Time-Series Load Data Analysis for User Power Profiling

In this paper, we present a time-warping power profiling model for smart grid consumers based on real time load data acquired smart meters. It profiles consumers based on their power consumption behaviour using the dynamic time warping (DTW) clustering algorithm. Due to the invariability of signal warping of this algorithm, time-disordered load data can be profiled and consumption features be extracted. Two load types are defined and the related load patterns are extracted for clustering consumption behaviour by DTW. The classification methodology is discussed in detail. To evaluate the performance of the method, we analyze the time-series load data measured by a smart meter in a real case. The results verify the effectiveness of the proposed profiling method with 90.91% true positive rate for load type clustering in the best case.

[1]  A. Ghorbani,et al.  Memory forensics tools: a comparative analysis , 2022, Journal of Cyber Security Technology.

[2]  S. Stanek,et al.  A Multi-Agent Adaptive Architecture for Smart-Grid-Intrusion Detection and Prevention , 2022, Energies.

[3]  Ali A. Ghorbani,et al.  An evaluation framework for industrial control system cyber incidents , 2021, Int. J. Crit. Infrastructure Prot..

[4]  Md Fazla Elahe,et al.  Review of load data analytics using deep learning in smart grids: Open load datasets, methodologies, and application challenges , 2021, International Journal of Energy Research.

[5]  Abdel Moumen Darcherif,et al.  Energy management in the smart grid: State-of-the-art and future trends , 2021, International Journal of Engineering Business Management.

[6]  Debdeep Mukhopadhyay,et al.  Demand Manipulation Attack Resilient Privacy Aware Smart Grid Using PUFs and Blockchain , 2021, ACNS Workshops.

[7]  Ali A. Ghorbani,et al.  An evaluation framework for privacy‐preserving solutions applicable for blockchain‐based internet‐of‐things platforms , 2020, Secur. Priv..

[8]  Tianjiao Pu,et al.  Analysis of users’ electricity consumption behavior based on ensemble clustering , 2019 .

[9]  Juan M. Belman-Flores,et al.  Thermal and Energy Evaluation of a Domestic Refrigerator under the Influence of the Thermal Load , 2019, Energies.

[10]  Sanguthevar Rajasekaran,et al.  DTWNet: a Dynamic Time Warping Network , 2019, NeurIPS.

[11]  Zhihui Du,et al.  Program power profiling based on phase behaviors , 2018, Sustain. Comput. Informatics Syst..

[12]  E. Bompard,et al.  Big data analytics in smart grids: a review , 2018, Energy Inform..

[13]  Orhan Kaplan,et al.  The Determination of Load Profiles and Power Consumptions of Home Appliances , 2018 .

[14]  Laurent Itti,et al.  shapeDTW: Shape Dynamic Time Warping , 2016, Pattern Recognit..

[15]  Zheng Zhang,et al.  Dynamic Time Warping under limited warping path length , 2017, Inf. Sci..

[16]  Damiano Toffanin,et al.  Generation of customer load profiles based on smart-metering time series, building-level data and aggregated measurements , 2016 .

[17]  Fred Popowich,et al.  Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014 , 2016, Scientific Data.

[18]  Yuguang Fang,et al.  A Privacy-Preserving Scheme for Incentive-Based Demand Response in the Smart Grid , 2016, IEEE Transactions on Smart Grid.

[19]  Jaewoo Park,et al.  Detecting False Emergency Requests Using Callers' Reporting Behaviors and Locations , 2016, 2016 30th International Conference on Advanced Information Networking and Applications Workshops (WAINA).

[20]  Rohit J. Kate.  Using dynamic time warping distances as features for improved time series classification , 2016, Data Mining and Knowledge Discovery.

[21]  Abhisek Ukil,et al.  Modeling and Validation of Electrical Load Profiling in Residential Buildings in Singapore , 2015, IEEE Transactions on Power Systems.

[22]  Antans Sauhats,et al.  Analysis and prediction of electricity consumption using smart meter data , 2015, 2015 IEEE 5th International Conference on Power Engineering, Energy and Electrical Drives (POWERENG).

[23]  Chongqing Kang,et al.  Load profiling and its application to demand response: A review , 2015 .

[24]  Hyoungshick Kim,et al.  Privacy Preserving Nearest Neighbor Search Based on Topologies in Cellular Networks , 2015, 2015 IEEE 29th International Conference on Advanced Information Networking and Applications Workshops.

[25]  Wolfgang Kastner,et al.  Analysis of Similarity Measures in Times Series Clustering for the Discovery of Building Energy Patterns , 2013 .

[26]  Alfredo Pulvirenti,et al.  Similarity Measures and Dimensionality Reduction Techniques for Time Series Data Mining , 2012 .

[27]  Stephen B. Wicker,et al.  Inferring Personal Information from Demand-Response Systems , 2010, IEEE Security & Privacy.

[28]  Toni Giorgino,et al.  Computing and Visualizing Dynamic Time Warping Alignments in R: The dtw Package , 2009 .

[29]  Stan Salvador,et al.  FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space , 2004 .

[30]  Eamonn J. Keogh,et al.  Making Time-Series Classification More Accurate Using Learned Constraints , 2004, SDM.

[31]  Alan Bundy,et al.  Dynamic Time Warping , 1984 .