Identification of typical building daily electricity usage profiles using Gaussian mixture model-based clustering and hierarchical clustering

Abstract This paper presents a clustering-based strategy to identify typical daily electricity usage (TDEU) profiles of multiple buildings. Different from the majority of existing clustering strategies, the proposed strategy consists of two levels of clustering, i.e. intra-building clustering and inter-building clustering. The intra-building clustering used a Gaussian mixture model-based clustering to identify the TDEU profiles of each individual building. The inter-building clustering used an agglomerative hierarchical clustering to identify the TDEU profiles of multiple buildings based on the TDEU profiles identified for each individual building through intra-building clustering. The performance of this strategy was evaluated using two-year hourly electricity consumption data collected from 40 university buildings. The results showed that this strategy can discover useful information related to building electricity usage, including typical patterns of daily electricity usage (DEU) and periodical variation of DEU. It was also shown that this proposed strategy can identify additional electricity usage patterns with a less computational cost, in comparison to two single-step clustering strategies including a Partitioning Around Medoids-based clustering strategy and a hierarchical clustering strategy. The results obtained from this study could be potentially used to assist in improving energy performance of university buildings and other types of buildings.

[1]  Gianfranco Chicco,et al.  Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings , 2018, Energy.

[2]  Yong Shi,et al.  Cluster analysis for occupant-behavior based electricity load patterns in buildings: A case study in Shanghai residences , 2017 .

[3]  Andrea Costa,et al.  Building operation and energy performance: Monitoring, analysis and optimisation toolkit , 2013 .

[4]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[5]  Fu Xiao,et al.  A framework for knowledge discovery in massive building automation data and its application in building diagnostics , 2015 .

[6]  A. Raftery,et al.  Model-based Gaussian and non-Gaussian clustering , 1993 .

[7]  Hadley Wickham,et al.  ggplot2 - Elegant Graphics for Data Analysis (2nd Edition) , 2017 .

[8]  Zhenjun Ma,et al.  Building energy performance assessment using volatility change based symbolic transformation and hierarchical clustering , 2018 .

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

[10]  Alfonso Capozzoli,et al.  Mining typical load profiles in buildings to support energy management in the smart city context , 2017 .

[11]  João Miguel da Costa Sousa,et al.  Analysis of residential natural gas consumers using fuzzy c-means clustering , 2016, 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[12]  John E. Seem,et al.  Pattern recognition algorithm for determining days of the week with similar energy consumption profiles , 2005 .

[13]  Chandra Sekhar,et al.  k-Shape clustering algorithm for building energy usage patterns analysis and forecasting model accuracy improvement , 2017 .

[14]  J. H. Ward.  Hierarchical Grouping to Optimize an Objective Function , 1963 .

[15]  Michael Conlon,et al.  A clustering approach to domestic electricity load profile characterisation using smart metering data , 2015 .

[16]  Ruth Kerrigan,et al.  Identification of representative buildings and building groups in urban datasets using a novel pre-processing, classification, clustering and predictive modelling approach , 2018, Building and Environment.

[17]  J. Cavanaugh,et al.  The Bayesian information criterion: background, derivation, and applications , 2012 .

[18]  Fionn Murtagh.  Expected-Time Complexity Results for Hierarchic Clustering Algorithms Which Use Cluster Centres , 1983, Inf. Process. Lett..

[19]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[20]  Roger K. Blashfield,et al.  Mixture model tests of cluster analysis: Accuracy of four agglomerative hierarchical methods. , 1976 .

[21]  Anil K. Jain,et al.  Unsupervised Learning of Finite Mixture Models , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  David Hsu,et al.  Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data , 2015 .

[23]  Charles Bouveyron,et al.  Model-based clustering of high-dimensional data: A review , 2014, Comput. Stat. Data Anal..

[24]  Herricos Stapountzis,et al.  Energy analysis of an improved concept of integrated PV panels in an office building in central Greece , 2011 .

[25]  Michael E. Webber,et al.  Clustering analysis of residential electricity demand profiles , 2014 .

[26]  W. Torgerson.  Multidimensional scaling: I. Theory and method , 1952 .

[27]  Luca Scrucca,et al.  mclust 5: Clustering, Classification and Density Estimation Using Gaussian Finite Mixture Models , 2016, R J..

[28]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[29]  Nhien-An Le-Khac,et al.  Efficient Large Scale Clustering Based on Data Partitioning , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[30]  Furong Li,et al.  A novel time-of-use tariff design based on Gaussian Mixture Model , 2016 .

[31]  Sarvapali D. Ramchurn,et al.  On the distinctiveness of the electricity load profile , 2018, Pattern Recognit..

[32]  N.D. Hatziargyriou,et al.  Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers , 2007, IEEE Transactions on Power Systems.

[33]  Ryuichiro Yoshie,et al.  Development and construction of the novel solar thermal desiccant cooling system incorporating hot water production , 2010 .

[34]  Theofilos A. Papadopoulos,et al.  Pattern recognition algorithms for electricity load curve analysis of buildings , 2014 .

[35]  Vipin Kumar,et al.  Introduction to Data Mining , 2022, Data Mining and Machine Learning Applications.

[36]  Zhenjun Ma,et al.  A sensor fault detection strategy for air handling units using cluster analysis , 2016 .

[37]  Hamid A. Jalab,et al.  A Hybrid Algorithm for Clustering of Time Series Data Based on Affinity Search Technique , 2014, TheScientificWorldJournal.

[38]  Zhenjun Ma,et al.  Nano-enhanced phase change materials for improved building performance , 2016 .

[39]  Zhenjun Ma,et al.  A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings , 2017 .

[40]  M. Ouyang,et al.  Approximate Pontryagin’s minimum principle applied to the energy management of plug-in hybrid electric vehicles , 2014 .

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

[42]  Mary Ann Piette,et al.  Electric load shape benchmarking for small- and medium-sized commercial buildings , 2017 .

[43]  Zhenjun Ma,et al.  Optimal design of vertical ground heat exchangers by using entropy generation minimization method and genetic algorithms , 2014 .