臺灣博碩士論文加值系統

根據聯合國環境規劃署UNEP估計，建築物所消耗的能源和釋放的溫室氣體占全世界能源總消耗量的40%左右，因此世界各國均視建築節能為減少溫室氣體排放的一個重要手段 [1]。其中我們關注的是提高能源效率—特別是電力—以減少電力浪費。由於BAS整合了各種電器控制，溫濕度、照明、頻率、水池流量、二氧化碳濃度等等，這些大量的歷史紀錄，使統計為導向的數據挖掘方法也因此能夠應用在建築能源預測上。能源管理者可藉由預測結果進行能源控制。
本研究在一部份提出了用在電量預測的特徵轉換方式，以及預測的架構。首先透過資料視覺化的方式分析使用者行為，並從資料視覺化的結果及文獻篩選進一步挑選適合的作為訓練資料的感測器，最後以Support vector machine（SVR）及線性加權回歸（WLR）進行用電量擬合。
第二部分為應用深度學習模型再用電量的預測。由於加權回歸模型與SVR須進行一層又一層的篩選，才能找出有關連的參數、特徵才能得到較佳的結果，但篩選過程中，不同篩選方式難免有疏漏或是難以描述的部分，因此我們提出了幾種不同的架構，能夠更全面的採用更多感測器的資訊，也能在少數幾個感測器受擾動時能夠避免模型完全失去預測能力。
本研究提供了更佳準確及彈性的架構，並有一個清楚的方法及流程作為參考，讓不同樣本數大小的資料集可以依據資料的特性選擇適合的預測架構。以達到預測的目的。

According to UNEP, the energy consumption and greenhouse gas discharged by buildings are responsible for about 40% of the global energy used. Thus, the energy efficiency is an important mean of reducing greenhouse gas emission. Among the improving methods, we put our attentions on energy efficiency to cut energy waste, especially on electricity consumption. In the past decades, the rate of buildings with Building Automation System (BAS) is increasing. BAS integrates electrical consumption, temperature, humidity and so on, which depends on the building. With various kinds of record, BAS allows data mining techniques to support decision making.
The first part of our research developed an approach of feature extraction and a prediction structure which will be utilized in energy forecasting. To begin with, we analyzed user behavior by data visualization. Next, we selected the appropriate sensors to obtain training data through observing the results on the last step and literature reviews. At the last, we apply support vector regression (SVR) and weighted linear regression to train a regression model.
In the second part of this study, we presented some deep learning structures to forecast electricity consumption. In the last part of our research, we combined some ways to select proper sensors. In addition, we made multiple steps to train a better model. To solve difficult problems such as that features are hard to describe, we integrated Deep Learning in this chapter.
To sum up, we build a flexible and accuracy architecture which different BAS data and field can be applied in. In additional, we also provide a clear method and process as an example, so that people can select the appropriate forecasting architecture based on the characteristics of their data.

口試委員會審定書 #
中文摘要 i
ABSTRACT ii
CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES ix
第1章 緒論 1
1.1 研究背景與動機 1
1.2 文獻回顧 3
1.2.1 用電預測需求 3
1.2.2 現有預測方法 4
1.2.3 電量數據特性 5
1.3 研究目的 5
1.4 論文組織 6
第2章 資料描述與分析方法 8
2.1 資料與場域描述 8
2.2 分析架構與順序 10
第3章 感測器篩選與預測模型 15
3.1 方法 15
3.1.1 感測器篩選與資料視覺化 15
3.1.2 特徵選擇 17
3.1.3 加權線性回歸 20
3.1.4 SVR 21
3.1.5 時間序列交叉驗證 22
3.2 感測器篩選 23
3.3 篩選模型 26
3.4 回歸模型 29
3.5 特徵模型 39
3.6 小結 44
第4章 深度學習預測模型 46
4.1 Recurrent Neural Network 47
4.2 Deep Neural Network 50
4.3 小結 53
第5章 論文總結 56
5.1 結果與討論 56
5.2 未來方向與建議 57
參考文獻 60

[1]Marasco, D. E., & Kontokosta, C. E. (2016). Applications of machine learning methods to identifying and predicting building retrofit opportunities. Energy and Buildings, 128, 431-441.
[2]陳海曙(2014), 建築物智慧能資源管理系統, 經濟部103年度政府機關學校能源管理與節能技術節能種子教師調訓班簡報資料，下載連結網址https://www.ftis.org.tw/active/download/pr1-1030820-2-class1-0821.pdf
[3]P. Waide, J. Ure, N. Karagianni, G. Smith, B. Bordass, The scope for energy and CO2 savings in the EU through the use of building automation technology, Final Report for the European Copper Institute, August 10 2013.
[4]Fan, C., Xiao, F., & Yan, C. (2015). A framework for knowledge discovery in massive building automation data and its application in building diagnostics. Automation in Construction, 50, 81-90.
[5]Accenture (2011) Energy-Smart Buildings: demonstrating how information technology can cut energy use and cost of real estate portfolios. retrieved from http://czgbc.org/energy-smart-buildings-whitepaper.pdf.
[6]Dong, B., Cao, C., & Lee, S. E. (2005). Applying support vector machines to predict building energy consumption in tropical region. Energy and Buildings, 37(5), 545-553.
[7]Xiao, F., & Fan, C. (2014). Data mining in building automation system for improving building operational performance. Energy and buildings, 75, 109-118.
[8]Mathieu, J. L., Price, P. N., Kiliccote, S., & Piette, M. A. (2011). Quantifying changes in building electricity use, with application to demand response. IEEE Transactions on Smart Grid, 2(3), 507-518.
[9]Agarwal, Y., Balaji, B., Gupta, R., Lyles, J., Wei, M., & Weng, T. (2010, November). Occupancy-driven energy management for smart building automation. In Proceedings of the 2nd ACM workshop on embedded sensing systems for energy-efficiency in building (pp. 1-6). ACM.
[10]Kleiminger, W., Beckel, C., Staake, T., & Santini, S. (2013, November). Occupancy detection from electricity consumption data. In Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings (pp. 1-8). ACM.
[11]Fan, C., Xiao, F., & Wang, S. (2014). Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques. Applied Energy, 127, 1-10.
[12]Marino, D. L., Amarasinghe, K., & Manic, M. (2016, October). Building energy load forecasting using deep neural networks. In Industrial Electronics Society, IECON 2016-42nd Annual Conference of the IEEE (pp. 7046-7051). IEEE.
[13]Amin-Naseri, M. R., & Soroush, A. R. (2008). Combined use of unsupervised and supervised learning for daily peak load forecasting. Energy Conversion and Management, 49(6), 1302-1308.
[14]Khan, I., Capozzoli, A., Corgnati, S. P., & Cerquitelli, T. (2013). Fault detection analysis of building energy consumption using data mining techniques. Energy Procedia, 42, 557-566.
[15]Wang, H., Xu, P., Lu, X., & Yuan, D. (2016). Methodology of comprehensive building energy performance diagnosis for large commercial buildings at multiple levels. Applied Energy, 169, 14-27.
[16]Elena Mocanu, Phuong H. Nguyen, Madeleine Gibescu, Wil L. Kling, Deep learning for estimating building energy consumption, Sustainable Energy, Grids and Networks, Volume 6, June 2016, Pages 91-99
[17]De Wilde, P., Martinez-Ortiz, C., Pearson, D., Beynon, I., Beck, M., & Barlow, N. (2013). Building simulation approaches for the training of automated data analysis tools in building energy management. Advanced Engineering Informatics, 27(4), 457-465.
[18]Kavousi-Fard, A., Samet, H., & Marzbani, F. (2014). A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting. Expert systems with applications, 41(13), 6047-6056.
[19]G. Escrivá-Escrivá, et al., New artificial neural network prediction method for electrical consumption forecasting based on building end-uses, Energy Build. 43 (11) (2011) 3112–3119.
[20]Chae, Y. T., Horesh, R., Hwang, Y., & Lee, Y. M. (2016). Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings. Energy and Buildings, 111, 184-194.
[21]The Commission for Energy Regulation (CER)
[22]Australian Government(2015) https://data.gov.au
[23]Beckel, C., Sadamori, L., Staake, T., & Santini, S. (2014). Revealing household characteristics from smart meter data. Energy, 78, 397-410.
Haben, S., Singleton, C., & Grindrod, P. (2016). Analysis and clustering of residential customers energy behavioral demand using smart meter data. IEEE transactions on smart grid, 7(1), 136-144.
[24]Fan, C., Xiao, F., & Zhao, Y. (2017). A short-term building cooling load prediction method using deep learning algorithms. Applied Energy, 195, 222-233.
[25]Chua, K. J., Chou, S. K., Yang, W. M., & Yan, J. (2013). Achieving better energy-efficient air conditioning–a review of technologies and strategies. Applied Energy, 104, 87-104.
[26]Lazos, D., Sproul, A. B., & Kay, M. (2014). Optimisation of energy management in commercial buildings with weather forecasting inputs: A review. Renewable and Sustainable Energy Reviews, 39, 587-603.
[27]Kutner, M. H., Nachtsheim, C., & Neter, J. (2004). Applied linear regression models. McGraw-Hill/Irwin.
[28]https://onlinecourses.science.psu.edu/stat501/node/352
[29]Chou, J. S., & Ngo, N. T. (2016). Time series analytics using sliding window metaheuristic optimization-based machine learning system for identifying building energy consumption patterns. Applied Energy, 177, 751-770.
[30]Kavousi-Fard, A., Samet, H., & Marzbani, F. (2014). A new hybrid modified firefly algorithm and support vector regression model for accurate short term load forecasting. Expert systems with applications, 41(13), 6047-6056.
[31]LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
[32]Olah, C. (2015). Understanding LSTM Networks. 2015. URL http://colah. github. io/posts/2015-08-Understanding-LSTMs/img/LSTM3-chain. png.
[33]Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems.
[34]Mnih, V., Heess, N., & Graves, A. (2014). Recurrent models of visual attention. In Advances in neural information processing systems (pp. 2204-2212).