Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression

Rui Tang; Cheng Fan; Fanzhe Zeng; Wei Feng

doi:10.1007/s12273-021-0811-x

Building Simulation 2022, 15(3): 317-331 https://doi.org/10.1007/s12273-021-0811-x

Cover Article | Issue | Published: 30 June 2021

Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression

Show Author's Information Hide Author's Information Rui Tang^¹, Cheng Fan^{²^,³}(

), Fanzhe Zeng^⁴, Wei Feng^⁵

Institute for Environmental Design and Engineering, University College London, London, UK

Key Laboratory for Resilient Infrastructures of Coastal Cities (Shenzhen University), Ministry of Education, China

Sino-Australia Joint Research Center in BIM and Smart Construction, Shenzhen University, Shenzhen, China

School of Municipal and Environmental Engineering, Shenyang Jianzhu University, Shenyang, China

China Energy Group, Lawrence Berkeley National Laboratory, Berkeley, CA, USA

Keywords:

machine learning, smart grid, demand response, model predictive control, support vector regression, building peak demand

Cite this article:

Tang R, Fan C, Zeng F, et al. Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression. Building Simulation, 2022, 15(3): 317-331. https://doi.org/10.1007/s12273-021-0811-x

Download citation

EndNote(RIS)

BibTeX

559

Views

Downloads

Citations

Crossref

WoS

Scopus

CSCD

Abstract Full text Electronic supplementary material About this article

Abstract

Demand response (DR) of commercial buildings by directly shutting down part of operating chillers could provide an immediate power reduction for power grids. In this special fast DR event, effective control needs to guarantee expected power reduction and ensure an acceptable indoor environment. This study, therefore, developed a data-driven model predictive control (MPC) using support vector regression (SVR) for fast DR events. According to the characteristics of fast DR events, the optimized hyperparameters of SVR and shortened searching range of genetic algorithm are used to improve the control performance. Meanwhile, a comprehensive comparison with RC-based MPC is conducted based on three scenarios of power demand controls. Test results show that the proposed SVR-based MPC could fulfill the control objectives of power demand and indoor temperature simultaneously. Compared with RC-based MPC, the SVR-based MPC could alleviate the time/labor cost of model development without sacrificing the control performance of fast DR events.

Full text

Abstract

Full text

Outline

Electronic supplementary material

About this article

Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression

Show Author's information Hide Author's Information Rui Tang^¹, Cheng Fan^{²^,³}(

), Fanzhe Zeng^⁴, Wei Feng^⁵

Institute for Environmental Design and Engineering, University College London, London, UK

Key Laboratory for Resilient Infrastructures of Coastal Cities (Shenzhen University), Ministry of Education, China

Sino-Australia Joint Research Center in BIM and Smart Construction, Shenzhen University, Shenzhen, China

School of Municipal and Environmental Engineering, Shenyang Jianzhu University, Shenyang, China

China Energy Group, Lawrence Berkeley National Laboratory, Berkeley, CA, USA

Abstract

Keywords: machine learning, smart grid, demand response, model predictive control, support vector regression, building peak demand

References(51)

Afram A, Janabi-Sharifi F (2014). Theory and applications of HVAC control systems—A review of model predictive control (MPC). Building and Environment, 72: 343–355.

DOI Google Scholar

Ahmad MW, Reynolds J, Rezgui Y (2018). Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. Journal of Cleaner Production, 203: 810–821.

DOI Google Scholar

Arnold GW (2011). Challenges and opportunities in smart grid: A position article. Proceedings of the IEEE, 99: 922–927.

Google Scholar

Avci M, Erkoc M, Rahmani A, et al. (2013). Model predictive HVAC load control in buildings using real-time electricity pricing. Energy and Buildings, 60: 199–209.

DOI Google Scholar

Chen Y, Xu P, Chu Y, et al. (2017). Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings. Applied Energy, 195: 659–670.

DOI Google Scholar

Cui B, Wang S, Yan C, et al. (2015). Evaluation of a fast power demand response strategy using active and passive building cold storages for smart grid applications. Energy Conversion and Management, 102: 227–238.

DOI Google Scholar

Depuru SSSR, Wang L, Devabhaktuni V, et al. (2011). Smart meters for power grid—Challenges, issues, advantages and status. In: Proceedings of 2011 IEEE/PES Power Systems Conference and Exposition, Phoenix, AZ, USA.https://doi.org/10.1109/PSCE.2011.5772451

DOI

DOE (2011). 2011 DOE Building Energy Data Book. US Department of Energy. Available at http://buildingsdatabook.eren.doe.gov.

EMSD of Hong Kong (2014). Hong Kong Energy End-use Data, 2014. Electrical and Mechanical Services Department (EMSD) of Hong Kong Government. Available at https://data.gov.hk/en-data/dataset/hk-emsd-emsd1-energy-end-use-data-2014.

Fan C, Xiao F, Zhao Y (2017). A short-term building cooling load prediction method using deep learning algorithms. Applied Energy, 195: 222–233.

DOI Google Scholar

Fan C, Wang J, Gang W, et al. (2019). Assessment of deep recurrent neural network-based strategies for short-term building energy predictions. Applied Energy, 236: 700–710.

DOI Google Scholar

Fan C, Yan D, Xiao F, et al. (2021a). Advanced data analytics for enhancing building performances: From data-driven to big data-driven approaches. Building Simulation, 14: 3–24.

DOI Google Scholar

Fan C, Chen M, Wang X, et al. (2021b). A review on data preprocessing techniques towards efficient and reliable knowledge discovery from building operational data. Frontiers in Energy Research, 9: 652801.

DOI Google Scholar

Huang G, Wang S, Xu X (2009). A robust model predictive control strategy for improving the control performance of air-conditioning systems. Energy Conversion and Management, 50: 2650–2658.

DOI Google Scholar

Killian M, Kozek M (2016). Ten questions concerning model predictive control for energy efficient buildings. Building and Environment, 105: 403–412.

DOI Google Scholar

Klein SA, Beckman WA, Mitchell JW, et al. (2006). TRNSYS 16: Volume 8 Programmer's Guide. University of Wisconsin-Madison, USA. Available at http://web.mit.edu/parmstr/Public/Documentation/08-ProgrammersGuide.pdf. Accessed 2 July 2018.

Kolokotsa D, Rovas D, Kosmatopoulos E, et al. (2011). A roadmap towards intelligent net zero- and positive-energy buildings. Solar Energy, 85: 3067–3084.

DOI Google Scholar

Li Q, Meng Q, Cai J, et al. (2009). Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks. Energy Conversion and Management, 50: 90–96.

DOI Google Scholar

Li W, Xu P, Jiao F (2016). Optimal demand response strategy of a portfolio of multiple commercial buildings: Methods and a case study. Science and Technology for the Built Environment, 22: 655–665.

DOI Google Scholar

Li S, Peng J, Tan Y, et al. (2020). Study of the application potential of photovoltaic direct-driven air conditioners in different climate zones. Energy and Buildings, 226: 110387.

DOI Google Scholar

Lofberg J (2004). A toolbox for modeling and optimization in MATLAB. In: Proceedings of 2004 IEEE International Conference on Robotics and Automation.

Mai W, Chung CY (2015). Economic MPC of aggregating commercial buildings for providing flexible power reserve. IEEE Transactions on Power Systems, 30: 2685–2694.

DOI Google Scholar

Morari M, Lee JH (1999). Model predictive control: past, present and future. Computers & Chemical Engineering, 23: 667–682.

DOI Google Scholar

Motegi N, Piette MA, Watson DS, et al. (2007). Introduction to commercial building control strategies and techniques for demand response. Lawrence Berkeley National Laboratory LBNL-59975.https://doi.org/10.2172/1004169

DOI

Oldewurtel F, Parisio A, Jones CN, et al. (2012). Use of model predictive control and weather forecasts for energy efficient building climate control. Energy and Buildings, 45: 15–27.

DOI Google Scholar

Olivieri SJ, Henze GP, Corbin CD, et al. (2014). Evaluation of commercial building demand response potential using optimal short-term curtailment of heating, ventilation, and air-conditioning loads. Journal of Building Performance Simulation, 7: 100–118.

DOI Google Scholar

Gurobi Optimization (2014). Gurobi Optimizer Reference Manual. Available at http://www.gurobi.com.

Paniagua-Tineo A, Salcedo-Sanz S, Casanova-Mateo C, et al. (2011). Prediction of daily maximum temperature using a support vector regression algorithm. Renewable Energy, 36: 3054–3060.

DOI Google Scholar

Pérez-Lombard L, Ortiz J, Pout C (2008). A review on buildings energy consumption information. Energy and Buildings, 40: 394–398.

DOI Google Scholar

Popoola O, Chipango M (2021). Improved peak load management control technique for nonlinear and dynamic residential energy consumption pattern. Building Simulation, 14: 195–208.

DOI Google Scholar

Pourjafari E, Reformat M (2019). A support vector regression based model predictive control for volt-var optimization of distribution systems. IEEE Access, 7: 93352–93363.

DOI Google Scholar

Ran F, Gao D, Zhang X, et al. (2020). A virtual sensor based self-adjusting control for HVAC fast demand response in commercial buildings towards smart grid applications. Applied Energy, 269: 115103.

DOI Google Scholar

Simon D (2006). Optimal State Estimation: Kalman, H infinity, and Nonlinear Approaches. Hoboken, NJ, USA: John Wiley & Sons.https://doi.org/10.1002/0470045345

DOI

Smarra F, Jain A, de Rubeis T, et al. (2018). Data-driven model predictive control using random forests for building energy optimization and climate control. Applied Energy, 226: 1252–1272.

DOI Google Scholar

Tang R, Wang S, Gao D, et al. (2016). A power limiting control strategy based on adaptive utility function for fast demand response of buildings in smart grids. Science and Technology for the Built Environment, 22: 810–819.

DOI Google Scholar

Tang R, Wang S, Shan K, et al. (2018a). Optimal control strategy of central air-conditioning systems of buildings at morning start period for enhanced energy efficiency and peak demand limiting. Energy, 151: 771–781.

DOI Google Scholar

Tang R, Wang S, Yan C (2018b). A direct load control strategy of centralized air-conditioning systems for building fast demand response to urgent requests of smart grids. Automation in Construction, 87: 74–83.

DOI Google Scholar

Tang R, Wang S (2019). Model predictive control for thermal energy storage and thermal comfort optimization of building demand response in smart grids. Applied Energy, 242: 873–882.

DOI Google Scholar

Tang R, Wang S, Li H (2019). Game theory based interactive demand side management responding to dynamic pricing in price-based demand response of smart grids. Applied Energy, 250: 118–130.

DOI Google Scholar

Tuballa ML, Abundo ML (2016). A review of the development of Smart Grid technologies. Renewable and Sustainable Energy Reviews, 59: 710–725.

DOI Google Scholar

Tuhus-Dubrow D, Krarti M (2010). Genetic-algorithm based approach to optimize building envelope design for residential buildings. Building and Environment, 45: 1574–1581.

DOI Google Scholar

Wang S (1998). Dynamic simulation of a building central chilling system and evaluation of EMCS on-line control strategies. Building and Environment, 33: 1–20.

DOI Google Scholar

Wang S, Tang R (2017). Supply-based feedback control strategy of air-conditioning systems for direct load control of buildings responding to urgent requests of smart grids. Applied Energy, 201: 419–432.

DOI Google Scholar

Wang J, Li S, Chen H, et al. (2019). Data-driven model predictive control for building climate control: Three case studies on different buildings. Building and Environment, 160: 106204.

DOI Google Scholar

Xi X, Poo AN, Chou SK (2007). Support vector regression model predictive control on a HVAC plant. Control Engineering Practice, 15: 897–908.

DOI Google Scholar

Xu L, Wang S, Tang R (2019). Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load. Applied Energy, 237: 180–195.

DOI Google Scholar

Xue, Wang S, Yan C, et al. (2015). A fast chiller power demand response control strategy for buildings connected to smart grid. Applied Energy, 137: 77–87.

DOI Google Scholar

Yin R, Xu P, Piette MA, et al. (2010). Study on Auto-DR and pre-cooling of commercial buildings with thermal mass in California. Energy and Buildings, 42: 967–975.

DOI Google Scholar

Yuan X, Pan Y, Yang J, et al. (2021). Study on the application of reinforcement learning in the operation optimization of HVAC system. Building Simulation, 14: 75–87.

DOI Google Scholar

Zhang F, Deb C, Lee SE, et al. (2016). Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique. Energy and Buildings, 126: 94–103.

DOI Google Scholar

Zong Y, Kullmann D, Thavlov A, et al. (2012). Application of model predictive control for active load management in a distributed power system with high wind penetration. IEEE Transactions on Smart Grid, 3: 1055–1062.

DOI Google Scholar

Electronic supplementary material

File

bs-15-3-317_ESM.pdf (831 KB)

About this article

Publication history

Acknowledgements

Publication history

Received: 31 January 2021

Revised: 28 March 2021

Accepted: 19 April 2021

Published: 30 June 2021

Issue date: March 2022

Copyright

Acknowledgements

The authors gratefully acknowledge the support of this research by the National Natural Science Foundation of China (No. 51908365, No. 71772125) and the Philosophical and Social Science Program of Guangdong Province (GD18YGL07).