請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18132
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳希立(Sih-Li Chen) | |
dc.contributor.author | Wei-Long Chen | en |
dc.contributor.author | 陳韋龍 | zh_TW |
dc.date.accessioned | 2021-06-08T00:52:11Z | - |
dc.date.copyright | 2020-08-21 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-13 | |
dc.identifier.citation | 住宅用戶用電情形分析,台灣電力公司,2020 Luo, Y., Mesgarani, N. (2019). Conv-TasNet: Surpassing Ideal Time-Frequency gnitude Masking for Speech Separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(8), 1256–1266. https://doi.org/10.1109/TASLP.2019.2915167 Kolter, J. Z., Johnson, M. J. (n.d.). REDD: A Public Data Set for energy Disaggregation Research. 6. 台灣電力公司107年統計年報,台灣電力公司,2019 Hart, G. W. (1992). Nonintrusive appliance load monitoring. Proceedings of the IEEE,80(12), 1870–1891. https://doi.org/10.1109/5.1920696 Kee, F. K.-K., Lim, Y. S., Wong, J., Chua, K. H. (2019). Non-Intrusive Load Monitoring (NILM) – A Recent Review with Cloud Computing. 2019 IEEE International Conference on Smart Instrumentation, Measurement and Application (ICSIMA), 1–6.https://doi.org/10.1109/ICSIMA47653.2019.9057316 Leeb, S. B., Shaw, S. R., Kirtley, J. L. (1995). Transient event detection in spectral envelope estimates for nonintrusive load monitoring. IEEE Transactions on Power Delivery, 10(3), 1200–1210. https://doi.org/10.1109/61.400897 Kelly, J., Knottenbelt, W. (2015b). The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data,2(1), 150007. https://doi.org/10.1038/sdata.2015.7 Anderson, K., Ocneanu, A., Carlson, D. R., Rowe, A., Bergés, M. (2012). BLUED: A Fully Labeled Public Dataset for Event-Based Non-Intrusive Load Monitoring Research. /paper/BLUED-%3A-A-Fully-Labeled-Public-Dataset-for-LoadAnderson-Ocneanu/ed1b8fc3074ec5d7bb7cf83e233d3b130637706f Ghahramani, Z., Jordan, M. I. (1996). Factorial Hidden Markov Models.: Defense Technical Information Center. https://doi.org/10.21236/ADA307097 Barsim, K. S. (n.d.). An Approach for Unsupervised Non-Intrusive Load Monitoring of Residential Appliances. 5.Commenges, D. (2015). Information Theory and Statistics: An overview.ArXiv:1511.00860 [Math, Stat]. http://arxiv.org/abs/1511.00860 He, K., Stankovic, L., Liao, J., Stankovic, V. (2018). Non-Intrusive Load Disaggregation Using Graph Signal Processing. IEEE Transactions on Smart Grid, 9(3), 1739–1747. https://doi.org/10.1109/TSG.2016.2598872 Linge, N., Wu, Z., Liu, X., Chen, F., Liu, Q., Chen, F. (2018). Home appliances classification based on multi-feature using ELM. International Journal of Sensor Networks, 28, 34. https://doi.org/10.1504/IJSNET.2018.10015979 Roos, J. G., Lane, I. E., Botha, E. C., Hancke, G. P. (1994). Using neural networks for non-intrusive monitoring of industrial electrical loads. Conference Proceedings. 10thAnniversary. IMTC/94. Advanced Technologies in I M. 1994 IEEE Instrumentationand Measurement Technolgy Conference (Cat. No.94CH3424-9), 11151118 vol.3. https://doi.org/10.1109/IMTC.1994.351862 Kelly, J., Knottenbelt, W. (2015a). Neural NILM: Deep Neural Networks Applied to Energy Disaggregation. Proceedings of the 2nd ACM International Conference onEmbedded Systems for Energy-Efficient Built Environments – Build Sys ’15, 55–64.https://doi.org/10.1145/2821650.2821672 Hochreiter, S., Schmidhuber, J. (1997). Long Short-term Memory. Neural Computation, 9, 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 [17] Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. Proceedings of the 25thInternational Conference on Machine Learning - ICML ’08, 1096–1103.https://doi.org/10.1145/1390156.1390294 Sirojan, T., Phung, B. T., Ambikairajah, E. (2018). Deep Neural Network Based Energy Disaggregation. 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE), 73–77. https://doi.org/10.1109/SEGE.2018.8499441 Kingma, D. P., Welling, M. (2014). Auto-Encoding Variational Bayes.ArXiv:1312.6114 [Cs, Stat]. http://arxiv.org/abs/1312.6114 Kullback, S., Leibler, R. A. (1951). On Information and Sufficiency. The Annals of Mathematical Statistics, 22(1), 79–86. JSTOR. Liang, J., Ren, Z., Wang, L., Tang, B., Liu, J., Liu, Y. (2019). Deep Neural Networking Sequence to Short Sequence Form for Non-intrusive Load Monitoring. 2019 IEEE 3rdConference on Energy Internet and Energy System Integration (EI2), 565–570.https://doi.org/10.1109/EI247390.2019.9062180 Hinton, G. E. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. https://doi.org/10.1126/science.1127647 Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, Luo, Y., Mesgarani, N. (2018). TasNet: Time-domain audio separation network for real-time, single-channel speech separation. ArXiv:1711.00541[Cs, Eess]. http://arxiv.org/abs/1711.00541 Kolbæk, M., Yu, D., Tan, Z.-H., Jensen, J. (2017). Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks. ArXiv:1703.06284 [Cs, Eess].http://arxiv.org/abs/1703.06284 智慧電網總體規劃方案,台灣電力公司,2020 智慧住宅高齡照護設計指引,內政部建築研究所,2019 Yasin, A., Khan, S. A. (2018). Unsupervised Event Detection and On-Off Pairing Approach Applied to NILM. 2018 International Conference on Frontiers of Information Technology (FIT), 123–128. https://doi.org/10.1109/FIT.2018.00029 Hagan, M. T., Demuth, H. B., Beale, M. (1995). Neural Network Design.Hart, G. W. (1992). Nonintrusive appliance load monitoring. Proceedings of the IEEE, 80(12),1870–1891. https://doi.org/10.1109/5.19206929 Oord, A. van den, Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., Kavukcuoglu, K. (2016). WaveNet: A Generative Model for Raw Audio.ArXiv:1609.03499 [Cs]. http://arxiv.org/abs/1609.03499 M., Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. ArXiv:1704.04861 [Cs]. http://arxiv.org/abs/1704.04861 Yang, G.-P., Wu, S.-L., Mao, Y.-W., Lee, H., Lee, L. (2019). Interrupted and cascaded permutation invariant training for speech separation. ArXiv:1910.12706 [Cs,Eess]. http://arxiv.org/abs/1910.12706 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18132 | - |
dc.description.abstract | 台灣為海島國家,能源仰賴進口,隨著用電需求增加,節約電力成為重要的課題。以往著重於工商業等高壓用戶,透過建立完善的監控系統,進行各種能源的掌握,協助電力改善及設備能效管控。台灣的低壓用戶佔全體用戶89%,因此電能議題上不可忽視。對低壓用戶而言,使用大量的監控設備進行能源管控,不僅增加成本同時負擔監控設備能耗,反而造成浪費。本研究為解決電力系統監控及設備管控問題,研究將單一電力訊號,分離成多種設備個別訊號之模型。 單一電力訊號分離已發展多年,隨著運算效能提升深度學習被廣泛運用於該領域。有鑑於語音分離領域,在時域領域能夠有所突破。本研究將語音分離模型 Conv-TasNet 轉換領域,透過 REDD 資料集測試模型轉換之參數及架構調整。研究 Conv-TasNet 應用於電力分離任務之可行性以及成效。 實驗結果顯示,以往使用SI-SNR作為目標函數,電力訊號領域時改用MSE函數以及在輸出層加上ReLU激活函數能夠提高模型成效。該模型於五種設備分離時,分離訊號於總電力訊號佔比,相對誤差小於10%。透過家庭一到三訓練模型,測試於家庭五之電冰箱及微波爐,分離訊號之MAE誤差約為24及5.6瓦特。 | zh_TW |
dc.description.abstract | Taiwan is an island country, energy using in Taiwan depends on imports. Through the increase in electricity demand, power saving has become an important task. Previously, it focused on high-voltage users such as industry and commerce. To build a complete monitoring system, it can control various energy sources to assist in power improvement and equipment energy efficiency control. But Taiwan’s low-voltage users account for 89% of all users, therefore the electrical connection cannot be ignored. For low voltage customers, the use of a large number of monitoring equipment for energy management and control causes waste while increase the cost and bear the consumption of monitoring equipment at the same time. In order to solve the problems of power system monitoring and equipment management control, this research build a model to separate the single power signal into multiple devices. Single power signal separation has been developed for many years, and deep learning has been widely used in this field with the improvement of computing performance. In view of the field of speech separation, a breakthrough can be made in the time domain. In this research using the speech separation model Conv-TasNet transform to the field. Through the REDD data set, testing model conversion parameters and structure adjustments used to study the feasibility and effectiveness of Conv-TasNet, applied to power separation tasks. According to the results, SI-SNR was used as the objective function in the past. The MSE function was used in the power signal field and the ReLU activation function was added to the output layer were the most effective of the model. Using this model to separate the five devices, the separation signal accounts for the proportion of the total power signal its relative error is less than 10%. Through the family one to three training model, tested in household five refrigerators and microwave ovens, the MAE error of the separated signal is about 24 and 5.6 watts. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T00:52:11Z (GMT). No. of bitstreams: 1 U0001-1308202014400800.pdf: 3160608 bytes, checksum: 07bd66e88fb06504496bbd42594b8d22 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 摘要 I Abstract II 目錄 IV 圖目錄 VI 表目錄 VIII 第1章 緒論 1 1.1 前言 1 1.2 文獻回顧 3 1.2.1 非侵入式負載監測之文獻回顧 3 1.2.2 深度學習文獻回顧 10 1.3 研究動機與目的 13 1.4 研究流程 14 第2章 研究原理與方法 15 2.1 電力訊號資料集簡介 15 2.2非侵入式負載監測系統架構 16 2.3深度學習運用 18 2.3.1深度學習簡介 18 2.3.2卷積神經網路及卷積層 20 2.3.3 Conv-TasNet 21 第3章 實驗設計與步驟 25 3.1 實驗設計 25 3.2 數據分析軟體 25 3.3 研究步驟 26 3.3.1 數據處理 26 3.3.2 結果驗證 26 3.3.3 Conv-TasNet 之實驗架構 27 第4章 結果與討論 28 4.1實驗一 28 4.2實驗二 36 4.3實驗三 44 第5章、結論與未來展望 58 5.1結論 58 5.2未來展望 59 參考文獻 60 | |
dc.language.iso | zh-TW | |
dc.title | Conv-TasNet運用於家庭電力訊號分解 | zh_TW |
dc.title | Conv-TasNet apply to energy disaggregation | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 李文興(Wen-Shing Lee),柯明村(Ming-Tsun Ke), 江沅晉(Yuan-Chin Chiang),陳志豪(Chih-Hao Chen) | |
dc.subject.keyword | 電力訊號分解,深度學習,卷積神經網路,即時訊號,節約能源, | zh_TW |
dc.subject.keyword | energy disaggregation,deep learning,Convolutional Neural Network,real-time,energy conservation, | en |
dc.relation.page | 63 | |
dc.identifier.doi | 10.6342/NTU202003253 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2020-08-14 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
顯示於系所單位: | 機械工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1308202014400800.pdf 目前未授權公開取用 | 3.09 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。