A novel methodology to explain and evaluate data-driven building energy performance models based on interpretable machine learning

Abstract The development of advanced data-driven approaches for building energy management is becoming increasingly essential in the era of big data. Machine learning techniques have gained great popularity in predictive modeling due to their excellence in capturing nonlinear and complicated relationships. However, it is a big challenge for building professionals to fully understand the inference mechanism learnt and put trust into the prediction made, as the models developed are typically of high complexity and low interpretability. To enhance the practical value of advanced machine learning techniques in the building field, this study proposes a comprehensive methodology to explain and evaluate data-driven building energy performance models. The methodology is developed based on the framework of interpretable machine learning. It can help building professionals to understand the inference mechanism learnt, e.g., why a certain prediction is made and what are the supporting and conflicting evidences towards the prediction. A novel metric, i.e., trust, is proposed as an alternative approach other than conventional accuracy metrics to evaluate model performance. The methodology has been validated based on actual building operational data. The results obtained are valuable for the development of intelligent and user-friendly building management systems.

[1]  Miguel Molina-Solana,et al.  Data science for building energy management: A review , 2017 .

[2]  Arno Schlueter,et al.  A review of unsupervised statistical learning and visual analytics techniques applied to performance analysis of non-residential buildings , 2018 .

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

[4]  Shu-Hsien Liao,et al.  Data mining techniques and applications - A decade review from 2000 to 2011 , 2012, Expert Syst. Appl..

[5]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

[6]  Zhuoyuan Zheng,et al.  Oversampling Method for Imbalanced Classification , 2015, Comput. Informatics.

[7]  Yan Lu,et al.  Modeling and forecasting of cooling and electricity load demand , 2014 .

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  J. Gower,et al.  Metric and Euclidean properties of dissimilarity coefficients , 1986 .

[10]  Fu Xiao,et al.  Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review , 2018 .

[11]  Melvin Robinson,et al.  Prediction of residential building energy consumption: A neural network approach , 2016 .

[12]  P. N. Suganthan,et al.  An approach for classification of highly imbalanced data using weighting and undersampling , 2010, Amino Acids.

[13]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[14]  Fu Xiao,et al.  A short-term building cooling load prediction method using deep learning algorithms , 2017 .

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  Benjamin C. M. Fung,et al.  A decision tree method for building energy demand modeling , 2010 .

[17]  Huanxin Chen,et al.  Machine learning-based thermal response time ahead energy demand prediction for building heating systems , 2018, Applied Energy.

[18]  Fan Yang,et al.  Effect of input variables on cooling load prediction accuracy of an office building , 2018 .

[19]  Gail Brager,et al.  Making sense of building data: New analysis methods for understanding indoor climate , 2018 .

[20]  Jui-Sheng Chou,et al.  Smart meter monitoring and data mining techniques for predicting refrigeration system performance , 2014, Expert Syst. Appl..

[21]  Yibo Chen,et al.  Short-term prediction of electric demand in building sector via hybrid support vector regression , 2017 .

[22]  Xiaodong Cao,et al.  Building energy-consumption status worldwide and the state-of-the-art technologies for zero-energy buildings during the past decade , 2016 .

[23]  Siti Mariyam Shamsuddin,et al.  Classification with class imbalance problem: A review , 2015, SOCO 2015.

[24]  Chirag Deb,et al.  Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks , 2016 .

[25]  Benjamin C. M. Fung,et al.  Advances and challenges in building engineering and data mining applications for energy-efficient communities , 2016 .

[26]  Yueren Wang,et al.  A novel ensemble learning approach to support building energy use prediction , 2018 .

[27]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[28]  Francisco Herrera,et al.  An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics , 2013, Inf. Sci..

[29]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[30]  Jessica Granderson,et al.  Gradient boosting machine for modeling the energy consumption of commercial buildings , 2018 .

[31]  Qiang Zhang,et al.  Research on short-term and ultra-short-term cooling load prediction models for office buildings , 2017 .

[32]  Ravi Prakash,et al.  Life cycle energy analysis of buildings: An overview , 2010 .

[33]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[34]  Yong Shi,et al.  A review of data-driven approaches for prediction and classification of building energy consumption , 2018 .

[35]  Gary Higgins,et al.  Prediction of indoor temperature in an institutional building , 2017 .