天
Vincent F. Yu
學位類別： 碩士
Master
系所名稱： 管理學院 - 工業管理系
Department of Industrial Management
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 44
中文關鍵詞： 能源 、資料探勘與分析 、能源管理 、資料
外文關鍵詞： energy, data analysis, energy management, data
相關次數： 點閱：335  下載：0 
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
  •  上一筆

    • 過去十年，建築物能源管理議題引起多方的關注，因而促進節能策略的發展；隨著科技的日新月異，對能源的需求與消耗在近年也顯著得提高，而昂貴的電價與碳排放等連帶議題亦不容忽視；因此，善用記錄能源使用情況的資料並建立分析機制，以增強能源使用量監測系統是一條必經之路，本論文提出一個運用於觀察能源消耗數據的資料分析架構，並監測建築物內能源使用的異常狀況；最後，對此偵測異常狀況的演算法做性能比較，研究結果為，與異常預測模型及深度學習比較，密度模型有較好的精確度與特異性。
    關鍵字：能源、資料探勘與分析、能源管理、資料

    In the past decade, building energy management issue has drawn many attentions, which trigger the development of strategies for improving energy efficiency. Along with the rapid development of technology, the operation of energy consumption grows significantly in recent years, and the expensive electricity cost and carbon emission produced are hard to be ignored. Therefore, it is necessary to develop an energy data analysis mechanism to enhance the energy monitoring system. This thesis presents a data analysis framework for analyzing energy consumption data, and detecting anomaly condition in the building. Finally, a comparison of the performance of the anomaly detection algorithms was provided. The results show that the density based model had better accuracy and specificity than the anomaly prediction based model and deep autoencoder.

    Abstract i Acknowledgements ii Table of Contents iii List of Figures v List of Tables vi Chapter 1 Introduction 7 1.1 Background 7 1.2 Research Objective 8 1.3 Organization of Thesis 8 Chapter 2 Literature Review 9 2.1 Data Mining 9 2.2 Anomaly Detection 9 2.3 Prediction Based Anomaly Detection 10 2.4 Proximity Based Anomaly Detection 11 2.5 Density Based Anomaly Detection 11 2.6 Deep Autoencoders Anomaly Detection 12 2.7 Support Vector Regression 12 Chapter 3 Methodology 14 3.1 Towards an Energy Management Framework 14 3.2 Data Sources 16 3.3 Anomaly Detection Methodology 22 3.3.1 Data Preprocessing 23 3.3.2 Data Training and Testing 23 3.3.3 Density Based Anomaly Detection 24 3.3.4 Prediction BasedAnomaly Detection 24 3.3.5 Anomaly Detection using Deep autoencoder 26 3.3.6 Prediction Evaluation 28 3.3.7 Anomaly Detection Evaluation 28 Chapter 4 Analysis and Results 29 4.1 Data Preprocessing 29 4.2 Prediction 30 4.3 Anomaly Detection 32 4.3.1 Performance of the Anomaly Detection 33 4.3.2 Anomaly Detection of Taipei Bus Station Dataset 33 Chapter 5 Conclusions 37 5.1 Conclusions 37 5.2 Future Research 37 References 38 APPENDIX 40

    [1] L. Pérez-Lombard, J. Ortiz, and C. Pout, "A review on buildings energy consumption information," Energy and buildings, vol. 40, pp. 394-398, 2008.
    [2] U. Sbci, "Buildings and climate change: Summary for decision-makers," United Nations Environmental Programme, Sustainable Buildings and Climate Initiative, Paris, pp. 1-62, 2009.
    [3] K.-H. Yang and R. Hwang, "Energy conservation of buildings in Taiwan," Pattern recognition, vol. 28, pp. 1483-1491, 1995.
    [4] J.-S. Chou and N.-T. Ngo, "Smart grid data analytics framework for increasing energy savings in residential buildings," Automation in Construction, 2016.
    [5] X. Liu and P. S. Nielsen, "Regression-based Online Anomaly Detection for Smart Grid Data," arXiv preprint arXiv:1606.05781, 2016.
    [6] T. Silwattananusarn and K. Tuamsuk, "Data mining and its applications for knowledge management: a literature review from 2007 to 2012," arXiv preprint arXiv:1210.2872, 2012.
    [7] V. Chandola, A. Banerjee, and V. Kumar, "Anomaly detection: A survey," ACM computing surveys (CSUR), vol. 41, p. 15, 2009.
    [8] K. Marini, "Using dashboards to improve energy and comfort in federal buildings," Lawrence Berkeley National Laboratory, 2011.
    [9] D. Cheboli, "Anomaly detection of time series," University of Minnesota, 2010.
    [10] M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander, "LOF: identifying density-based local outliers," in ACM sigmod record, 2000, pp. 93-104.
    [11] A. Smola and V. Vapnik, "Support vector regression machines," Advances in neural information processing systems, vol. 9, pp. 155-161, 1997.
    [12] H. Janetzko, F. Stoffel, S. Mittelstädt, and D. A. Keim, "Anomaly detection for visual analytics of power consumption data," Computers & Graphics, vol. 38, pp. 27-37, 2014.
    [13] S. Kotsiantis, D. Kanellopoulos, and P. Pintelas, "Data preprocessing for supervised leaning," International Journal of Computer Science, vol. 1, pp. 111-117, 2006.
    [14] H.-x. Zhao and F. Magoulès, "A review on the prediction of building energy consumption," Renewable and Sustainable Energy Reviews, vol. 16, pp. 3586-3592, 2012.
    [15] J.-S. Chou and A. S. Telaga, "Real-time detection of anomalous power consumption," Renewable and Sustainable Energy Reviews, vol. 33, pp. 400-411, 2014.
    [16] W. Zhu, N. Zeng, and N. Wang, "Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS® implementations," NESUG proceedings: health care and life sciences, Baltimore, Maryland, pp. 1-9, 2010.
    [17] J. Sowa, "CO2-Based Occupancy Detection for On-Line Demand Controlled Ventilation Systems," Proceedings of Indoor Air, vol. 3, pp. 334-339, 2002.
    [18] I. Bonefacic, B. Frankovic, I. Vilicic, and V. Glazar, "Numerical modelling of temperature and air flow distribution in enclosed room," Proceedings of the Heat-SET 2007: Heat Transfer in components and systems for sustainable energy technologies, vol. 2, pp. 1055-62, 2007.
    [19] Z. Dacheng and X. Jie, "Multi-party authentication for Web services: protocols, implementation and evaluation," in Object-Oriented Real-Time Distributed Computing, 2004. Proceedings. Seventh IEEE International Symposium on, 2004, pp. 227-234.
    [20] J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, "Internet of Things (IoT): A vision, architectural elements, and future directions," Future Gener. Comput. Syst., vol. 29, pp. 1645-1660, 2013.
    [21] A. Segev and E. Toch, "Context-Based Matching and Ranking of Web Services for Composition," Services Computing, IEEE Transactions on, vol. 2, pp. 210-222, 2009.
    [22] C. Perera, A. Zaslavsky, C. H. Liu, M. Compton, P. Christen, and D. Georgakopoulos, "Sensor Search Techniques for Sensing as a Service Architecture for the Internet of Things," Sensors Journal, IEEE, vol. 14, pp. 406-420, 2014.

    無法下載圖示 全文公開日期 2022/01/23 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)
    QR CODE