有別於傳統侵入式的負載量測方法，非侵入式負載監測系統不必於各個負載點加裝任何的感測器，僅需要於電力供應入口端加裝電壓與電流感測器並與監測系統連接，經由系統計算分析與辨識處理後，即可得知各個負載的使用情形。
本研究所建立的非侵入式負載監測系統，使用倒傳遞類神經網路於負載辨識器，負載電力特徵資料只取用有效功率及無效功率。然而倒傳遞類神經網路在搜尋權重與偏移量的過程中，常有可能陷入區域極小值，以致於網路訓練成效不彰而造成辨識率極差之情形。所以本研究結合特徵萃取的最佳化演算法，以獲得更佳的負載辨識精確度。
本研究嘗試使用以三層倒傳遞類神經網路(Back-Propagation Neural Network, BPNN)架構並結合基因演算法(Genetic Algorithm, GA)或粒子群優法(Particle Swarm Optimization, PSO)來搜尋權重及偏移量。透過三個案例的辨識結果，可知基因演算法或粒子群優法的全域搜索能力確實能夠有效地找到較佳的權重及偏移量給倒傳遞類神經網路，藉以提升倒傳遞類神經網路之辨識率，使得該方法能使用於非侵入式負載監測系統的負載辨識。
本論文之主要貢獻在於建構人機介面：提供即時波形顯示、諧波電流分析、負載辨識、用電相關資訊紀錄表格與資料庫更新，讓使用者能夠清楚了解所使用負載的相關電力資訊。

An intrusive load monitoring system needs to install sensors for each load. On the other hand, a non-intrusive load monitoring system only needs to install a sensor at the electric power entrance point. By analyzing the voltage and current waveforms from the electric power entrance point, the power usage of each load can be obtained and analyzed.
This research applies the back propagation neural network (BPNN) to the implementation of a non-intrusive load monitoring system to identify loads, using real power and reactive power to be the power signature. However, the solution by BPNN may fall into a local minimum easily and result in poor recognition result because bad network training. Therefore, we combine the optimization algorithm with feature extraction to obtain better load recognition accuracy.
This thesis applies genetic algorithm (GA) and particle swarm optimization (PSO) to search weights and bias for BPNN. According to the recognition accuracy of the three cases tested, it has been indicated that GA and PSO have a superior searching ability to find weights and bias to improve the recognition accuracy of BPNN.
This research establishes a monitoring system which involves some useful power information for users：real time waveform display, analysis of harmonic currents, recognition of loads, power demand information table and updating database.

[1] S. Drenker, A. Kader, “Nonintrusive Monitoring of Electric Loads,” IEEE Computer Applications in Power, Vol. 12, pp. 47-51, 1999.
[2] 錢柏青，使用基因演算法於非侵入式負載監測系統之特徵萃取，碩士論文，國立台灣科技大學電機工程學系，台北，2011。
[3] A. Cole and A. Albicki, “Nonintrusive Identification of Electrical Loads in a Three-Phase Environment Based on Harmonic Content,” IEEE Conference on Instrumentation and Measurement Technology, Baltimore, USA, Vol. 1, pp. 24-29, 2000.
[4] K.D. Lee, S.B. Leeb, L.K. Norford, P.R. Armstrong, J. Holloway, and S.R. Shaw, “Estimation of Variable-Speed-Drive Power Consumption from Harmonic Content,” IEEE Transactions on Energy Conversion, Vol.20, No.3, pp. 566- 574, Sept. 2005.
[5] 蕭玉庭，以基因演算法為基礎之非侵入式負載監測系統設計，碩士論文，中原大學電機工程學系，桃園，2001。
[6] H. H. Chang, H. T. Yang and C. L. Lin, “Load Identification in Neural Networks for a Non-Intrusive Monitoring of Industrial Electrical Loads,” Computer Supported Cooperative Work in Design IV, Vol. 5236, pp. 664-674, 2008.
[7] H. H. Chang, C. L. Lin, L.S. Wang, “Application of Artificial Intelligence and Non-intrusive Energy-managing System to Economic Dispatch Strategy for Cogeneration System and Utility, “CSCWD 2009 Conference on Computer Supported Cooperative Work in Design, Santiago, Chile, pp.740-745, 2009.
[8] H. H. Chang, C. L. Lin, H. T. Yang, “Load Recognition for Different Loads with the Same Real Power and Reactive Power in a Non-intrusive Load-monitoring System, “CSCWD 2008 Conference on Computer Supported Cooperative Work in Design, Xi’an, China, pp.1122-1127, 2008.
[9] J. G. Roos, I. E. Lane, E. C. Botha, and G. P. Hancke, “Using Neural Networks for Non-intrusive Monitoring of Industrial Electrical Loads,” Instrumentation and Measurement Technology Conference, Hamamatsu, Tunisa, Vol. 3, pp. 1115-1118, May 1994.
[10] N. Gomez Bias, L. F. Mingo and J. Castellanos, “Network of Evolutionary Processors with a Self-organizing Learning,” IEEE International Conference on Computer Systems and Applications, Doha, Qatar, pp. 917-918, 2008.
[11] P. D. Heerman and N. Khazenie, “Classification of Multispectral Remote Sensing Data Using a Back Propagation Neural Network,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 30, No. 1, pp. 81–88, 1992.
[12] A.G. Jongepier and L. van der Sluis, “Adaptive Distance Protection of Double-circuit Lines Using Artificial Neural Networks,” IEEE Transactions on Power Delivery, Vol. 12, No. 1, pp. 97-105, Jan. 1997.
[13] 李哲毅，以特徵擷取及基因規劃為基礎之非侵入式負載監測系統設計，碩士論文，中原大學電機工程學系，桃園，2008。
[14] 林郁修，基於一個新穎的特徵萃取方式及人工智慧技術之自適應非侵入式負載監控系統研發，碩士論文，國立台北科技大學自動化科技研究所，台北，2010。
[15] S. B. Leeb, S. R. Shaw and J. L. Kirtley, Jr. “Transient Event Detection in Spectral Envelope Estimates for Nonintrusive Load Monitoring,” IEEE Transactions on Power Delivery, Vol. 10, No. 3, pp. 1200-1210, 1995.
[16] Tao Zhu, S.R. Shaw and S.B. Leeb, “Transient Recognition Control for Hybrid Fuel Cell Systems,” IEEE Transactions on Energy Conversion, Vol.21, No.1, pp. 195- 201, 2006.
[17] R. Cox, S.B. Leeb, S.R. Shaw and L.K. Norford, “Transient Event Detection for Nonintrusive Load Monitoring and Demand Side Management Using Voltage Distortion,” Applied Power Electronics Conference and Exposition, pp. 19-23, Manama, Bahrain, 2006.
[18] 蘇易清，以小波轉換為主之非侵入式負載監測，碩士論文，國立台灣科技大學電機工程學系，台北，2012。
[19] 章學賢，非侵入式負載監測方法及其應用，博士論文，中原大學電機工程學系，桃園，2009。
[20] 葉怡成，類神經網路應用與實作，儒林出版社，1999。
[21] 羅華強，類神經網路-Matlab的應用，高立圖書有限公司，2008。
[22] 溫盛夫，A M H S派貨邏輯利用類神經網路結合遺傳演算法實現效能動態最佳化研究，碩士論文，國立中央大學機械工程學系，桃園，2010。
[23] 莊文仲，多層感知等化器-使用進化演算法，碩士論文，國立中央大學電機工程學系，2001。
[24] D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, MA, 1989.
[25] M. A. Abido, “Multiple Objective Evolutionary Algorithms for Electric Power Dispatch Problem,” IEEE Transactions on Evolutionary Computation, Vol. 10, No. 3, pp.315-329, 2006.
[26] S. Y. Woon, O. M. Querin and G. P. Steven, “Structural Application of a Shape Optimization Method Based on a Genetic Algorithm,” Structural and Multidisciplinary Optimization, Vol. 22, pp. 57-64, 2001.
[27] R. J. Allard, D. H. Werner and P. L. Werner, “Radiation Pattern Synthesis for Arrays of Conformal Antennas Mounted on Arbitrarily-shaped Three-dimensional Platforms Using Genetic Algorithms,” IEEE Transactions on Antennas and Propagation, Vol. 51, No. 5, pp. 1054-1062, 2003.
[28] C. J. Hsu, C. Y. Huang and T. Y. Chen,”A Modified Genetic Algorithm for Parameter Estimation of Software Reliability Growth Models,” IEEE International Conference on Software Reliability Engineering, Washington, USA, pp. 281-282, 2008.
[29] N. S. Chaudhari, A. Purohit and A. Tiwari, “A Multiclass Classifier Using Genetic Programming,” IEEE International Conference on Control, Automation, Robotics and Vision, Hanoi, Vietnam, pp. 1884-1887, 2008.
[30] P. C. Chang, J. C. Hsieh and C. H. Hsiao, “Application of Genetic Algorithm to The Unrelated Parallel Machine Problem Scheduling,” Journal of the Chinese Institute of Industrial Engineering, Vol. 19, No. 2,pp. 79-95, 2002.
[31] Qiuwen Zhang and Cheng Wang, “Using Genetic Algorithm to Optimize Artificial Neural Network: A Case Study on Earthquake Prediction,” Genetic and Evolutionary Computing on WGEC 2008 Second International Conference, Hubei, China, pp. 128-131, 2008.
[32] Lian Zhang, Wen-juan Li, Fang-fang Zhang and Wei Lai, “Application Research on Genetic Neural Network for Water Quality Comprehensive Evaluation,” Computer Science and Information Technology (ICCSIT) 2010 3rd IEEE International Conference, Chengdu, China, pp. 636-640, 2010.
[33] Yuegang Luo, Songhe Zhang, Xiaodong Liu and Bangchun Wen, “Integrated Genetic Neural Networks and its Application in Fault Diagnosis,” Natural Computation ICNC 2008 Fourth International Conference, Dalian, China, pp. 231-235, 2008.
[34] M. Gen and R. Cheng, Genetic Algorithms & Engineering Design, John Wiley &Sons International Inc., 1997.
[35] 林昇甫、徐永吉, 遺傳演算法及其應用, 五南出版社, 2009。
[36] J. Kennedy, and R. Eberhart, “A New Optimizer Using Particle Swarm Theory,” Proceedings of Sixth International Symposium Machine and Human Science, Nagoya, Japan, pp. 39-43, 1995.
[37] Jia Rong and Huang Ge, “Hydroelectric Generating Unit Vibration Fault Diagnosis via BP Neural Network Based on Particle Swarm Optimization,” Sustainable Power Generation and Supply SUPERGEN 2009 International Conference, Nanjing, China, pp. 1-4, 2009.
[38] Qiao Yan, ChangBin Wu, Songzhao LV and MingLiang Bi, “Displacement Back-analysis of Rock-fill Dam Based on Particle Swarm Optimization and Genetic Neural Network Algorithm,” Computer Application and System Modeling (ICCASM) 2010 International Conference, Taiyuan, China, Vol. 5,pp.377-380, 2010.
[39] Hua Wang, Bingxiang Liu and Xiang Cheng, “Probabilistic Neural Network Model Based on Wavelet and Particle Swarm Optimization,” Biomedical Engineering and Informatics (BMEI) 2011 4th International Conference, Shanghai, China, pp.2225-2227, 2011.
[40] 蔡承昌，基於粒子群優演算法之適性化數位課程組裝流程，碩士論文，國立成功大學資訊工程學系，台南，2008。
[41] 蘇昱豪，具隨機粒子與微調機制式粒子權最佳化於多級值函數問題之研究，碩士論文，國立台灣科技大學機械工程學系，台北，2006。
[42] X. H. Wang, J. J. Li and J. M. Xiao, “Particle Swarm Optimization Algorithm Based on Same Side Keeping and Elitism,” IEEE International Conference on Control and Decision, Yantai, Shandong, pp. 3078-3082, 2008.
[43] C. F. Juang, “A Hybrid of Genetic Algorithm and Particle Swarm Optimization for Recurrent Network Design,” IEEE Transactions on Syst., Man and Cyber, Part B, Vol. 34, No. 2, pp. 997-1006, 2004.
[44] Cunningham, David R. and John A. Stuller, Circuit Analysis, John Wiley & Sons International Inc, 1995.
[45] Kamen, Edward W. and Bonnie S. Heck, Signals and Systems, Prentice-Hall International Inc., 2000.