A data mining-based framework for the identification of daily electricity usage patterns and anomaly detection in building electricity consumption data

International Energy Agency (IEA), 2012, 2012 Fan, 2018, Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: a review, Energy Build., 159, 296, 10.1016/j.enbuild.2017.11.008 Miller, 2018, A review of unsupervised statistical learning and visual analytics techniques applied to performance analysis of non-residential buildings, Renew. Sustain. Energy Rev., 81, 1365, 10.1016/j.rser.2017.05.124 EIA. How many smart meters are installed in the United States, and who has them?; 2020 https://www.eia.gov/tools/faqs/faq.php?id=108&t=3 (Accessed on 11 July 2020). Wei, 2009, Government management and implementation of national real-time energy monitoring system for China large-scale public building, Energy Policy., 37, 2087, 10.1016/j.enpol.2008.12.032 Hou, 2016, Comparative study of commercial building energy-efficiency retrofit policies in four pilot cities in China, Energy Policy, 88, 204, 10.1016/j.enpol.2015.10.016 Zhao, 2020, A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis, Energy Built Environ., 1, 149, 10.1016/j.enbenv.2019.11.003 Li, 2018, Identification of typical building daily electricity usage profiles using Gaussian mixture model-based clustering and hierarchical clustering, Appl. Energy, 231, 331, 10.1016/j.apenergy.2018.09.050 Rajabi, 2020, A comparative study of clustering techniques for electrical load pattern segmentation, Renew. Sustain. Energy Rev., 120, 10.1016/j.rser.2019.109628 Wei, 2018, A review of data-driven approaches for prediction and classification of building energy consumption, Renew. Sustain. Energy Rev., 82, 1027, 10.1016/j.rser.2017.09.108 Aghabozorgi, 2015, Time-series clustering – A decade review, Inf. Syst., 53, 16, 10.1016/j.is.2015.04.007 Ma, 2017, A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings, Energy, 134, 90, 10.1016/j.energy.2017.05.191 Li, 2019, An agglomerative hierarchical clustering-based strategy using Shared Nearest Neighbours and multiple dissimilarity measures to identify typical daily electricity usage profiles of university library buildings, Energy, 174, 735, 10.1016/j.energy.2019.03.003 Y. Wang, Q. Chen, C. Kang, Q. Xia, Clustering of Electricity Consumption Behavior Dynamics Toward Big Data Applications, (2017). https://doi.org/10.1109/TSG.2016.2548565. Lu, 2019, GMM clustering for heating load patterns in-depth identification and prediction model accuracy improvement of district heating system, Energy Build., 190, 49, 10.1016/j.enbuild.2019.02.014 Park, 2019, Apples or oranges? Identification of fundamental load shape profiles for benchmarking buildings using a large and diverse dataset, Appl. Energy, 236, 1280, 10.1016/j.apenergy.2018.12.025 Wen, 2019, A shape-based clustering method for pattern recognition of residential electricity consumption, J. Clean. Prod., 212, 475, 10.1016/j.jclepro.2018.12.067 Do Carmo, 2016, Cluster analysis of residential heat load profiles and the role of technical and household characteristics, Energy Build., 125, 171, 10.1016/j.enbuild.2016.04.079 M. Verleysen, D. François, The curse of dimensionality in data mining and time series pre- diction, In: Proceedings of International Work-Conference on Artificial Neural Networks (IWANN 2005), Heidelberg, Berlin, Springer, 2005. pp. 758–770. 2005. https://doi.org/10.1007/11494669_93. Chiba, 1978, Dynamic Programming Algorithm Optimization for Spoken Word Recognition, IEEE Trans. Acoust Speech Singal Process., 1, 159 A. Sard, Comparing Time-Series Clustering Algorithms in R Using the dtwclust Comparing Time-Series Clustering Algorithms in R Using the dtwclust Package, (2019). Luo, 2017, Electric load shape benchmarking for small- and medium-sized commercial buildings, Appl. Energy., 204, 715, 10.1016/j.apenergy.2017.07.108 T. Räsänen, M. Kolehmainen, Feature-Based Clustering for Electricity Use Time Feature-Based Clustering for Electricity Use, In: Proceedings of international conference on adaptive and natural computing algorithms (LNCS 5495). Berlin, Germany: Springer-Verlag; 2009. pp. 401–412. 2009. https://doi.org/10.1007/978-3-642-04921-7. Haben, 2016, Analysis and clustering of residential customers energy behavioral demand using smart meter data, IEEE Trans. Smart Grid., 1, 136, 10.1109/TSG.2015.2409786 Fan, 2015, A framework for knowledge discovery in massive building automation data and its application in building diagnostics, Autom. Constr., 50, 81, 10.1016/j.autcon.2014.12.006 F. Wang, K. Li, N. Dui, Z. Mi, B. Hodge, M. Sha, J.P.S. Catalão, Association rule mining based quantitative analysis approach of household characteristics impacts on residential electricity consumption patterns, 171 (2018) 839–854. https://doi.org/10.1016/j.enconman.2018.06.017. Capozzoli, 2018, Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings, Energy, 157, 336, 10.1016/j.energy.2018.05.127 McLoughlin, 2015, A clustering approach to domestic electricity load profile characterisation using smart metering data, Appl. Energy, 141, 190, 10.1016/j.apenergy.2014.12.039 Ma, 2017, A real-time detection method of abnormal building energy consumption data coupled POD-LSE and FCD, Procedia Eng., 205, 1657, 10.1016/j.proeng.2017.10.334 Zhao, 2016, Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach, IEEE Trans. Geosci. Remote Sens., 54, 4544, 10.1109/TGRS.2016.2543748 Sarkar, 2019, On perfect clustering of high dimension, low sample size data, IEEE Trans. Pattern Anal. Mach. Intell., 1 M. Ester, H. Kriegel, X. Xu, D.- Miinchen, A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise, In: Proceedings of the 2nd ACM SIGKDD, Portland, Oregon; 1996. pp. 226–231. M. Hahsler M. Piekenbrock S. Arya D. Mount R, Package 'dbscan' 2020 (Accessed on 11 July 2020). Xu, 2005, Survey of clustering algorithms, IEEE Trans. Neural Netw., 16, 645, 10.1109/TNN.2005.845141 Benítez, 2014, Dynamic clustering segmentation applied to load profiles of energy consumption from Spanish customers, Int. J. Electr. Power Energy Syst., 55, 437, 10.1016/j.ijepes.2013.09.022 B. Lkhagva, Y. Suzuki, K. Kawagoe, New Time Series Data Representation ESAX for Financial Applications New Time Series Data Representation ESAX for Financial Applications, 22nd International Conference on Data Engineering Workshops (ICDEW'06), Atlanta, GA, USA, 2006, pp. x115–x115, https://doi.org/10.1109/ICDEW.2006.99. G. Brock, V. Pihur, S. Datta, S. Datta, ClValid: An R package for cluster validation, J. Stat. Softw. 25 (2008) 1–22. https://doi.org/10.18637/jss.v025.i04. R. Agrawal, Mining Association Rules between Sets of Items in Large Databases, In: Proc of the 1993 ACM-SIGMOD international conference on management of data. pp. 207–216. T.M. Therneau, E.J. Atkinson, An Introduction to Recursive Partitioning Using the RPART Routines, 2019 https://cran.r-project.org/web/packages/rpart/vignettes/longintro.pdf (Accessed on 11July 2020). P. Rousseeuw, A. Struyf, M. Hubert, M. Studer, P. Roudier, Package 'cluster', 2020 https://cran.r-project.org/web/packages/cluster/cluster.pdf (Accessed on 11 July 2020). T. Therneau, B. Atkinson, B. Ripley, M.B. Ripley, R Package 'rpart', 2020 http://cran.ma.ic.ac.uk/web/packages/rpart/rpart.pdf (Accessed on 11 July 2020). Li, 2018, An object-oriented energy benchmark for the evaluation of the office building stock, Util. Policy, 51, 1, 10.1016/j.jup.2018.01.008 Zhao, 2013, Development of an energy monitoring system for large public buildings, Energy Build., 66, 41, 10.1016/j.enbuild.2013.07.007 Miller, 2017, The building data genome project: an open, public data set from non-residential building electrical meters, Energy Procedia, 122, 439, 10.1016/j.egypro.2017.07.400 Wang, 2020, Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN), Energy Build., 224, 10.1016/j.enbuild.2020.110299 Sun, 2014, Stochastic modeling of overtime occupancy and its application in building energy simulation and calibration, Build. Environ., 79, 1, 10.1016/j.buildenv.2014.04.030 Biernacki, 2000, Assessing a mixture model for clustering with the integrated completed likelihood, IEEE Trans. Pattern Anal. Mach. Intell., 22, 719, 10.1109/34.865189 Hubert, 1976, Quadratic assignment as a general data analysis strategy, Br. J. Math. Stat. Psychol., 29, 190, 10.1111/j.2044-8317.1976.tb00714.x Caliñski, 1974, A dendrite method foe cluster analysis, Commun. Stat., 3, 1 Dunn, 1974, Well-separated clusters and optimal fuzzy partitions, J. Cybern., 4, 95, 10.1080/01969727408546059 Davies, 1979, A cluster separation measure, IEEE Trans. Pattern Anal. Mach. Intell., 29, 224, 10.1109/TPAMI.1979.4766909 Rousseeuw, 1987, Silhouettes: a graphical aid to the interpretation and validation of cluster analysis, J. Comput. Appl. Math., 20, 53, 10.1016/0377-0427(87)90125-7