隨著科技的進步，能源消耗的速度也越發快速，能源成本也日益上升，然而，日常生活的大規模用電加上環保意識逐漸抬頭，節省能源降低碳排放，已經是各個國家重要政策之一了。傳統的中央化電力系統面臨許多挑戰，包含能源供應不穩定、能源效益不足，智慧電網的出現大大解決了這些問題。智慧電網不單單只是可以配電傳輸而以還可以達到讓用戶端可以即時監測與控制家中設備。本論文拿出了最近較為常出現在大眾目光中的三種演算法來進預測用電、預測碳排放及預測危險用電，這三種演算法分別為循環神經網路(Recurrent Neural Network, RNN)的變種長短期記憶(Long Short-Term Memory, LSTM)可以達到長短期的記憶，LSTM簡化版的門控循環單元(Gated Recurrent Unit, GRU)，還有LSTM的變種版雙向長短記憶網路（Bi-directional Long Short-Term Memory, Bi-LSTM），透過用這三種演算法去對英國公開用電數據庫進行訓練與預測，看哪種演算法較為準確。本論文還透過這三種演算法去做實際應用比較，來達到更貼近台灣用電生活，在實際應用部分，本論文透過Flask去作出淺顯易懂的介面，讓使用者可以簡單的看到家中用電的使用狀況，也可以透過本論文比較出的演算法來去預測本期電價與本期碳排放量。其中也有增設LINE的聊天室功能可以透過問答的方式去了解使用者家庭用電。

With the advancement of technology, the rate of energy consumption has been accelerating, leading to a continuous rise in energy costs. However, coupled with the growing environmental awareness and the widespread use of electricity in daily life, energy conservation and carbon emission reduction have become essential policies in various countries. Traditional centralized power systems face numerous challenges, including unstable energy supply and inadequate energy efficiency. The emergence of the smart grid has significantly addressed these issues.
The smart grid not only facilitates electricity distribution and transmission but also enables end-users to monitor and control home devices in real-time. This paper presents three commonly discussed algorithms in recent times: the variant of Recurrent Neural Network (RNN) known as Long Short-Term Memory (LSTM), which excels in capturing long and short-term patterns; the simplified version of LSTM called Gated Recurrent Unit (GRU); and the variant of LSTM called Bi-directional Long Short-Term Memory (Bi-LSTM). These algorithms are utilized to predict electricity consumption, carbon emissions, and potentially hazardous electricity usage.
By training and predicting using these algorithms on the publicly available electricity consumption database in the UK, this paper aims to determine which algorithm performs more accurately. Additionally, practical applications of these algorithms are explored to better suit the electricity consumption patterns in Taiwan. In the practical application aspect, the paper employs Flask to create a user-friendly interface, enabling users to easily monitor their home's electricity usage and make predictions on current electricity prices and carbon emissions based on the compared algorithms. The paper also incorporates a LINE chatroom feature, allowing users to engage in a question-and-answer format to better understand their household electricity usage.

摘要...i
Abstract...ii
誌謝...iii
目錄...iv
表目錄...vi
圖目錄...vii
第一章 緒論...1
1.1研究背景...1
1.2研究動機與目的...2
1.3論文架構...2
第二章 文獻回顧...3
2.1物聯網...3
2.2智慧電網...5
2.3碳排放...7
2.4深度學習...8
2.4.1門控循環單元(Gated Recurrent Unit, GRU)...9
2.4.2長短期記憶（Long Short Term Memory, LSTM）...11
2.4.3雙向長短期記憶(Bi-directional Long Short-Term Memory, Bi-LSTM)...13
第三章 系統規劃...15
3.1軟硬體設備介紹...15
3.1.1 Socket...15
3.1.2 phpMyAdmin...17
3.1.3 Flask...18
3.1.4 Raspberry Pi...18
3.1.5 ESP32...19
3.1.6交流電多功能感測模組...20
3.1.7繼電器...21
3.1.8實驗用電設備介紹...21
3.2系統規劃...22
3.2.1系統流程...22
3.3英國公開用電資料模型建立與預測...23
3.3.1用電紀錄不安全狀態...23
3.3.2英國公開用電資料庫...23
3.3.3模型建立與預測...24
3.3.3.1 GRU模型...25
3.3.3.2 LSTM模型...26
3.3.3.3 Bi-LSTM...27
3.4智慧電網實際應用架構...28
3.4.1實驗環境與實驗架構...28
第四章 實驗與結果...30
4.1模擬不安全用電偵測實驗...30
4.2模型評估...35
4.2.1評估方式介紹...35
4.2.2 GRU模型評估...36
4.2.3 LSTM模型評估...37
4.2.4 Bi-LSTM...38
4.2.5各模型結果比較...39
4.3實際應用...39
第五章 結論與未來研究...43
參考文獻...44
Extended Abstract...47

[1] A. Singhal and R. Saxena, "Software models for smart grid," in 2012 First International Workshop on Software Engineering Challenges for the Smart Grid (SE-SmartGrids), 2012: IEEE, pp. 42-45.
[2] Q. Sun, J. Wu, Y. Zhang, N. Jenkins, and J. Ekanayake, "Comparison of the development of Smart Grids in China and the United Kingdom," in 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe), 2010: IEEE, pp. 1-6.
[3] J. Holler, V. Tsiatsis, C. Mulligan, S. Karnouskos, S. Avesand, and D. Boyle, "From machine-to-machine to the Internet of Things: introduction to a new age of," intelligence, 2014.
[4] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash, "Internet of things: A survey on enabling technologies, protocols, and applications," IEEE communications surveys & tutorials, vol. 17, no. 4, pp. 2347-2376, 2015.
[5] Z. Yang, Y. Yue, Y. Yang, Y. Peng, X. Wang, and W. Liu, "Study and application on the architecture and key technologies for IOT," in 2011 International Conference on Multimedia Technology, 2011: IEEE, pp. 747-751.
[6] D. o. Honer. "物聯網架構概念 - 伊伊威爾斯 - Medium." Dr. of Honer. https://medium.com/knowledge-letter/%E7%89%A9%E8%81%AF%E7%B6%B2%E6%9E%B6%E6%A7%8B%E6%A6%82%E5%BF%B5-332c4818c95 (accessed May 23, 2023).
[7] 賴振昌, "物聯網智慧監控系統," 碩士, 資訊管理系, 朝陽科技大學, 台中市, 2018. [Online]. Available: https://hdl.handle.net/11296/6b282q
[8] X. Fang, S. Misra, G. Xue, and D. Yang, "Smart grid—The new and improved power grid: A survey," IEEE communications surveys & tutorials, vol. 14, no. 4, pp. 944-980, 2011.
[9] H. Farhangi, "The path of the smart grid," IEEE power and energy magazine, vol. 8, no. 1, pp. 18-28, 2009.
[10] F. Rahimi and A. Ipakchi, "Demand response as a market resource under the smart grid paradigm," IEEE Transactions on smart grid, vol. 1, no. 1, pp. 82-88, 2010.
[11] 行政院環境保護署. "行政院環境保護署主管法規共用系統-法規內容-氣候變遷因應法." 行政院環境保護署. https://oaout.epa.gov.tw/law/LawContent.aspx?id=GL005511 (accessed May 23, 2023).
[12] 連育輝, "從企業成長動態與總體經濟發展觀點進行企業碳排放時間序列分析," 碩士, 運籌管理學系, 國防大學, 桃園縣, 2019. [Online]. Available: https://hdl.handle.net/11296/7e7sv4
[13] 鄭曜東, "營建業碳排放估算與管控系統開發," 碩士, 土木工程學系碩士班, 淡江大學, 新北市, 2022. [Online]. Available: https://hdl.handle.net/11296/qtftq9
[14] M. o. E. A. Bureau of Energy, R.O.C. "110年度電力排碳係數 - 便民服務 - 經濟部能源局(Bureau of Energy, Ministry of Economic Affairs, R.O.C.)全球資訊網." Bureau of Energy, Ministry of Economic Affairs, R.O.C. https://www.moeaboe.gov.tw/ecw/populace/content/ContentDesc.aspx?menu_id=20850 (accessed May 23, 2023).
[15] M. o. E. A. Bureau of Energy, R.O.C. "111年度電力排碳係數 - 便民服務 - 經濟部能源局(Bureau of Energy, Ministry of Economic Affairs, R.O.C.)全球資訊網." Bureau of Energy, Ministry of Economic Affairs, R.O.C. https://www.moeaboe.gov.tw/ecw/populace/content/ContentDesc.aspx?menu_id=23142 (accessed May 23, 2023).
[16] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, pp. 436-444, 2015.
[17] 李文富, "深度學習應用於動作辨識中的key pose分類," 碩士, 資訊工程研究所, 國立中正大學, 嘉義縣, 2015. [Online]. Available: https://hdl.handle.net/11296/rne52v
[18] 張育瑞, "基於深度學習之AAC壓縮域翻唱歌快速檢索," 碩士, 通訊工程學系, 國立中央大學, 桃園縣, 2015. [Online]. Available: https://hdl.handle.net/11296/834uxs
[19] K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv preprint arXiv:1406.1078, 2014.
[20] H. M. Lynn, S. B. Pan, and P. Kim, "A deep bidirectional GRU network model for biometric electrocardiogram classification based on recurrent neural networks," IEEE Access, vol. 7, pp. 145395-145405, 2019.
[21] 璞. 謝, "基於RNN 模型的GRU和LSTM方法結合AES 加密與智慧合約進行來源身份驗證," 碩士, 資訊工程學系, 國立清華大學, 新竹市, 2022. [Online]. Available: https://hdl.handle.net/11296/h9wkp7
[22] M. Ravanelli, P. Brakel, M. Omologo, and Y. Bengio, "Light gated recurrent units for speech recognition," IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no. 2, pp. 92-102, 2018.
[23] 林家瑋, "深度學習 RNN、LSTM 與 GRU 預測模型之比較：以台灣與美國期貨市場為例," 碩士, 數學系, 東吳大學, 台北市, 2022. [Online]. Available: https://hdl.handle.net/11296/452dzp
[24] N. Gunji, "Research and Analysis of GRU and LSTM through Attention Mechanism," 碩士, 前瞻製造系統碩士學位學程, 國立中正大學, 嘉義縣, 2022. [Online]. Available: https://hdl.handle.net/11296/s56q67
[25] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[26] R. Fu, Z. Zhang, and L. Li, "Using LSTM and GRU neural network methods for traffic flow prediction," in 2016 31st Youth academic annual conference of Chinese association of automation (YAC), 2016: IEEE, pp. 324-328.
[27] C. Olah. "Understanding LSTM Networks -- colah's blog." Christopher Olah. http://colah.github.io/posts/2015-08-Understanding-LSTMs/ (accessed May 23, 2023).
[28] N. Kalchbrenner, I. Danihelka, and A. Graves, "Grid long short-term memory," arXiv preprint arXiv:1507.01526, 2015.
[29] J. Xiang, Z. Qiu, Q. Hao, and H. Cao, "Multi-time scale wind speed prediction based on WT-bi-LSTM," in MATEC Web of Conferences, 2020, vol. 309: EDP Sciences, p. 05011.
[30] 翻轉工作室：粘添壽. "Socket 簡介." 翻轉工作室：粘添壽. https://www.tsnien.idv.tw/Internet_WebBook/chap8/8-1%20Socket%20%E7%B0%A1%E4%BB%8B.html (accessed May 23, 2023).