Extracting discriminative features for event-based electricity disaggregation

We describe a novel method for electricity load disaggregation based on the machine learning method of time series shapelets. We frame the electricity disaggregation problem as that of event detection and event classification from time series data. We use existing shapelet-based algorithms to separate appliance activity periods (caused by switching on/off of appliances and denoted as events) from time periods without any such activity. We then identify which type of appliances in a household correspond to the events detected within the power consumption data. Such appliance-level feedback is critical for end-users in managing their energy use efficiently. We use the BLUED dataset for experimental evaluation of the proposed method. This dataset is a fully labeled publicly available dataset of electricity consumption of a household in the United States for one week, the data being recorded at a very high frequency and externally labeled with the times when specific appliances were switched on or off. The proposed approach is able to achieve approximately 98% accuracy for event detection and between 77% to 84% accuracy for event classification. The data segments that were identified as being most discriminative for electricity disaggregation are visually interpretable, and the appliances identified to be responsible for heavy energy consumption can be reported to consumers to encourage reduction in energy consumption.

[1]  Xi Fang,et al.  3. Full Four-channel 6.3-gb/s 60-ghz Cmos Transceiver with Low-power Analog and Digital Baseband Circuitry 7. Smart Grid — the New and Improved Power Grid: a Survey , 2022 .

[2]  Radu Zmeureanu,et al.  Using a pattern recognition approach to disaggregate the total electricity consumption in a house into the major end-uses , 1999 .

[3]  Francisco Martinez Alvarez,et al.  Energy Time Series Forecasting Based on Pattern Sequence Similarity , 2011, IEEE Transactions on Knowledge and Data Engineering.

[4]  Eamonn J. Keogh,et al.  Fast Shapelets: A Scalable Algorithm for Discovering Time Series Shapelets , 2013, SDM.

[5]  Eamonn J. Keogh,et al.  Time series shapelets: a new primitive for data mining , 2009, KDD.

[6]  Yogesh L. Simmhan,et al.  Energy management systems: state of the art and emerging trends , 2013, IEEE Communications Magazine.

[7]  Vikrambhai S. Sorathia,et al.  Semantic management of Enterprise Integration Patterns: A use case in Smart Grids , 2014, 2014 IEEE 30th International Conference on Data Engineering Workshops.

[8]  José M. F. Moura,et al.  Event detection for Non Intrusive load monitoring , 2012, IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society.

[9]  Philip S. Yu,et al.  Extracting Interpretable Features for Early Classification on Time Series , 2011, SDM.

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

[11]  Alessandro Margara,et al.  Processing flows of information: From data stream to complex event processing , 2012, CSUR.

[12]  Anthony Rowe,et al.  BLUED : A Fully Labeled Public Dataset for Event-Based Non-Intrusive Load Monitoring Research , 2012 .

[13]  Eamonn J. Keogh,et al.  Clustering Time Series Using Unsupervised-Shapelets , 2012, 2012 IEEE 12th International Conference on Data Mining.

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

[15]  Juan Shishido,et al.  Smart Meter Data Quality Insights , 2012 .

[16]  Gregor Hohpe,et al.  Enterprise Integration Patterns: Designing, Building, and Deploying Messaging Solutions , 2003 .

[17]  Lucio Soibelman,et al.  User-Centered Nonintrusive Electricity Load Monitoring for Residential Buildings , 2011 .

[18]  Gail E. Kaiser,et al.  An Active Events Model for Systems Monitoring , 2001 .

[19]  Vikrambhai S. Sorathia,et al.  The process-oriented event model (PoEM): a conceptual model for industrial events , 2014, DEBS '14.

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

[21]  Muhammad Ali Imran,et al.  Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey , 2012, Sensors.

[22]  Abhay Gupta,et al.  Is disaggregation the holy grail of energy efficiency? The case of electricity , 2013 .

[23]  Eric C. Larson,et al.  Disaggregated End-Use Energy Sensing for the Smart Grid , 2011, IEEE Pervasive Computing.