非侵入式負載監測系統(Non-intrusive Load Monitoring, NILM)係指不須加裝任何的感測器到想監測的各個負載上，也不需要與主系統做內部接線，只需將監測裝置與用戶電表做結合後安裝於電力供給入口處，藉著量測電力供給入口處的電壓與電流波形資料並加以分析，就能知道各個負載上線或下線的狀況與用電情形。
本文提出基於非侵入式負載監測系統之負載老化偵測方法，此方法採用Hellinger距離(Hellinger Distance)理論來搜尋最佳負載辨識特徵，該最佳特徵可用於辨識負載之老化情形，且使用倒傳遞類神經網路(Back-Propagation Artificial Neural Network, BP-ANN)作為辨識負載老化的工具。所提方法可針對負載的老化情形進行分析及辨識，進而提供負載能源的資訊，並透過案例的模擬，可得知該Hellinger距離理論所搜尋到的最佳負載辨識特徵可以利於提升負載老化的辨識率。
研究試驗結果顯示基於Hellinger距離理論所搜尋之最佳特徵可適用於負載老化的偵測，且透過數據的分析，以達到減少能源虛耗與即時提醒之用途。

A non-intrusive load monitoring system (NILM) only needs to install a sensor combined with the meter at the electric power service entrance. By analyzing the voltage and current waveforms from the electric power service entrance, the device status and power utilization of loads can be obtained.
This study proposes a Hellinger distance algorithm for extracting the power features of load aging based on a non-intrusive load monitoring system (NILM). In this paper, Hellinger distance algorithm is used to extract optimal features for load identification and a back-propagation artificial neural network (BP-ANN) is employed for aging load detection. The proposed methods are used to analyze and identify the aging of loads in a residential building. The result of aging load detection can provide load demand information for each load. The recognition result shows the recognition accuracy can be improved by using the proposed method. In order to reduce the consumption of energy and send a real-time alarm of load aging to the user, the system provides information of energy usage from data analysis.

[1] G. A. Bruce, “Reliability Analysis of Electric Utility SCADA Systems,” IEEE Transactions on Power Systems, Vol. 13, No. 3, pp. 844-849, Aug. 1998.
[2] 蘇易清，「以小波轉換為主之非侵入式負載監測」，碩士論文，國立臺灣科技大學電機工程學系，台北，2012年。
[3] S. R. Shaw, S. B. Leeb, L. K. Norford and R. W. Cox, “Nonintrusive Load Monitoring and Diagnostics in Power Systems,” IEEE Transactions on Instrumentation and Measurement, Vol. 57, No. 7, pp. 1445-1454, July 2008.
[4] C. Laughman, D. Lee, R. Cox, S. Shaw, S. Leeb, L. Norford, and
P. Armstrong, “High Performance Commercial Building Systems: Advanced Nonintrusive Monitoring of Electric Loads,” IEEE Power and Energy Magazine, Vol. 99, No. 2, pp. 56-63, March/April 2003.
[5] V. P. Borin, C. H. Barriquello and R. A. Pinto, “An Improved Technique for Load Identification in Residential Buildings,” International Conference on New Concepts in Smart Cities: Fostering Public and Private Alliances (SmartMILE), Gijon, Spain, pp. 1-5, Dec. 2013.
[6] P. A. Chou, C. C. Chuang and R. I. Chang, “Automatic Appliance Classification for Non-intrusive Load Monitoring,” IEEE International Conference on Power System Technology (POWERCON), Auckland, New Zealand, pp. 1-6, 30 Oct. 2012-2 Nov. 2012.
[7] W. Zhenyu and Z. Guilin, "The Application of Mean-shift Cluster in Residential Appliance Identification," 30th Chinese Control Conference (CCC), Yantai, China, pp. 3111-3114, 22-24 July 2011.
[8] Z. Wang and G. Zheng, "Residential Appliances Identification and Monitoring by a Nonintrusive Method," IEEE Transactions on Smart Grid, Vol. 3, No. 1, pp. 80-92, March 2012.
[9] 林溶徐，「以粒子群優法及類神經網路建置非侵入式負載監測系統」，碩士論文，國立臺灣科技大學電機工程系，台北，2012年。
[10] K. L. Chen, H. H. Chang and N. Chen, "A New Transient Feature Extraction Method of Power Signatures for Nonintrusive Load Monitoring Systems," IEEE International Workshop on Applied Measurements for Power Systems (AMPS), Aachen, Germany, pp. 79-84, 25-27 Sept. 2013.
[11] C. Laughman, K. Lee, R. Cox, S. Shaw, S. Leeb, L. Norford, and P. Armstrong, "Power Signature Analysis," IEEE Power and Energy Magazine, Vol. 1, No. 2, pp. 56-63, Mar. – Apr. 2003.
[12] H. H. Chang, “Non-Intrusive Demand Monitoring and Load Identification for Energy Management Systems Based on Transient Feature Analyses,” Energies, Vol. 5, No. 11, pp. 4569-4589, 14 November 2012.
[13] Y. F. Wong, Y. A. Sekercioglu, T. Drummond and V. S. Wong, "Recent Approaches to Non-intrusive Load Monitoring Techniques in Residential Settings," IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG), Singapore, pp. 73-79, 16-19 April 2013.
[14] S. R. Shaw, S. B. Leeb, L. K. Norford and R. W. Cox, "Nonintrusive Load Monitoring and Diagnostics in Power Systems," IEEE Transactions on Instrumentation and Measurement, Vol. 57, No. 7, pp. 1445-1454, July 2008.
[15] F. Sultanem, "Using Appliance Signatures for Monitoring Residential Loads at Meter Panel Level," IEEE Transactions on Power Delivery, Vol. 6, No. 4, pp. 1380-1385, Oct. 1991.
[16] Z. Wang and G. Zheng, "New Method for Non-intrusive Data Extraction and Classification of Residential Appliances," Chinese Control and Decision Conference (CCDC), Mianyang, China, pp. 2196-2201, 23-25 May 2011.
[17] A. S. Bouhouras, A. N. Milioudis, G. T. Andreou and D. P. Labridis, "Load Signatures Improvement through the Determination of a Spectral Distribution Coefficient for Load Identification," 9th International Conference on European Energy Market (EEM), Florence, Italy, pp. 1-6, 10-12 May 2012.
[18] V. S. Wong, Y. F. Wong, T. Drummond and Y. A. Sekercioglu, "A Fast Multiple Appliance Detection Algorithm for Non-intrusive Load Monitoring," IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG), Singapore, pp. 80-86, 16-19 April 2013.
[19] Y. H. Lin, M. S. Tsai and C. S. Chen, "Applications of Fuzzy Classification with Fuzzy C-means Clustering and Optimization Strategies for Load Identification in NILM Systems," IEEE International Conference on Fuzzy Systems (FUZZ), Taipei, Taiwan, pp. 859-866, 27-30 June 2011.
[20] Y. H. Lin and M. S. Tsai, "A Novel Feature Extraction Method for the Development of Nonintrusive Load Monitoring System Based on BP-ANN," International Symposium on Computer Communication Control and Automation (3CA), Tainan, Taiwan, Vol.2, pp. 215-218, 5-7 May 2010.
[21] L. Jiang, S. Luo and J. Li, "An Approach of Household Power Appliance Monitoring Based on Machine Learning," Fifth International Conference on Intelligent Computation Technology and Automation (ICICTA), Zhangjiajie, Hunan, China, pp. 577-580, 12-14 Jan. 2012.
[22] Q. Guo and M. Zhang, "A Novel Approach for Fault Diagnosis of Steam Turbine Based on Neural Network and Genetic Algorithm," IEEE International Joint Conference on Neural Networks (IJCNN) (IEEE World Congress on Computational Intelligence), Hong Kong, pp. 25-29, 1-8 June 2008.
[23] F. Aminian, M. Aminian and H. W. Collins, "Analog Fault Diagnosis of Actual Circuits Using Neural Networks," IEEE Transactions on Instrumentation and Measurement, Vol. 51, No.3, pp. 544-550, Jun 2002.
[24] W. J. Tian, Y. Tian, L. Ai and J. C. Liu, "A New Method for Dynamic Fault Diagnosis of Electric Appliance," International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, Zhejiang, China, Vol.2, pp. 413-418, 26-27 Aug. 2009.
[25] A. Rahul, S. K. Prashanth, B. Suresh kumar and G. Arun, “Detection of Intruders and Flooding in Voip Using IDS, Jacobson Fast And Hellinger Distance Algorithms,” International Organization of Scientific Research Journal of Computer Engineering(IOSRJCE), Vol. 2, pp. 30-36, July-Aug. 2012.
[26] C. Hecht, P. Reichl, A. Berger, O. Jung and I. Gojmerac, "Intrusion Detection in IMS: Experiences with a Hellinger Distance-Based Flooding Detector," First International Conference on Evolving Internet, INTERNET, Cannes, France, pp. 65-70, 23-29 Aug. 2009.
[27] 陳秀瑜，「用Hellinger距離估計基因序列間的非相似性」，碩士論文，國立成功大學統計學研究所，台南，2006年。
[28] G. Ditzler, and R. Polikar, "Hellinger Distance Based Drift Detection for Non-stationary Environments," IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments (CIDUE), Paris, France, pp. 41-48, 11-15 April 2011.
[29] Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, "Image Quality Assessment: From Error Visibility to Structural Similarity, " IEEE Transactions on Image Processing, Vol. 13, No. 4, pp. 600, 612, April, 2004.
[30] 羅華強，類神經網路—MATLAB的應用，高立圖書有限公司，2008年。
[31] 王奕鈞，「神經網路應用於地籍坐標轉換之研究」，碩士論文，國立政治大學地政研究所，台北，2005年。
[32] 章學賢，非侵入式負載監測方法及其應用，博士論文，中原大學電機工程研究所，桃園，2009年。
[33] 家用和類似用途電器產品的安全-第1部：通則，中華民國國家標準 CNS 3765，2005年九月。
[34] 內政部消防署，102年全國火災統計分析。
[35] 余大波，「家用電器火災原因和調查方法的研究」，碩士論文，重慶大學環境工程研究所，重慶，2005年。