Data-driven building energy modeling with feature selection and active learning for data predictive control

Zhang, Liang

doi:10.1016/j.enbuild.2021.111436

Title: Data-driven building energy modeling with feature selection and active learning for data predictive control

Journal Article · 09 September 2021 · Energy and Buildings

DOI: https://doi.org/10.1016/j.enbuild.2021.111436 · OSTI ID:1823584

^[1]

National Renewable Energy Lab. (NREL), Golden, CO (United States)

Three gaps impede the development of cost-effective and accurate data-driven building energy modeling/models (DBEM) for energy forecasting and predictive control strategies. Gap 1: data bias is common in building operation data, but this topic is hardly studied in DBEM; Gap 2: high data dimensionality is common in DBEM, but a systematic and scalable methodology is lacking to solve the problem; Gap 3: the interactions between data bias and high dimensionality have not been systematically studied for DBEM and predictive control in buildings. In this work, to address the three gaps mentioned above, we develop a framework that integrates active learning and feature selection for DBEM used for whole building data predictive control (or DPC, which is a branch of model predictive control). The framework provides a systematic methodology and automatic workflow that starts with raw data from building automation systems to the establishment of data-driven energy models for DPC controllers. The developed strategies and framework are evaluated in a virtual testbed based on EnergyPlus and BCVTB. Improved performance and reduced computational complexity are observed from the DBEM built with the developed framework, as well as the DPC controller based on that DBEM, indicating the effectiveness of the developed framework.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: National Renewable Energy Laboratory (NREL), Golden, CO (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office

Grant/Contract Number:: AC36-08GO28308

OSTI ID:: 1823584

Report Number(s):: NREL/JA--5500-81110; MainId:79886; UUID:3161d00f-506b-4840-be8a-d289ff4d8bd0; MainAdminID:63064

Journal Information:: Energy and Buildings, Journal Name: Energy and Buildings Vol. 252; ISSN 0378-7788

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (42)

Small-Scale Building Load Forecast based on Hybrid Forecast Engine Mohammadi, Mohsen; Talebpour, Faraz; Safaee, Esmaeil Neural Processing Letters, Vol. 48, Issue 1 https://doi.org/10.1007/s11063-017-9723-2	journal	October 2017
EnergyPlus: creating a new-generation building energy simulation program Crawley, Drury B.; Lawrie, Linda K.; Winkelmann, Frederick C. Energy and Buildings, Vol. 33, Issue 4 https://doi.org/10.1016/S0378-7788(00)00114-6	journal	April 2001
A data-driven approach for steam load prediction in buildings Kusiak, Andrew; Li, Mingyang; Zhang, Zijun Applied Energy, Vol. 87, Issue 3 https://doi.org/10.1016/j.apenergy.2009.09.004	journal	March 2010
Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques Fan, Cheng; Xiao, Fu; Wang, Shengwei Applied Energy, Vol. 127 https://doi.org/10.1016/j.apenergy.2014.04.016	journal	August 2014
A review of machine learning in building load prediction Zhang, Liang; Wen, Jin; Li, Yanfei Applied Energy, Vol. 285 https://doi.org/10.1016/j.apenergy.2021.116452	journal	March 2021
A selective sampling approach to active feature selection Liu, Huan; Motoda, Hiroshi; Yu, Lei Artificial Intelligence, Vol. 159, Issue 1-2 https://doi.org/10.1016/j.artint.2004.05.009	journal	November 2004
Theory and applications of HVAC control systems – A review of model predictive control (MPC) Afram, Abdul; Janabi-Sharifi, Farrokh Building and Environment, Vol. 72 https://doi.org/10.1016/j.buildenv.2013.11.016	journal	February 2014
Optimal HVAC Control as Demand Response with On-site Energy Storage and Generation System Lee, Young M.; Horesh, Raya; Liberti, Leo Energy Procedia, Vol. 78 https://doi.org/10.1016/j.egypro.2015.11.253	journal	November 2015
Impact of adaptive comfort criteria and heat waves on optimal building thermal mass control Henze, Gregor P.; Pfafferott, Jens; Herkel, Sebastian Energy and Buildings, Vol. 39, Issue 2 https://doi.org/10.1016/j.enbuild.2006.06.006	journal	February 2007
A decision tree method for building energy demand modeling Yu, Zhun; Haghighat, Fariborz; Fung, Benjamin C. M. Energy and Buildings, Vol. 42, Issue 10 https://doi.org/10.1016/j.enbuild.2010.04.006	journal	October 2010
Use of model predictive control and weather forecasts for energy efficient building climate control Oldewurtel, Frauke; Parisio, Alessandra; Jones, Colin N. Energy and Buildings, Vol. 45 https://doi.org/10.1016/j.enbuild.2011.09.022	journal	February 2012
Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools Tsanas, Athanasios; Xifara, Angeliki Energy and Buildings, Vol. 49 https://doi.org/10.1016/j.enbuild.2012.03.003	journal	June 2012
Optimization of Predicted Mean Vote index within Model Predictive Control framework: Computationally tractable solution Cigler, Jiří; Prívara, Samuel; Váňa, Zdeněk Energy and Buildings, Vol. 52 https://doi.org/10.1016/j.enbuild.2012.05.022	journal	September 2012
Short-term load forecasting in a non-residential building contrasting models and attributes Massana, Joaquim; Pous, Carles; Burgas, Llorenç Energy and Buildings, Vol. 92 https://doi.org/10.1016/j.enbuild.2015.02.007	journal	April 2015
Ensemble of various neural networks for prediction of heating energy consumption Jovanović, Radiša Ž.; Sretenović, Aleksandra A.; Živković, Branislav D. Energy and Buildings, Vol. 94 https://doi.org/10.1016/j.enbuild.2015.02.052	journal	May 2015
Short-term electricity load forecasting of buildings in microgrids Chitsaz, Hamed; Shaker, Hamid; Zareipour, Hamidreza Energy and Buildings, Vol. 99 https://doi.org/10.1016/j.enbuild.2015.04.011	journal	July 2015
Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings Chae, Young Tae; Horesh, Raya; Hwang, Youngdeok Energy and Buildings, Vol. 111 https://doi.org/10.1016/j.enbuild.2015.11.045	journal	January 2016
Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption Ahmad, Muhammad Waseem; Mourshed, Monjur; Rezgui, Yacine Energy and Buildings, Vol. 147 https://doi.org/10.1016/j.enbuild.2017.04.038	journal	July 2017
Activity-aware HVAC power demand forecasting Sala-Cardoso, Enric; Delgado-Prieto, Miguel; Kampouropoulos, Konstantinos Energy and Buildings, Vol. 170 https://doi.org/10.1016/j.enbuild.2018.03.087	journal	July 2018
A systematic feature selection procedure for short-term data-driven building energy forecasting model development Zhang, Liang; Wen, Jin Energy and Buildings, Vol. 183 https://doi.org/10.1016/j.enbuild.2018.11.010	journal	January 2019
Comparison of time-frequency-analysis techniques applied in building energy data noise cancellation for building load forecasting: A real-building case study Zhang, Liang; Alahmad, Mahmoud; Wen, Jin Energy and Buildings, Vol. 231 https://doi.org/10.1016/j.enbuild.2020.110592	journal	January 2021
Active learning strategy for high fidelity short-term data-driven building energy forecasting Zhang, Liang; Wen, Jin Energy and Buildings, Vol. 244 https://doi.org/10.1016/j.enbuild.2021.111026	journal	August 2021
A hybrid short-term load forecasting with a new input selection framework Ghofrani, M.; Ghayekhloo, M.; Arabali, A. Energy, Vol. 81 https://doi.org/10.1016/j.energy.2015.01.028	journal	March 2015
Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques Jurado, Sergio; Nebot, Àngela; Mugica, Fransisco Energy, Vol. 86 https://doi.org/10.1016/j.energy.2015.04.039	journal	June 2015
Simplified dynamic neural network model to predict heating load of a building using Taguchi method Sholahudin, S.; Han, Hwataik Energy, Vol. 115 https://doi.org/10.1016/j.energy.2016.03.057	journal	November 2016
Electricity load forecasting by an improved forecast engine for building level consumers Liu, Yang; Wang, Wei; Ghadimi, Noradin Energy, Vol. 139 https://doi.org/10.1016/j.energy.2017.07.150	journal	November 2017
Forecasting Short-term Electricity Demand in Residential Sector Based on Support Vector Regression and Fuzzy-rough Feature Selection with Particle Swarm Optimization Son, Hyojoo; Kim, Changwan Procedia Engineering, Vol. 118 https://doi.org/10.1016/j.proeng.2015.08.459	journal	January 2015
Simulation Study on Supply Temperature Optimization of University Campus Heating System Basalaev, Aleksandr A.; Barbasova, Tatyana A.; Shnayder, Dmitry A. Procedia Engineering, Vol. 129 https://doi.org/10.1016/j.proeng.2015.12.070	journal	January 2015
Advanced control systems engineering for energy and comfort management in a building environment—A review Dounis, A. I.; Caraiscos, C. Renewable and Sustainable Energy Reviews, Vol. 13, Issue 6-7, p. 1246-1261 https://doi.org/10.1016/j.rser.2008.09.015	journal	August 2009
Review of building energy modeling for control and operation Li, Xiwang; Wen, Jin Renewable and Sustainable Energy Reviews, Vol. 37 https://doi.org/10.1016/j.rser.2014.05.056	journal	September 2014
Grey-box modeling and application for building energy simulations - A critical review Li, Yanfei; O'Neill, Zheng; Zhang, Liang Renewable and Sustainable Energy Reviews, Vol. 146 https://doi.org/10.1016/j.rser.2021.111174	journal	August 2021
CUR matrix decompositions for improved data analysis Mahoney, Michael W.; Drineas, Petros Proceedings of the National Academy of Sciences, Vol. 106, Issue 3 https://doi.org/10.1073/pnas.0803205106	journal	January 2009
Co-simulation of building energy and control systems with the Building Controls Virtual Test Bed Wetter, Michael Journal of Building Performance Simulation, Vol. 4, Issue 3 https://doi.org/10.1080/19401493.2010.518631	journal	September 2011
Household Electricity Demand Forecast Based on Context Information and User Daily Schedule Analysis From Meter Data Hsiao, Yu-Hsiang IEEE Transactions on Industrial Informatics, Vol. 11, Issue 1 https://doi.org/10.1109/TII.2014.2363584	journal	February 2015
A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines Ceperic, Ervin; Ceperic, Vladimir; Baric, Adrijan IEEE Transactions on Power Systems, Vol. 28, Issue 4 https://doi.org/10.1109/TPWRS.2013.2269803	journal	November 2013
Load Control Using Building Thermal Mass Braun, James E. Journal of Solar Energy Engineering, Vol. 125, Issue 3 https://doi.org/10.1115/1.1592184	journal	August 2003
Statistical Analysis of Neural Networks as Applied to Building Energy Prediction Dodier, Robert H.; Henze, Gregor P. Journal of Solar Energy Engineering, Vol. 126, Issue 1 https://doi.org/10.1115/1.1637640	journal	February 2004
Query by committee Seung, H. S.; Opper, M.; Sompolinsky, H. Proceedings of the fifth annual workshop on Computational learning theory - COLT '92 https://doi.org/10.1145/130385.130417	conference	January 1992
Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method Zhao, Hai-Xiang; Magoulès, Frédéric Journal of Algorithms & Computational Technology, Vol. 6, Issue 1 https://doi.org/10.1260/1748-3018.6.1.59	journal	March 2012
U.S. Department of Energy Commercial Reference Building Models of the National Building Stock Deru, M.; Field, K.; Studer, D. https://doi.org/10.2172/1009264	report	February 2011
Model Predictive Control (MPC) for Enhancing Building and HVAC System Energy Efficiency: Problem Formulation, Applications and Opportunities Serale, Gianluca; Fiorentini, Massimo; Capozzoli, Alfonso Energies, Vol. 11, Issue 3 https://doi.org/10.3390/en11030631	journal	March 2018
A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems Zhang, Liang Sensors, Vol. 20, Issue 20 https://doi.org/10.3390/s20205947	journal	October 2020

Similar Records

Building energy simulation in real time through an open standard interface

Journal Article · 2015 · Energy and Buildings · OSTI ID:1436593

Pang, Xiufeng; Nouidui, Thierry S.; Wetter, Michael; +3 more

A Modular Building Controls Virtual Test Bed for the Integrations of Heterogeneous Systems

Conference · 2008 · OSTI ID:936246

Wetter, Michael; Wetter, Michael; Haves, Philip

Building Controls Virtual Test Bed

Software · 2008 · OSTI ID:code-54668

Wetter, Michael; Haves, Philip; Coffey, Brian

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
active learning
data predictive control
data-driven building energy modeling
feature selection
joint active learning and feature selection
machine learning

Title: Data-driven building energy modeling with feature selection and active learning for data predictive control

Citation Formats

References (42)

Similar Records

Related Subjects