An Efficient Sparse Coding-Based Data-Mining Scheme in Smart Grid

With the availability of Smart Grid, disaggregation, i.e. decomposing a whole electricity signal into its component appliances has gotten more and more attentions. Now the solutions based on the sparse coding, i.e. the supervised learning algorithm that belongs to Non-Intrusive Load Monitoring (NILM) have developed a lot. But the accuracy and efficiency of these solutions are not very high, we propose a new efficient sparse coding-based data-mining (ESCD) scheme in this paper to achieve higher accuracy and efficiency. First, we propose a new clustering algorithm – Probability Based Double Clustering (PDBC) based on Fast Search and Find of Density Peaks Clustering (FSFDP) algorithm, which can cluster the device consumption features fast and efficiently. Second, we propose a feature matching optimization algorithm – Max-Min Pruning Matching (MMPM) algorithm which can make the feature matching process to be real-time. Third, real experiments on a publicly available energy data set REDD [1] demonstrate that our proposed scheme achieves a for energy disaggregation. The average disaggregation accuracy reaches 77% and the disaggregation time for every 20 data is about 10 s.

[1]  Henning Lange,et al.  Efficient Inference in Dual-Emission FHMM for Energy Disaggregation , 2016, AAAI Workshop: AI for Smart Grids and Smart Buildings.

[2]  Tommi S. Jaakkola,et al.  Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation , 2012, AISTATS.

[3]  Xiaojiang Du,et al.  A survey of key management schemes in wireless sensor networks , 2007, Comput. Commun..

[4]  Zuowei Shen,et al.  Dictionary Learning for Sparse Coding: Algorithms and Convergence Analysis , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[6]  Benny Pinkas,et al.  Cryptographic techniques for privacy-preserving data mining , 2002, SKDD.

[7]  Angshul Majumdar,et al.  Nuclear norm regularized robust dictionary learning for energy disaggregation , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[8]  Secure cell relay routing protocol for sensor networks: Research Articles , 2006 .

[9]  Manish Marwah,et al.  A Temporal Motif Mining Approach to Unsupervised Energy Disaggregation: Applications to Residential and Commercial Buildings , 2013, AAAI.

[10]  S. Shankar Sastry,et al.  Energy Disaggregation via Learning Powerlets and Sparse Coding , 2015, AAAI.

[11]  Steven B. Leeb,et al.  Non-intrusive electrical load monitoring in commercial buildings based on steady-state and transient load-detection algorithms , 1996 .

[12]  Jie Wu,et al.  Defending Resource Depletion Attacks on Implantable Medical Devices , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[13]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[14]  A.C. Liew,et al.  Neural-network-based signature recognition for harmonic source identification , 2006, IEEE Transactions on Power Delivery.

[15]  Rajasekhar Mungara,et al.  A Routing-Driven Elliptic Curve Cryptography based Key Management Scheme for Heterogeneous Sensor Networks , 2014 .

[16]  Mohsen Guizani,et al.  Transactions papers a routing-driven Elliptic Curve Cryptography based key management scheme for Heterogeneous Sensor Networks , 2009, IEEE Transactions on Wireless Communications.

[17]  Chase Qishi Wu,et al.  Secure cell relay routing protocol for sensor networks , 2005, PCCC 2005. 24th IEEE International Performance, Computing, and Communications Conference, 2005..

[18]  Gregory D. Abowd,et al.  At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line (Nominated for the Best Paper Award) , 2007, UbiComp.

[19]  Steven B. Leeb,et al.  Nonintrusive Load Monitoring and Diagnostics in Power Systems , 2008, IEEE Transactions on Instrumentation and Measurement.

[20]  Shwetak N. Patel,et al.  ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home , 2010, UbiComp.

[21]  Steven B. Leeb,et al.  Instrumentation for High Performance Nonintrusive Electrical Load Monitoring , 1998 .

[22]  N. Goddard,et al.  Interleaved factorial non-homogeneous hidden Markov models for energy disaggregation , 2014, 1406.7665.

[23]  Mohsen Guizani,et al.  Secure and Efficient Time Synchronization in Heterogeneous Sensor Networks , 2008, IEEE Transactions on Vehicular Technology.

[24]  G. W. Hart,et al.  Nonintrusive appliance load monitoring , 1992, Proc. IEEE.

[25]  Manish Marwah,et al.  Unsupervised Disaggregation of Low Frequency Power Measurements , 2011, SDM.

[26]  Xiaojiang Du,et al.  A Lightweight Multicast Authentication Mechanism for Small Scale IoT Applications , 2013, IEEE Sensors Journal.

[27]  Andrew Y. Ng,et al.  Energy Disaggregation via Discriminative Sparse Coding , 2010, NIPS.

[28]  Lucio Soibelman,et al.  Learning Systems for Electric Consumption of Buildings , 2009 .

[29]  Patrik O. Hoyer,et al.  Non-negative sparse coding , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[30]  S. Shankar Sastry,et al.  Dissimilarity-Based Sparse Subset Selection , 2015, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  J. Zico Kolter,et al.  REDD : A Public Data Set for Energy Disaggregation Research , 2011 .