Classification and characterization of intra-day load curves of PV and non-PV households using interpretable feature extraction and feature-based clustering

Abstract Load pattern categorization plays a significant role in enhancing the understanding of demand characteristics of different cohorts of energy customers on a distribution network. For a distribution network with embedded photovoltaic (PV) systems, it is also desirable to enumerate these premises since unreported PV installations can have a detrimental impact on voltage control, frequency regulation, and incur reverse power flows. In this paper, a holistic smart meter data analytics approach is proposed for classifying and characterizing the intra-day load curves of PV and non-PV households. Unlike existing studies based on raw time-series data, a series of interpretable and discriminating global and peak-period features are first developed to extract the physical information of load patterns. A two-step feature-based clustering is then applied to classify the load profiles of PV and non-PV households. A post-clustering quantitative compositional analysis is developed to characterize the energy use variability and compositional changes for each household. The proposed PV household identification method allows network owners to identify the existence of PV installations in a particular area for voltage control and ancillary service provision. In the longer term, effective load pattern categorization and post-clustering characterization can help better understand demand characteristics of different cohorts of customers, network utilization, and network-level changes in load growth.

[1]  Eamonn J. Keogh,et al.  Mining motifs in massive time series databases , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[2]  Fu Xiao,et al.  Neighborhood-level coordination and negotiation techniques for managing demand-side flexibility in residential microgrids , 2021 .

[3]  Eamonn J. Keogh,et al.  HOT SAX: efficiently finding the most unusual time series subsequence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[4]  Gianfranco Chicco,et al.  Overview and performance assessment of the clustering methods for electrical load pattern grouping , 2012 .

[5]  Fu Xiao,et al.  Frequency control of air conditioners in response to real-time dynamic electricity prices in smart grids , 2019, Applied Energy.

[6]  Heng Huang,et al.  Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities , 2015, IEEE Transactions on Smart Grid.

[7]  Chao Shen,et al.  A review of electric load classification in smart grid environment , 2013 .

[8]  Arno Schlueter,et al.  Unsupervised learning of energy signatures to identify the heating system and building type using smart meter data , 2020 .

[9]  Carsten Rode,et al.  Clustering-based analysis for residential district heating data , 2018, Energy Conversion and Management.

[10]  John Aitchison,et al.  The Statistical Analysis of Compositional Data , 1986 .

[11]  Jens Timmer,et al.  Characteristics of hand tremor time series , 1993, Biological Cybernetics.

[12]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[13]  Kelum A. A. Gamage,et al.  Demand side management in smart grid: A review and proposals for future direction , 2014 .

[14]  Arno Schlueter,et al.  Automated daily pattern filtering of measured building performance data , 2015 .

[15]  Fei Wang,et al.  A Distributed PV System Capacity Estimation Approach Based on Support Vector Machine with Customer Net Load Curve Features , 2018 .

[16]  Carolina Carmo,et al.  Cluster analysis of residential heat load profiles and the role of technical and household characteristics , 2016 .

[17]  Linyun Xiong,et al.  Optimal energy management and control aspects of distributed microgrid using multi-agent systems , 2019, Sustainable Cities and Society.

[18]  David Wallom,et al.  Clustering disaggregated load profiles using a Dirichlet process mixture model , 2015 .

[19]  A. Lima,et al.  Measuring the change under compositional data analysis (CoDA): Insight on the dynamics of geochemical systems , 2017, Journal of Geochemical Exploration.

[20]  Jorge Cadima,et al.  Principal component analysis: a review and recent developments , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[21]  Da Yan,et al.  Building categorization revisited: A clustering-based approach to using smart meter data for building energy benchmarking , 2020 .

[22]  Yi Wang,et al.  Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges , 2018, IEEE Transactions on Smart Grid.

[23]  Pierluigi Siano,et al.  Demand response and smart grids—A survey , 2014 .

[24]  Xiaochen Zhang,et al.  A Data-Driven Approach for Detection and Estimation of Residential PV Installations , 2016, IEEE Transactions on Smart Grid.

[25]  V. Pawlowsky-Glahn,et al.  Dealing with Zeros and Missing Values in Compositional Data Sets Using Nonparametric Imputation , 2003 .

[26]  David C. H. Wallom,et al.  Impacts of Raw Data Temporal Resolution Using Selected Clustering Methods on Residential Electricity Load Profiles , 2015, IEEE Transactions on Power Systems.

[27]  Fábio Gonçalves Jota,et al.  Building load management using cluster and statistical analyses , 2011 .

[28]  Shilpa Lakhina,et al.  Feature Reduction using Principal Component Analysis for Effective Anomaly – Based Intrusion Detection on NSL-KDD , 2010 .

[29]  A.G. Marin,et al.  Characterization and identification of electrical customers through the use of self-organizing maps and daily load parameters , 2004, IEEE PES Power Systems Conference and Exposition, 2004..

[30]  R. Granell,et al.  Predicting winning and losing businesses when changing electricity tariffs , 2014 .

[31]  Ram Rajagopal,et al.  Lifestyle Segmentation Based on Energy Consumption Data , 2018, IEEE Transactions on Smart Grid.

[32]  Yang Zhao,et al.  Demand side flexibility: potentials and building performance implications , 2016 .

[33]  Shengwei Wang,et al.  Coordinated demand-controlled ventilation strategy for energy-efficient operation in multi-zone cleanroom air-conditioning systems , 2021 .

[34]  G. A. Taylor,et al.  Towards an understanding of dynamic energy pricing and tariffs , 2012, 2012 47th International Universities Power Engineering Conference (UPEC).

[35]  Mohamed Chaouch,et al.  Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves , 2014, IEEE Transactions on Smart Grid.

[36]  Jordan M. Malof,et al.  Automatic Detection of Solar Photovoltaic Arrays in High Resolution Aerial Imagery , 2016, ArXiv.

[37]  Joao P. S. Catalao,et al.  Impact of distributed generation on protection and voltage regulation of distribution systems: A review , 2019, Renewable and Sustainable Energy Reviews.

[38]  Gui Yun Tian,et al.  A FEATURE EXTRACTION TECHNIQUE BASED ON PRINCIPAL COMPONENT ANALYSIS FOR PULSED EDDY CURRENT NDT , 2003 .

[39]  Miguel Brito,et al.  Impact of solar and wind forecast uncertainties on demand response of isolated microgrids , 2016 .

[40]  G. Chicco,et al.  Comparisons among clustering techniques for electricity customer classification , 2006, IEEE Transactions on Power Systems.

[41]  Mikko Kolehmainen,et al.  Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data , 2010 .

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

[43]  Li Wei,et al.  Experiencing SAX: a novel symbolic representation of time series , 2007, Data Mining and Knowledge Discovery.