能源相關現今已被越來越重視，雖然人們已開始有想要節能的環保意識，但卻仍然跟不上人口的快速攀升以及市場的需求，特別是開發中國家需要大量的能源以發展他們的產業。然而，能源管理系統這塊市場也正快速興起，尤其是建築能源管理系統，因為根據調查建築所佔能源消耗60%。雖然再生能源市場也正在興起，但由於生產所占比例仍還不足，且供應也還尚不穩定，目前仍然無法完全取代石化能源。

因此，如何在滿足用戶需求的情況下提高能源的使用效率才是現在相關領域所著重的目標，本研究將以建立建築能源系統的架構下進行建築耗能模式分析，過去就有的能源管理系統以無法滿足現代多元化的需求，必須與現代新興科技整合並發展智慧應用，才能有效的提高能源使用效率。

最後，我們以台灣科技大學為案例分析，從所安裝的兩百多顆電錶中，建立資料導向的能源管理系統，並對現階段所蒐集到的資料做初步的分析，找出建築中日常能耗模式，利用這些分析結果作更深入的研究。

Energy-related issues have become more and more important nowadays. Although people have begun to have environmental awareness that to do energy conservation, we still can't keep up with the rapid rise of population and market demand. Especially for developing countries,they still need more energy to develop their industry. However, the market for energy management systems is also rapidly emerging, specially building energy management systems, due to the energy consumption of buildings is 60%. Although the renewable energy market also arise, but the proportion of production is still insufficient to fulfill the demand. And the supply is also unstable, renewable energy is still unable to completely replace petrochemical energy.

How to improve energy efficiency without sacrifice personal needs is now focusing on. This study will analyze the building energy consumption profile under the framework of establishing a building energy system. In order to satify the modern diversity demands, it is necessary to integrate and develop smart applications with modern emerging technologies in order to effectively improve energy efficiency.

In our research, we use Taiwan University of Science and Technology as a case study to establish a data-oriented energy management system from more than 200 installed meters, and make a preliminary analysis of the data collected at this stage to find out the daily energy in the building. We can use the result of this study to llearn futher more in-depth research.

[1] B. p.l.c. BP Statistical Review 2019 launch event. Available: https://www.bp.com/
[2] X. Cao, X. Dai, J. J. E. Liu, and buildings, "Building energy-consumption status worldwide and the state-of-the-art technologies for zero-energy buildings during the past decade," vol. 128, pp. 198-213, 2016.
[3] "Energy Management Systems (EMS) Market Analysis By Product (IEMS, BEMS, HEMS), By Component (Sensors, Controllers, Software, Batteries, Display Devices), By Vertical (Power & Energy, Telecom & IT, Manufacturing, Retail & Offices, Healthcare), By End-Use (Residential, Commercial) And Segment Forecasts To 2024," Oct, 2016.
[4] V. Marinakis et al., "From big data to smart energy services: An application for intelligent energy management," 2018.
[5] F. Al-Turjman and M. J. F. G. C. S. Abujubbeh, "IoT-enabled smart grid via SM: An overview," 2019.
[6] V. Marinakis, A. G. Papadopoulou, H. Doukas, J. J. I. J. o. I. Psarras, and D. Sciences, "A web tool for sustainable energy communities," vol. 7, no. 1, pp. 18-31, 2015.
[7] C. Cooremans and A. J. J. o. C. P. Schönenberger, "Energy management: A key driver of energy-efficiency investment?," vol. 230, pp. 264-275, 2019.
[8] W.-S. J. E. Lee and Buildings, "Benchmarking the energy efficiency of government buildings with data envelopment analysis," vol. 40, no. 5, pp. 891-895, 2008.
[9] F. Maghsoodlou, R. Masiello, T. J. I. P. Ray, and E. Magazine, "Energy management systems," vol. 2, no. 5, pp. 49-57, 2004.
[10] D. D. Sharma, S. Singh, L. Jeremy, E. J. J. o. M. P. S. Foruzan, and C. Energy, "Identification and characterization of irregular consumptions of load data," vol. 5, no. 3, pp. 465-477, 2017.
[11] I. Benítez, A. Quijano, J.-L. Díez, I. J. I. J. o. E. P. Delgado, and E. Systems, "Dynamic clustering segmentation applied to load profiles of energy consumption from Spanish customers," vol. 55, pp. 437-448, 2014.
[12] K. Wang, X. Qi, H. Liu, and J. J. E. Song, "Deep belief network based k-means cluster approach for short-term wind power forecasting," vol. 165, pp. 840-852, 2018.
[13] S. Joseph and J. J. I. T. o. E. E. S. Erakkath Abdu, "Real‐time retail price determination in smart grid from real‐time load profiles," vol. 28, no. 3, p. e2509, 2018.
[14] K. Song, S. Kim, M. Park, and H.-S. J. E. Lee, "Energy efficiency-based course timetabling for university buildings," vol. 139, pp. 394-405, 2017.
[15] C. Fan, F. Xiao, and S. J. A. E. Wang, "Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques," vol. 127, pp. 1-10, 2014.
[16] W. J. A. E. Chung, "Review of building energy-use performance benchmarking methodologies," vol. 88, no. 5, pp. 1470-1479, 2011.
[17] T. Silwattananusarn and K. J. a. p. a. Tuamsuk, "Data mining and its applications for knowledge management: a literature review from 2007 to 2012," 2012.
[18] M. Halkidi, Y. Batistakis, and M. J. J. o. i. i. s. Vazirgiannis, "On clustering validation techniques," vol. 17, no. 2-3, pp. 107-145, 2001.
[19] C. Phua, V. Lee, K. Smith, and R. J. a. p. a. Gayler, "A comprehensive survey of data mining-based fraud detection research," 2010.
[20] T. W. J. P. r. Liao, "Clustering of time series data—a survey," vol. 38, no. 11, pp. 1857-1874, 2005.
[21] N. Kaur and S. K. J. I. S. J. Sood, "An energy-efficient architecture for the Internet of Things (IoT)," vol. 11, no. 2, pp. 796-805, 2015.
[22] E. Mocanu, P. H. Nguyen, M. Gibescu, W. L. J. S. E. Kling, Grids, and Networks, "Deep learning for estimating building energy consumption," vol. 6, pp. 91-99, 2016.
[23] M. J. Kofler, C. Reinisch, W. J. E. Kastner, and Buildings, "A semantic representation of energy-related information in future smart homes," vol. 47, pp. 169-179, 2012.