分析住宅內電器用電資料以尋找節電或浪費樣式，對於達到節能減碳目標至關重要，同時也能夠提供家戶更有效瞭解住宅整體狀況。隨著物聯網的發展，目前已有各式智慧插座能偵測與蒐集電器用電與附近環境資料，歐美各國也已公開家戶用電資料集合供各界研究。已公開的用電紀錄常取樣過於頻繁、未考慮電器所在空間、將電器與插座視為固定關係，及欄位設計不當等，造成不利於時空資料分析等問題。
本研究旨在提出一套通用的用電紀錄格式與相關分析模型，若能從建築中得到插座空間位置，套用本作法則能大幅縮減用電紀錄筆數卻不失真，可從中尋找特定用電樣式提醒住戶改變行為，最後以序列資料探勘(Generalized Sequential Patterns Mining, GSP)分析節電戶與浪費電戶的常見用電行為。
應用本作法於其他用電資料集合，可預期能讓住戶瞭解自身用電行為進而改善，與促進用電樣式分析技術的完備，未來物聯網架構下之住家能源管理系統也可以更經濟、更有效的方式分析用電紀錄。

It is crucial to analyze residential appliance power consumption data in order to identify patterns of power-saving and power-wasting behaviors and to achieve the goals of energy saving and carbon reduction. Providing better understanding of entire residential power usage information to residents is of most importance. With the development of the Internet of Things (IoT) technology, a variety of smart power plugs can be used to measure and collect power usage data consumed by each appliance in a household. Several research reports on household electricity usage datasets have been published worldwide. However, problems such as sampling frequency, lack of room or location information, and ignorance of dynamic relationships between appliances and power sockets have not been adequately addressed in the literature. This research aimed at providing a commonly used electricity consumption form and a related analyzing tool. By applying the proposed method and tool, it can be expected that households may be able to better understand their power utilization behaviors and to make appropriate improvements, while also promoting completeness of power consuming patterns analysis. In the future, under the framework of IoT, home energy management system can facilitate a more economical and effective way to analyze power consuming records.

1. Lee, M., Uhm, Y., Kim, Y., Kim, G., & Park, S. (2009). Intelligent Power Management Device with Middleware based Living Pattern Learning for Power Reduction. Ieee Transactions on Consumer Electronics, 55(4), 2081-2089.
2. Zayour, I., & Hamdar, A. (2016). A qualitative study on debugging under an enterprise IDE. Information and Software Technology, 70, 130-139.
3. Ellul, C. (2012). Can Free (and Open Source) Software and Data be Used to Underpin a Self-Paced Tutorial on Spatial Databases? Transactions in Gis, 16(4), 435-454.
4. Frenzel, L. (2007). Experience report: Building an Eclipse-based IDE for Haskell. Acm Sigplan Notices, 42(9), 220-222.
5. Tseng, W. T., Chiang, W. F., Liu, S. Y., Roan, J., & Lin, C. N. (2015). The Application of Data Mining Techniques to Oral Cancer Prognosis. Journal of Medical Systems, 39(5), 7.
6. Cho, H. S., Yamazaki, T., & Hahn, M. (2010). AERO: Extraction of User's Activities from Electric Power Consumption Data. Ieee Transactions on Consumer Electronics, 56(3), 2011-2018.
7. Alhamoud, A., Ruettiger, F., Reinhardt, A., Englert, F., Burgstahler, D., D, B., . . . Steinmetz, R. (2014, 8-11 Sept. 2014). SMARTENERGY.KOM: An intelligent system for energy saving in smart home. Paper presented at the Local Computer Networks Workshops (LCN Workshops), 2014 IEEE 39th Conference on.
8. Pei, J., Han, J. W., Mortazavi-Asl, B., Wang, J. Y., Pinto, H., Chen, Q. M., . . . Hsu, M. C. (2004). Mining sequential patterns by pattern-growth: The PrefixSpan approach. Ieee Transactions on Knowledge and Data Engineering, 16(11), 1424-1440.
9. Guerassimoff, G., & Thomas, J. (2015). Enhancing energy efficiency and technical and marketing tools to change people's habits in the long-term. Energy and Buildings, 104, 14-24.
10. Lichman, M. (2013). Machine Learning Data Sets, UCI Machine Learning Repository, Retrieved from http://archive.ics.uci.edu/ml (April 26, 2016).
11. Alaa Alhamoud, M. Sc. (2014). SMARTENERGY.KOM, KOM - Multimedia Communications Lab: SMARTENERGY.KOM, Retrieved from https://www.kom.tu-darmstadt.de/research-results/software-downloads/software/smartenergykom/ (April 26, 2016).
12. Marc Liberatore, (2013). UMass Trace Repository, Smart - UMass Trace Repository, Retrieved from http://traces.cs.umass.edu/index.php/Smart/Smart (April 26, 2016).