A new strategy to benchmark and evaluate building electricity usage using multiple data mining technologies

Abstract This study presents a new strategy using cluster analysis, multivariate adaptive regression splines and conditional inference trees to benchmark and evaluate building electricity usage. Different from the existing studies, cluster analysis was first used to group buildings based on their annual electricity usage patterns in order to improve the accuracy of the benchmarking result. Multivariate adaptive regression splines technique was then applied to capture the non-linear relationships (i.e. benchmarking models) between building electricity usage per square meter and explanatory factors with enhanced interpretability. Conditional inference trees technique was further used to evaluate the benchmarking result. The performance of this strategy was evaluated using two-year time-series electricity usage data of 20 university buildings. The results showed that the multivariate adaptive regression splines can effectively describe the complex non-linear relationships between building electricity usage per square meter and explanatory variables. The conditional inference trees can help identify conditions when buildings had higher electricity usage. The results obtained from this study can be further used to assist in building energy auditing, and fault detection and diagnosis.

[1]  Siew Eang Lee,et al.  Review of occupancy sensing systems and occupancy modeling methodologies for the application in institutional buildings , 2016 .

[2]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[3]  Zhenjun Ma,et al.  Using evidence accumulation-based clustering and symbolic transformation to group multiple buildings based on electricity usage patterns , 2020 .

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

[5]  Ram Rajagopal,et al.  Benchmarking building energy efficiency using quantile regression , 2018, Energy.

[6]  Suzanne Lacasse,et al.  State-of-the-art review of soft computing applications in underground excavations , 2020, Geoscience Frontiers.

[7]  Qiang Zhang,et al.  Model-based benchmarking with application to laboratory buildings , 2002 .

[8]  Niklaus Kohler,et al.  Building age as an indicator for energy consumption , 2015 .

[9]  Fu Xiao,et al.  Quantitative energy performance assessment methods for existing buildings , 2012 .

[10]  Zhenjun Ma,et al.  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 , 2019, Energy.

[11]  P. McCullagh,et al.  Generalized Linear Models , 1972, Predictive Analytics.

[12]  K. Hornik,et al.  Unbiased Recursive Partitioning: A Conditional Inference Framework , 2006 .

[13]  Wengang Zhang,et al.  Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization , 2021 .

[14]  Kumar Neeraj Jha,et al.  Benchmarking green building attributes to achieve cost effectiveness using a data envelopment analysis , 2017 .

[15]  Chongzhi Wu,et al.  Probabilistic stability analysis of earth dam slope under transient seepage using multivariate adaptive regression splines , 2020, Bulletin of Engineering Geology and the Environment.

[16]  Jiahui Liu,et al.  An energy performance evaluation methodology for individual office building with dynamic energy benchmarks using limited information , 2017 .

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

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

[19]  William Chung,et al.  Using the fuzzy linear regression method to benchmark the energy efficiency of commercial buildings , 2012 .

[20]  Jelena Srebric,et al.  Building energy model calibration with schedules derived from electricity use data , 2017 .

[21]  Neng Zhu,et al.  Benchmark analysis of electricity consumption for complex campus buildings in China , 2018 .

[22]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines for analysis of geotechnical engineering systems , 2013 .

[23]  William Chung,et al.  Review of building energy-use performance benchmarking methodologies , 2011 .

[24]  Sandhya Patidar,et al.  Understanding the energy consumption and occupancy of a multi-purpose academic building , 2015 .

[25]  Zheng Yang,et al.  DUE-B: Data-driven urban energy benchmarking of buildings using recursive partitioning and stochastic frontier analysis , 2018 .

[26]  Laia Ledo,et al.  Energy efficiency and thermal comfort upgrades for higher education buildings , 2015 .

[27]  Zhengwei Li,et al.  Methods for benchmarking building energy consumption against its past or intended performance: An overview , 2014 .

[28]  Vojislav Novakovic,et al.  Review of possibilities and necessities for building lifetime commissioning , 2009 .

[29]  Pandarasamy Arjunan,et al.  Apples or oranges? Identification of fundamental load shape profiles for benchmarking buildings using a large and diverse dataset , 2019, Applied Energy.

[30]  Zhenjun Ma,et al.  A decision tree based data-driven diagnostic strategy for air handling units , 2016 .

[31]  Alfonso Capozzoli,et al.  A novel methodology for energy performance benchmarking of buildings by means of Linear Mixed Effect Model: The case of space and DHW heating of out-patient Healthcare Centres , 2016 .

[32]  Endong Wang,et al.  Benchmarking whole-building energy performance with multi-criteria technique for order preference by similarity to ideal solution using a selective objective-weighting approach , 2015 .

[33]  Chongzhi Wu,et al.  Assessment of pile drivability using random forest regression and multivariate adaptive regression splines , 2019, Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards.

[34]  Umberto Berardi,et al.  A data-driven approach for building energy benchmarking using the Lorenz curve , 2018, Energy and Buildings.

[35]  Jlm Jan Hensen,et al.  Evaluating energy performance in non-domestic buildings : a review , 2016 .

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

[37]  G. Zheng,et al.  Multivariate adaptive regression splines model for prediction of the liquefaction-induced settlement of shallow foundations , 2020 .

[38]  Chen Chang,et al.  Using a novel method to obtain heating energy benchmarks in a cold region of China for the preparation of formulating incentive energy policies , 2020 .

[39]  Zhonghua Gou,et al.  Energy use characteristics and benchmarking for higher education buildings , 2018 .

[40]  Zheng Wei,et al.  A study of city-level building energy efficiency benchmarking system for China , 2018, Energy and Buildings.

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

[42]  Endong Wang,et al.  Multi-criteria building energy performance benchmarking through variable clustering based compromise TOPSIS with objective entropy weighting , 2017 .

[43]  Ali M. Malkawi,et al.  A new methodology for building energy performance benchmarking: An approach based on intelligent clustering algorithm , 2014 .