Unsupervised grouping of industrial electricity demand profiles: Synthetic profiles for demand-side management applications

Abstract Demand side management is a promising alternative to offer flexibility to power systems with high shares of variable renewable energy sources. Numerous industries possess large demand side management potentials but accounting for them in energy system analysis and modelling is restricted by the availability of their demand data, which are usually confidential. In this study, a methodology to synthetize anonymized hourly electricity consumption profiles for industries and to calculate their flexibility potential is proposed. This combines different partitioning and hierarchical clustering analysis techniques with regression analysis. The methodology is applied to three case studies in Chile: two pulp and paper industry plants and one food industry plant. A significant hourly, daily and annual flexibility potential is found for the three cases (15% to 75%). Moreover, the resulting demand profiles share the same statistical characteristics as the measured profiles but can be used in modelling exercises without confidentiality issues.

[1]  Mark Junjie Li,et al.  Load Pattern Shape Clustering Analysis for Manufacturing , 2017, SmartCom.

[2]  Martin K. Patel,et al.  Comparison of clustering approaches for domestic electricity load profile characterisation - Implications for demand side management , 2019, Energy.

[3]  Michalis Vazirgiannis,et al.  c ○ 2001 Kluwer Academic Publishers. Manufactured in The Netherlands. On Clustering Validation Techniques , 2022 .

[4]  Geeta Sikka,et al.  Recent Techniques of Clustering of Time Series Data: A Survey , 2012 .

[5]  Ian F. C. Smith,et al.  A Bounded Index for Cluster Validity , 2007, MLDM.

[6]  Omid Motlagh,et al.  Clustering of residential electricity customers using load time series , 2019, Applied Energy.

[7]  J. Torriti,et al.  Demand response experience in Europe: Policies, programmes and implementation , 2010 .

[8]  Iñaki Albisua,et al.  SEP/COP: An efficient method to find the best partition in hierarchical clustering based on a new cluster validity index , 2010, Pattern Recognit..

[9]  Eng Gee Lim,et al.  A parametric bootstrap algorithm for cluster number determination of load pattern categorization , 2019 .

[10]  Carl-Fredrik Lindberg,et al.  Potential and limitations for industrial demand side management , 2014 .

[11]  Peter Laurinec,et al.  Comparison of Representations of Time Series for Clustering Smart Meter Data , 2016 .

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

[13]  Samuel J.G. Cooper,et al.  Uses of industrial energy benchmarking with reference to the pulp and paper industries , 2018, Renewable and Sustainable Energy Reviews.

[14]  Joydeep Ghosh,et al.  Data Clustering Algorithms And Applications , 2013 .

[15]  Martin K. Patel,et al.  Who is sensitive to DSM? Understanding the determinants of the shape of electricity load curves and demand shifting: Socio-demographic characteristics, appliance use and attitudes , 2019, Energy Policy.

[16]  R. Tol,et al.  Energy-using appliances and energy-saving features: Determinants of ownership in Ireland , 2008 .

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

[18]  Jose I. Bilbao,et al.  Recent advances in the analysis of residential electricity consumption and applications of smart meter data , 2017 .

[19]  J. Valdes,et al.  Industry, flexibility, and demand response: Applying German energy transition lessons in Chile , 2019, Energy Research & Social Science.

[20]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[21]  Aidan Duffy,et al.  Evaluation of time series techniques to characterise domestic electricity demand , 2013 .

[22]  Nikola Rajaković,et al.  Demand response capacity estimation in various supply areas , 2015 .

[23]  Ignacio E. Grossmann,et al.  Enterprise-wide optimization for industrial demand side management: Fundamentals, advances, and perspectives , 2016 .

[24]  Atsushi Imiya,et al.  Machine Learning and Data Mining in Pattern Recognition , 2013, Lecture Notes in Computer Science.

[25]  Ernst Worrell,et al.  Energy efficiency in the German pulp and paper industry – A model-based assessment of saving potentials , 2012 .

[26]  Risto Lahdelma,et al.  Economic potential of industrial demand side management in pulp and paper industry , 2017 .

[27]  J. Dunn.  Well-Separated Clusters and Optimal Fuzzy Partitions , 1974 .

[28]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Lynn Price,et al.  Assessment of emerging energy-efficiency technologies for the pulp and paper industry: a technical review , 2016 .

[30]  K. Sreekanth,et al.  A review on implementation strategies for demand side management (DSM) in Kuwait through incentive-based demand response programs , 2017 .

[31]  Philipp Grünewald,et al.  Demand response from the non-domestic sector: Early UK experiences and future opportunities , 2013 .

[32]  Gonzalo Escribano Francés,et al.  Energy security and renewable energy deployment in the EU: Liaisons Dangereuses or Virtuous Circle? , 2016 .

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

[34]  Hans Christian Gils,et al.  Assessment of the theoretical demand response potential in Europe , 2014 .

[35]  Yunesky Masip Macia,et al.  Unveiling the potential for combined heat and power in Chilean industry - A policy perspective , 2020, Energy Policy.

[36]  Te Li Su,et al.  Energy flow analysis in pulp and paper industry , 2011 .

[37]  A. Elayaperumal,et al.  Studies on combined cooling and drying of agro products using air cooled internal heat recovered vapour absorption system , 2016 .

[38]  Frieder Borggrefe,et al.  The potential of demand-side management in energy-intensive industries for electricity markets in Germany , 2011 .

[39]  P. Pathare,et al.  Recent advances in sustainable drying of agricultural produce: A review , 2019, Applied Energy.

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

[41]  A. Poulin,et al.  Daily load profiles clustering : a powerful tool for demand side management in medium-sized industries , 2017 .

[42]  Hao Yang,et al.  Spatial disparity and hierarchical cluster analysis of final energy consumption in China , 2020 .

[43]  Brian Norton,et al.  Real-life energy use in the UK: How occupancy and dwelling characteristics affect domestic electricity use , 2008 .

[44]  Alexis Sarda-Espinosa,et al.  Comparing Time-Series Clustering Algorithms in R Using the dtwclust Package , 2017 .