Automated daily pattern filtering of measured building performance data

Abstract The amount of sensor data generated by modern building systems is growing rapidly. Automatically discovering the structure of diurnal patterns in this data supports implementation of building commissioning, fault detection and retrofit analysis techniques. Additionally, these data are crucial to informing design professionals about the efficacy of their assumptions and strategies used in performance prediction simulation models. In this paper, we introduce DayFilter , a day-typing process that uses Symbolic Aggregate approXimation (SAX), motif and discord extraction, and clustering to detect the underlying structure of building performance data. Discords, or infrequent daily patterns, are filtered and tagged for deeper, detailed analysis of potential energy savings opportunities. Motifs, or the most frequent patterns, are detected and further aggregated using k-means clustering. This procedure is designed for application on whole building and sub-system metrics from hierarchical building and energy management systems (BMS/EMS). The process transforms quantitative raw data into qualitative subgroups based on daily performance similarity and visualizes them using expressive techniques. We apply DayFilter on 474 days of example data from an international school campus in a tropical climate and 407 days of data from an office building from a temperate European climate. Discords are filtered resulting in 17 and 22 patterns found. Selected discords are investigated and many correlate with specific failures and energy savings detected by the on-site operations staff. Six and ten motif candidates are detected in the two case studies. These motifs are then further aggregated to five and six performance clusters that reflect the typical operational behavior of those projects. We discuss the influence of the parameter choices and provide initial parameter settings for the DayFilter process.

[1]  Xiaoli Li,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. 1 Classification of Energy Consumption in Buildings with Outlier Detection , 2022 .

[2]  Zhe Song,et al.  Clustering-Based Performance Optimization of the Boiler–Turbine System , 2008, IEEE Transactions on Energy Conversion.

[3]  Jessica Granderson,et al.  Building energy information systems: user case studies , 2011 .

[4]  Benjamin C. M. Fung,et al.  A novel methodology for knowledge discovery through mining associations between building operational data , 2012 .

[5]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[6]  Kasper Hornbæk,et al.  Big data from the built environment , 2011, LARGE '11.

[7]  James A. Davis,et al.  Occupancy diversity factors for common university building types , 2010 .

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

[9]  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).

[10]  Benjamin C. M. Fung,et al.  Extracting knowledge from building-related data — A data mining framework , 2013, Building Simulation.

[11]  Fu Xiao,et al.  Data mining in building automation system for improving building operational performance , 2014 .

[12]  Ben Shneiderman,et al.  The eyes have it: a task by data type taxonomy for information visualizations , 1996, Proceedings 1996 IEEE Symposium on Visual Languages.

[13]  Bei Chen,et al.  Exploiting Generalized Additive Models for Diagnosing Abnormal Energy Use in Buildings , 2013, BuildSys@SenSys.

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

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

[16]  Mahbubur Rashid,et al.  Evaluating a data clustering approach for life-cycle facility control , 2013, J. Inf. Technol. Constr..

[17]  Manish Marwah,et al.  Sustainable operation and management of data center chillers using temporal data mining , 2009, KDD.

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

[19]  Donald L. Hadley,et al.  Daily variations in HVAC system electrical energy consumption in response to different weather conditions , 1993 .

[20]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

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

[22]  Eamonn J. Keogh,et al.  Visualizing and Discovering Non-Trivial Patterns in Large Time Series Databases , 2005, Inf. Vis..

[23]  Dina Q. Goldin,et al.  On Similarity Queries for Time-Series Data: Constraint Specification and Implementation , 1995, CP.

[24]  Sebastian Herkel,et al.  Black-box models for fault detection and performance monitoring of buildings , 2010 .

[25]  Jessica Lin,et al.  Visually mining and monitoring massive time series , 2004, KDD.

[26]  M. Manic,et al.  Computational intelligence based anomaly detection for Building Energy Management Systems , 2012, 2012 5th International Symposium on Resilient Control Systems.

[27]  Mo Yang,et al.  Field implementation and evaluation of a decoupling-based fault detection and diagnostic method for chillers , 2014 .

[28]  Takehisa Yairi,et al.  Identification of Causal Variables for Building Energy Fault Detection by Semi-supervised LDA and Decision Boundary Analysis , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[29]  Anthony R. Florita,et al.  Classification of Commercial Building Electrical Demand Profiles for Energy Storage Applications , 2013 .

[30]  Martin Fischer,et al.  A method to compare simulated and measured data to assess building energy performance , 2012 .

[31]  Paul Raftery,et al.  A review of methods to match building energy simulation models to measured data , 2014 .

[32]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

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

[34]  John E. Seem,et al.  Using intelligent data analysis to detect abnormal energy consumption in buildings , 2007 .

[35]  Richard T. Watson,et al.  A new paradigm for the design and management of building systems , 2012 .

[36]  Eamonn J. Keogh,et al.  Towards parameter-free data mining , 2004, KDD.

[37]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[38]  Jochen Teizer,et al.  Mobile 3D mapping for surveying earthwork projects using an Unmanned Aerial Vehicle (UAV) system , 2014 .

[39]  Carlos Duarte,et al.  Revealing occupancy patterns in an office building through the use of occupancy sensor data , 2013 .

[40]  Dino Bouchlaghem,et al.  Predicted vs. actual energy performance of non-domestic buildings: Using post-occupancy evaluation data to reduce the performance gap , 2012 .

[41]  David E. Claridge,et al.  Compilation of Diversity Factors and Schedules for Energy and Cooling Load Calculations, ASHRAE Research Project 1093-RP, Final Report , 1999 .

[42]  Peter Weiner,et al.  Linear Pattern Matching Algorithms , 1973, SWAT.

[43]  Xiufeng Pang,et al.  Model-based real-time whole building energy performance monitoring and diagnostics , 2014, Automated Diagnostics and Analytics for Buildings.

[44]  J. F. Kreider,et al.  Detecting whole building energy problems , 1999 .

[45]  Hiroshi Esaki,et al.  Strip, Bind, and Search: A method for identifying abnormal energy consumption in buildings , 2013, 2013 ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

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

[47]  Manish Marwah,et al.  Visual exploration of frequent patterns in multivariate time series , 2012, Inf. Vis..

[48]  Pieter de Wilde,et al.  The gap between predicted and measured energy performance of buildings: A framework for investigation , 2014 .