2015 年台灣電力公司將停止補貼各大專學校的用電補助，這對於用電量日漸增加的學校是非常震撼的政策新聞。若停止電力補助後將會造成近億元的支出，已造成校園節能的目標迫在眉梢。要達到節能這個目標，需提供有效且淺顯易懂的電力資訊，讓用電管理者可以一目了然的理解用電狀態並加以管理控制用電行為。然而，如何提供讓管理者輕鬆理解的用電資訊是一個尚待克服的研究難題。有鑑於此，本篇論文提出透過熱點影像視覺化的圖像方式讓管理者直覺理解用電資訊，希冀讓用電管理者容易理解其用電規律性並快速找出與用電異常事件。我們透過中興大學理學大樓所收集約一年之詳細電力進行系統展示，來展示我們想法之可用性。我們將所開發之程式碼與使用之資料分別公開於github (https://github.com/UDICatNCHU/power_heatmap.git) 與dataverse ( https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi%3A10.7910%2FDVN%2FHT52KTversion=DRAFT)，希冀拋磚引玉吸引更多研究者投入相關研究。

In 2015, Taiwan Power Company will stop subsidizing the electricity subsidiesof various tertiary institutions, which is a very shocking policy news forschools with increasing electricity consumption. Taking the National Chung HsingUniversity campus as an example, the total electricity bill to be paid for thewhole year of 2015 is as high as more than 190 million NT dollars. If the subsidyis stopped, it will result in nearly 100 million yuan of expenditure. This hasforced the goal of energy conservation in schools tip of brow. To achieve thegoal of energy saving, effective and easy-to-understand power information needsto be provided so that power managers can understand the status of power consumptionand manage and control the power consumption at a glance. However,how to provide electricity information that managers can easily understand is adifficult research problem to be solved. In this thesis, we propose to view thepower consumption information by heat-map view to provide an intuitively interfacefor easily understanding power consumption behaviors.We demonstratethe usability of our ideas by systematically presenting the detailed electricitycollected by the National Chung Hsing University Science Building for approximatelyone year. We developed the code and use of the data are disclosedin github(https://github.com/UDICatNCHU/power_heatmap.git) and dataverse(https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi%3A10.7910%2FDVN%2FHT52KTversion=DRAFT), hoping to attract more researchers initiateinvestment in related research.

摘要i
Abstract ii
Contents. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
List of Tables. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv
List of Figures. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
第1章 緒論1
1.1 研究背景與動機. . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 研究目的與貢獻. . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2.1 蒐集校園實際用電資料. . . . . . . . . . . . . . . . . 3
1.2.2 基於電力資料透過熱點影像視覺化技術研究. . . . . . 4
1.3 研究架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
第2章 文獻探討6
第3章 研究方法9
第4章 實驗過程與結果23
4.1 實驗設定以及資料集的敘述. . . . . . . . . . . . . . . . . . . 23
4.2 使用熱點圖視覺化的觀點. . . . . . . . . . . . . . . . . . . . 26
第5章 結論38
參考文獻. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39

[1] J. Z. Kolter and M. J. Johnson, “Redd: A public data set for energy disaggregation research,” in Workshop on Data Mining Applications in Sustainability (SIGKDD), San Diego, CA, vol. 25, pp. 59–62, 2011.
[2] S. Lee, G. Ryu, Y. Chon, R. Ha, and H. Cha, “Automatic standby power management using usage profiling and prediction,” IEEE Transactions on Human-Machine Systems, vol. 43, no. 6, pp. 535–546, 2013.
[3] L. Guan, T. Berrill, and R. J. Brown, “Measurement of standby power for selected electrical appliances in australia,” Energy and Buildings, vol. 43, no. 2-3, pp. 485–490, 2011.
[4] E. U. Warriach, “State of the art: embedded middleware platform for a smart home,” International Journal of Smart Home, vol. 7, no. 6, pp. 275–294, 2013.
[5] A. Fang, X. Xu, W. Yang, and L. Zhang, “The realization of intelligent home by zigbee wireless network technology,” in Circuits, Communications and Systems, 2009. PACCS’09. Pacific-Asia Conference on, pp. 81–84, IEEE, 2009.
[6] G. W. Hart, “Nonintrusive appliance load monitoring,” Proceedings of the IEEE, vol. 80, no. 12, pp. 1870–1891, 1992.
[7] A. Marchiori, D. Hakkarinen, Q. Han, and L. Earle, “Circuit-level load monitoring for household energy management,” IEEE Pervasive Computing, vol. 10, no. 1, pp. 40–48, 2011.
[8] J. Liang, S. K. Ng, G. Kendall, and J. W. Cheng, “Load signature study —part i: Basic concept, structure, and methodology,” IEEE transactions on power Delivery, vol. 25, no. 2, pp. 551–560, 2010.
[9] J. Liang, S. K. Ng, G. Kendall, and J. W. Cheng, “Load signature study —part ii: Disaggregation framework, simulation, and applications,” IEEE Transactions on Power Delivery, vol. 25, no. 2, pp. 561–569, 2010.
[10] S. S. S. R. Depuru, L. Wang, and V. Devabhaktuni, “Support vector machine based data classification for detection of electricity theft,” in Power Systems Conference and Exposition (PSCE), 2011 IEEE/PES, pp. 1–8, IEEE, 2011.
[11] N. Henao, K. Agbossou, S. Kelouwani, Y. Dubé, and M. Fournier, “Approach in nonintrusive type i load monitoring using subtractive clustering,”IEEE Transactions on Smart Grid, vol. 8, no. 2, pp. 812–821, 2017.