||Non-Intrusive Outlier Detection of Individual Residential Energy Consumption in Smart Grid Environment
||Department of Engineering Science
Dynamic Time Warping
在智慧電網的環境裡能夠透過資料傳輸及資料分析的技術，提升能源分配及能源使用的效率。近幾年有許多關於應用在智慧電網上的資料分析的研究，其中有關異常用電的偵測一直是重要的議題。本研究提出一種基於使用者的用電歷史數據的非侵入式異常偵測的方式。主要的目的在於透過歷史用電資料，偵測時間區間過高或過低的異常用電數據。研究方法首先挑選被期待相似度高的時間序列數據，再使用動態時間扭曲(Dynamic Time Warping)及K-近鄰演算法(k-nearest neighbors)將被選定的時間序列數據進行分群，挑選出最接近的時間序列數據群。最後偵測的用電數據與前述序列數據群以動態時間扭曲計算差距，進而識別是否有異常的數據。在本研究中以一獨立家庭的四年用電紀錄進行實驗及驗證，結果顯示本研究設計的方法可以達到相較相關研究較高的準確率(79.3%)。
In the smart grid environment, information and communication technology can improve energy distribution and reduce consumption. In recent years, a lot of researches have been proposed and applied in the smart grid environments. The outlier detection of energy consumption is one of the primary challenges. In this research, we proposed a non-intrusive outlier detection method which is based on the individual electricity consumption data. The major objective is to enable an energy management system to be used for detecting anomalies, both of abnormally high and low, energy use. We applied Dynamic Time Warping and k-nearest neighbors to group the patterns of energy consumption. The shortest distance calculated by Dynamic Time Warping to identify abnormal consumption in the same group. A dataset, based on an individual household with the smart meter environment which recorded the electricity usage in almost four years was adopted. The results demonstrated that the proposed method could be used to identify abnormal consumption with 79.3% accuracy. This result is better than related works.
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1 Background 1
1.2 Motivation 2
1.3 Organization of Thesis 3
Chapter 2 Related Works 5
2.1 Outlier Detection with Smart Meter 5
2.2 Processing of Time Series Data 6
2.2.1 Dynamic Time Warping 7
2.2.2 Fast Dynamic Time Warping 10
2.3 Clustering Techniques in Data Mining 11
2.3.1 Instance-Based Learning 11
2.3.2 K-Nearest Neighbors 11
Chapter 3 Proposed Method 13
3.1 Requirements 13
3.2 Method Overview 14
3.2.1 Data Extraction Phase 15
3.2.2 DTW-kNN Phase 17
3.2.3 Classification Phase 18
3.3 Effectiveness 18
Chapter 4 Experiments and Evaluation 19
4.1 Experiment Setup 19
4.2 Experimental Results 22
4.3 Evaluation 25
Chapter 5 Conclusions and Future Works 28
5.1 Conclusions 28
5.2 Future Works 29
 D. Mashima and A. A. Cárdenas, "Evaluating electricity theft detectors in smart grid networks," in Research in Attacks, Intrusions and Defenses, Berlin, Germany, Springer-Verlag, 2012, pp. 210–229.
 D. Alahakoon and X. Yu, "Smart Electricity Meter Data Intelligence for Future Energy Systems: A Survey," IEEE Transactions on Industrial Informatics, vol. 12, no. 1, pp. 425-436, Feb. 2016.
 H. Xu, H. Huang, R. S. Khalid and H. Yu, "Distributed machine learning based smart-grid energy management with occupant cognition," 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm), Sydney, NSW, Australia, 2016, pp. 491-496.
 V. Jakkula and D. Cook, "Outlier Detection in Smart Environment Structured Power Datasets," 2010 Sixth International Conference on Intelligent Environments, Kuala Lumpur, Malaysia, 2010, pp. 29-33.
 K. Grolinger, M. A. M. Capretz and L. Seewald, "Energy Consumption Prediction with Big Data: Balancing Prediction Accuracy and Computational Resources," 2016 IEEE International Congress on Big Data (BigData Congress), San Francisco, CA, U.S.A., 2016, pp. 157-164.
 X. Li, C. P. Bowers and T. Schnier, "Classification of Energy Consumption in Buildings With Outlier Detection," IEEE Transactions on Industrial Electronics, vol. 57, no. 11, pp. 3639-3644, 2010.
 M. Jain, A. Singh and V. Chandan, "Non-Intrusive Estimation and Prediction of Residential AC Energy Consumption," 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom), Sydney, NSW, Australia, 2016, pp. 1-9.
 U. Ali, C. Buccella and C. Cecati, "Households Electricity Consumption Analysis with Data Mining Techniques," IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, 2016, pp. 3966-3971.
 X. Liu, and P. S. Nielsen, "Regression-Based Online Anomaly Detection for Smart Grid Data," Department of Management Engineering, Technical University of Denmark, Kongens Lyngby, Denmark, 2016.
 R. Jiang, R. Lu, Y. Wang, J. Luo, C. Shen and X. S. Shen, "Energy-Theft Detection Issues for Advanced Metering Infrastructure in Smart Grid," Tsinghua Science and Technology, vol. 19, no. 2, pp. 105-120, April 2014.
 P. Jokar, N. Arianpoo and V. C. M. Leung, "Electricity Theft Detection in AMI Using Customers’ Consumption Patterns," IEEE Transactions on Smart Grid, vol. 7, no. 1, pp. 216-226, Jan. 2016.
 A. Jindal, A. Dua, K. Kaur, M. Singh, N. Kumar and S. Mishra, "Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid," IEEE Transactions on Industrial Informatics, vol. 12, no. 3, pp. 1005-1016, June 2016.
 J. D. Deng, "Online Outlier Detection of Energy Data Streams Using Incremental and Kernel PCA Algorithms," 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), Barcelona, Spain, 2016, pp. 390-397.
 S. S. S. R. Depuru, L. Wang and V. Devabhaktuni, "Support Vector Machine Based Data Classification for Detection of Electricity Theft," 2011 IEEE/PES Power Systems Conference and Exposition, Phoenix, AZ, U.S.A., 2011, pp. 1-8.
 T. Hartmann et al., "Suspicious Electric Consumption Detection Based on Multi-Profiling Using Live Machine Learning," 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm), Miami, FL, U.S.A., 2015, pp. 891-896.
 R. Batchu and N. M. Pindoriya "Residential Demand Response Algorithms: State-of-the-Art Key Issues and Challenges," International Conference on Wireless and Satellite Systems. Springer, Cham, 2015, pp. 18-32.
 D. J. Berndt, J. Clifford, "Using Dynamic Time Warping to Find Patterns in Time Series," Advances in Knowledge Discovery in Databases: Papers from the 1994 AAAI Workshop, pp. 359-370, July 1994.
 B. B. Ali, Y. Masmoudi and S. Dhouib, "Accurate and Fast Dynamic Time Warping Approximation Using Upper Bounds," 38th International Conference on Telecommunications and Signal Processing (TSP), Prague, Czech, 2015, pp. 1-6.
 S. Salvador and P. Chan, "FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space," Intelligent Data Analysis, vol. 11, pp. 561-580, 2007.
 M. Brent, Instance-Based Learning: Nearest Neighbor with Generalization, PhD Thesis, University of Waikato, Hamilton, New Zealand, 1995.
 D. R. Wilson and T. R. Martinez, "Reduction Techniques for Instance-Based Learning Algorithms," Machine Learning, vol. 38 no. 3, pp. 257-286, March 2000.
 G. Hebrail, "Individual Household Electric Power Consumption Data Set" [Online].Available: https://archive.ics.uci.edu/ml/datasets/individual+household+electric+power+consumption [Accessed: 20-July-2017]
 J. Eng, R. H. Morgan and J. Hopkins, "ROC Analysis" [Online].
 J. Nagi, K. S. Yap, S. K. Tiong, S. K. Ahmed and F. Nagi, "Improving SVM-Based Nontechnical Loss Detection in Power Utility Using the Fuzzy Inference System," IEEE Transactions on Power Delivery, vol. 26, no. 2, pp. 1284-1285, April 2011.