A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings

Marco Savino Piscitelli; Silvio Brandi; Alfonso Capozzoli; Fu Xiao

doi:10.1007/s12273-020-0650-1

Building Simulation 2021, 14(1): 131-147 https://doi.org/10.1007/s12273-020-0650-1

Research Article | Issue | Published: 13 May 2020

A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings

Show Author's Information Hide Author's Information Marco Savino Piscitelli^{¹^,²}, Silvio Brandi^¹, Alfonso Capozzoli^¹(

), Fu Xiao^²

1Department of Energy "Galileo Ferraris", TEBE research group, Politecnico di Torino, Italy

2Department of Building Services Engineering, The Hong Kong Polytechnic University, Hong Kong, China

Keywords:

pattern recognition, data analytics, anomaly detection, energy management, prediction models

Cite this article:

Piscitelli MS, Brandi S, Capozzoli A, et al. A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings. Building Simulation, 2021, 14(1): 131-147. https://doi.org/10.1007/s12273-020-0650-1

Download citation

EndNote(RIS)

BibTeX

567

Views

Downloads

Citations

Crossref

N/A

WoS

Scopus

CSCD

Abstract Full text About this article

Abstract

In this paper, a tool for the detection and diagnosis of anomalous electrical daily energy patterns relative to a transformer substation of a university campus was developed and tested. Through an innovative pattern recognition analysis consisting in a multi-step clustering process, six clusters of anomalous daily load profiles were identified and isolated in two-year historical data of total electrical energy consumption. The infrequent electrical load profiles were found to be strongly affected, in terms of both shape and magnitude, by the energy consumption behaviour related to the heating/cooling mechanical room. Then, a fault-free predictive model, which uses artificial neural network (ANN) in combination with a Regression Tree, was developed to detect anomalous trends of the electrical energy consumption. The model was able to detect the 93.7% of the anomalous profiles and only the 5% of fault-free days were wrongly predicted as anomalous. Eventually, a diagnosis phase was conceived and validated with a testing data set. A number of daily abnormal load profiles were detected and compared with the centroids of the anomalous clusters identified in the pattern-recognition stage. The work led to the development of a flexible intelligent tool useful for operating a continuous commissioning of the campus facilities.

Full text

Abstract

Full text

Outline

About this article

A data analytics-based tool for the detection and diagnosis of anomalous daily energy patterns in buildings

Show Author's information Hide Author's Information Marco Savino Piscitelli^{¹^,²}, Silvio Brandi^¹, Alfonso Capozzoli^¹(

), Fu Xiao^²

1Department of Energy "Galileo Ferraris", TEBE research group, Politecnico di Torino, Italy

2Department of Building Services Engineering, The Hong Kong Polytechnic University, Hong Kong, China

Abstract

Keywords: pattern recognition, data analytics, anomaly detection, energy management, prediction models

References(40)

Ahmad MW, Mourshed M, Yuce B, Rezgui Y (2016). Computational intelligence techniques for HVAC systems: A review. Building Simulation, 9: 359-398.

DOI Google Scholar

Breiman L, Friedman JH, Olshen RA, Stone CJ (1984). Classification and regression trees. New York: Routledge.

Capozzoli A, Lauro F, Khan I (2015). Fault detection analysis using data mining techniques for a cluster of smart office buildings. Expert Systems with Applications, 42: 4324-4338.

DOI Google Scholar

Capozzoli A, Piscitelli MS, Brandi S (2017). Mining typical load profiles in buildings to support energy management in the smart city context. Energy Procedia, 134: 865-874.

DOI Google Scholar

Capozzoli A, Piscitelli MS, Brandi S, Grassi D, Chicco G (2018). Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings. Energy, 157: 336-352.

DOI Google Scholar

Chicco G, Napoli R, Piglione F, Postolache P, Scutariu M, Toader C (2005). Emergent electricity customer classification. IEE Proceedings - Generation, Transmission and Distribution, 152: 164-172.

DOI Google Scholar

Chicco G, Napoli R, Piglione F (2006). Comparisons among clustering techniques for electricity customer classification. IEEE Transactions on Power Systems, 21: 933-940.

DOI Google Scholar

Chou JS, Telaga AS (2014). Real-time detection of anomalous power consumption. Renewable and Sustainable Energy Reviews, 33: 400-411.

DOI Google Scholar

Corder GW, Foreman DI (2014). Nonparametric statistics: A step-by- step approach. Hoboken, NJ, USA: John Wiley & Sons.

Davies DL, Bouldin DW (1979). A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1: 224-227.

DOI Google Scholar

Dehestani D, Eftekhari F, Guo Y, Ling S, Su S, Nguyen H (2011). Online support vector machine applicationfor model based fault detection and isolationof HVAC system. International Journal of Machine Learning and Computing, 1: 66-72.

DOI Google Scholar

Du Z, Fan B, Jin X, Chi J (2014). Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis. Building and Environment, 73: 1-11.

DOI Google Scholar

DOE (2012). Buildings Energy Databook. Office of Energy Efficiency and Renewable Energy, Department of Energy, USA.

EPBD (2009). Directive 2010/31/EU of the European Parliament and of the Council of 19 May 2019 on the energy performance of buildings.

Fan C, Xiao F, Madsen H, Wang D (2015). Temporal knowledge discovery in big BAS data for building energy management. Energy and Buildings, 109: 75-89.

DOI Google Scholar

Fan C, Xiao F, Zhao Y, Wang J (2018). Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data. Applied Energy, 211: 1123-1135.

DOI Google Scholar

González PA, Zamarreño JM (2005). Prediction of hourly energy consumption in buildings based on a feedback artificial neural network. Energy and Buildings, 37: 595-601.

DOI Google Scholar

Hinton G, Srivastava N, Swersky K (2012). Neural networks for machine learning lecture 6a overview of mini-batch gradient descent.

Han H, Gu B, Hong Y, Kang J (2011a). Automated FDD of multiple- simultaneous faults (MSF) and the application to building chillers. Energy and Buildings, 43: 2524-2532.

DOI Google Scholar

Han H, Gu B, Wang T, Li ZR (2011b). Important sensors for chiller fault detection and diagnosis (FDD) from the perspective of feature selection and machine learning. International Journal of Refrigeration, 34: 586-599.

DOI Google Scholar

Kim W, Katipamula S (2018). A review of fault detection and diagnostics methods for building systems. Science and Technology for the Built Environment, 24: 3-21.

DOI Google Scholar

Ku K, Jeong S (2018). Building electric energy prediction modeling for BEMS using easily obtainable weather factors with Kriging model and data mining. Building Simulation, 11: 739-751.

DOI Google Scholar

Li D, Zhou Y, Hu G, Spanos CJ (2016). Fault detection and diagnosis for building cooling system with a tree-structured learning method. Energy and Buildings, 127: 540-551.

DOI Google Scholar

Liang J, Du R (2007). Model-based fault detection and diagnosis of HVAC systems using support vector machine method. International Journal of Refrigeration, 30: 1104-1114.

DOI Google Scholar

Miller C, Nagy Z, Schlueter A (2015). Automated daily pattern filtering of measured building performance data. Automation in Construction, 49: 1-17.

DOI Google Scholar

Miller C, Nagy Z, Schlueter A (2018). A review of unsupervised statistical learning and visual analytics techniques applied to performance analysis of non-residential buildings. Renewable and Sustainable Energy Reviews, 81: 1365-1377.

DOI Google Scholar

Miller C (2019). More buildings make more generalizable models— Benchmarking prediction methods on open electrical meter data. Machine Learning and Knowledge Extraction, 1: 974-993.

DOI Google Scholar

Nair V, Hinton GE (2010). Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807-814.

Panapakidis I, Christoforidis G (2018). Optimal selection of clustering algorithm via multi-criteria decision analysis (MCDA) for load profiling applications. Applied Sciences, 8: 237.

DOI Google Scholar

Pearson RK (1999). Data cleaning for dynamic modeling and control. In: Proceedings of 1999 European Control Conference (ECC), pp. 2584-2589.

DOI

Piscitelli MS, Chiabrera E, Brandi S, Capozzoli A (2018). A tool for anomaly detection of energy consumption in buildings: The case of Politecnico di Torino campus. In: Proceedings of the 4th Asia Conference of International Building Performance Simulation Association (ASim2018), Hong Kong, China.

Piscitelli MS, Brandi S, Capozzoli A (2019). Recognition and classification of typical load profiles in buildings with non-intrusive learning approach. Applied Energy, 255: 113727.

DOI Google Scholar

Qiu S, Feng F, Li Z, Yang G, Xu P, Li Z (2019). Data mining based framework to identify rule based operation strategies for buildings with power metering system. Building Simulation, 12: 195-205.

DOI Google Scholar

R Core Team (2017). R: A Language and Environment for Statistical Computing. Available at http://www.r-project.org/.

Tan P-N, Steinbach M, Kumar V (2006). Classification: Basic concepts, decision trees, and model evaluation. In: Tan P-N, Steinbach M, Kumar V (eds), Introduction to Data Mining. Boston, MA, USA: Addison-Wesley. pp. 145-205.

DOI

Pan S, Wang X, Wei Y, Zhang X, Gal C, Ren G, Yan D, Shi Y, Wu J, Xia L, Xie J, Liu J (2017). Cluster analysis for occupant-behavior based electricity load patterns in buildings: A case study in Shanghai residences. Building Simulation, 10: 889-898.

DOI Google Scholar

Yan R, Ma Z, Kokogiannakis G, Zhao Y (2016). A sensor fault detection strategy for air handling units using cluster analysis. Automation in Construction, 70: 77-88.

DOI Google Scholar

Yu Z, Fung BCM, Haghighat F (2013). Extracting knowledge from building-related data—A data mining framework. Building Simulation, 6: 207-222.

DOI Google Scholar

Zhao Y, Wen J, Wang S (2015). Diagnostic Bayesian networks for diagnosing air handling units faults - Part II: Faults in coils and sensors. Applied Thermal Engineering, 90: 145-157.

DOI Google Scholar

Zhao Y, Wen J, Xiao F, Yang X, Wang S (2017). Diagnostic Bayesian networks for diagnosing air handling units faults - part I: Faults in dampers, fans, filters and sensors. Applied Thermal Engineering, 111: 1272-1286.

DOI Google Scholar

About this article

Publication history

Acknowledgements

Publication history

Received: 24 August 2019

Accepted: 15 April 2020

Published: 13 May 2020

Issue date: February 2021

Copyright

Acknowledgements

The authors express their gratitude to Living Lab of PoliTo for providing data and to Eng. Giovanni Carioni for the support in data preparation and collection. The authors also gratefully acknowledge the support of this research by the Research Grant Council of the Hong Kong SAR (152133/19E).