research-article

Data-Driven Model Predictive Control with Regression Trees—An Application to Building Energy Management

Authors:

Francesco Smarra,

Rahul MangharamAuthors Info & Claims

ACM Transactions on Cyber-Physical Systems, Volume 2, Issue 1

Article No.: 4, Pages 1 - 21

https://doi.org/10.1145/3127023

Published: 22 January 2018 Publication History

Abstract

Model Predictive Control (MPC) plays an important role in optimizing operations of complex cyber-physical systems because of its ability to forecast system’s behavior and act under system level constraints. However, MPC requires reasonably accurate underlying models of the system. In many applications, such as building control for energy management, Demand Response, or peak power reduction, obtaining a high-fidelity physics-based model is cost and time prohibitive, thus limiting the widespread adoption of MPC. To this end, we propose a data-driven control algorithm for MPC that relies only on the historical data. We use multi-output regression trees to represent the system’s dynamics over multiple future time steps and formulate a finite receding horizon control problem that can be solved in real-time in closed-loop with the physical plant. We apply this algorithm to peak power reduction in buildings to optimally trade-off peak power reduction against thermal comfort without having to learn white/grey box models of the systems dynamics.

References

[1]

Madhur Behl, Achin Jain, and Rahul Mangharam. 2016. Data-driven modeling, control and tools for cyber-physical energy systems. In Proceedings of the 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS’16). IEEE, 1--10.

Digital Library

[2]

Madhur Behl, Francesco Smarra, and Rahul Mangharam. 2016. DR-advisor: A data-driven demand response recommender system. Appl. Energy 170 (2016), 30--46. 0306-2619

[3]

Alberto Bemporad, Manfred Morari, Vivek Dua, and Efstratios N. Pistikopoulos. 2002. The explicit linear quadratic regulator for constrained systems. Automatica 38, 1 (2002), 3--20.

Digital Library

[4]

Leo Breiman, Jerome Friedman, Charles J. Stone, and Richard A. Olshen. 1984. Classification and Regression Trees. CRC Press.

[5]

L. Cavagnari, Lalo Magni, and Riccardo Scattolini. 1999. Neural network implementation of nonlinear receding-horizon control. Neural Comput. Appl. 8, 1 (1999), 86--92.

[6]

G. T. Costanzo, S. Iacovella, F. Ruelens, T. Leurs, and B. J. Claessens. 2016. Experimental analysis of data-driven control for a building heating system. Sustain. Energy Grids Netw. 6 (2016), 81--90.

[7]

Drury B. Crawley, Linda K. Lawrie, et al. 2001. EnergyPlus: Creating a new-generation building energy simulation program. Energy and Buildings 33, 4 (2001), 319--331.

[8]

Michael Deru, Kristin Field, Daniel Studer, Kyle Benne, Brent Griffith, Paul Torcellini, Bing Liu, Mark Halverson, Dave Winiarski, Michael Rosenberg, et al. 2011. U.S. Department of Energy commercial reference building models of the national building stock.

[9]

Richard E. Edwards, Joshua New, and Lynne E. Parker. 2012. Predicting future hourly residential electrical consumption: A machine-learning case study. Energy Build. 49 (2012), 591--603.

[10]

Federal Energy Regulatory Commission et al. 2012. Assessment of demand response and advanced metering.

[11]

P. M. Ferreira, A. E. Ruano, S. Silva, and E. Z. E. Conceicao. 2012. Neural networks-based predictive control for thermal comfort and energy savings in public buildings. Energy Build. 55 (2012), 238--251.

[12]

NOAA National Centers for Environmental Information. State of the Climate: Global Analysis for August 2015. Retrieved from http://www.ncdc.noaa.gov/sotc/global/201508.

[13]

Trevor Hastie, Robert Tibshirani, Jerome Friedman, and James Franklin. 2005. The elements of statistical learning: Data mining, inference and prediction. Math. Intell. 27, 2 (2005), 83--85.

[14]

Kyoung ho Lee and James E. Braun. 2008. Development of methods for determining demand-limiting setpoint trajectories in buildings using short-term measurements. Build. Environ. 43, 10 (2008).

[15]

David G. Holmberg, Girish Ghatikar, Edward Koch, and Jim Boch. 2012. OpenADR advances. ASHRAE J. 54 (11/2012 2012).

[16]

Z.-S. Hou and Z. Wang. 2013. From model-based control to data-driven control: Survey, classification and perspective. Info. Sci. 235 (2013), 3--35.

Digital Library

[17]

Achin Jain, Madhur Behl, and Rahul Mangharam. 2016. Data predictive control for peak power reduction. In Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys).

Digital Library

[18]

Achin Jain, Madhur Behl, and Rahul Mangharam. 2017. Data predictive control for building energy management. In Proceedings of the 2017 American Control Conference. IEEE.

[19]

Achin Jain, Francesco Smarra, and Rahul Mangharam. 2017. Data predictive control using regression trees and ensemble learning. In Proceedings of the 2017 Conference on Decision and Control. IEEE.

[20]

S. Kiliccote, M. A. Piette, and D. Hansen. 2006. Advanced controls and communications for demand response and energy efficiency in commercial buildings. In Proceedings of the 2nd Carnegie Mellon Conference in Electronic Power Systems.

[21]

Andrew Kusiak, Zhe Song, and Haiyang Zheng. 2009. Anticipatory control of wind turbines with data-driven predictive models. IEEE Trans. Energy Conv. 24, 3 (2009), 766--774.

[22]

PJM Interconnection and Michael J. Kormos. 2014. PJM response to consumer reports on 2014 winter pricing. Retrieved from http://www.pjm.com/-/media/documents/reports/20140919-pjm-response-to-consumer-reports-on-2014-winter-pricing.ashx?la=en.

[23]

Navigant Research. 2015. Demand response for commercial 8 industrial markets market players and dynamics, key technologies, competitive overview, and global market forecasts. Retrieved from https://www.prnewswire.com/news-releases/demand-response-for-commercial--industrial-markets--market-players-and-dynamics-key-technologies-competitive-overview-and-global-market-forecasts---reportlinker-review-300151285.html.

[24]

F. Oldewurtel et al. 2013. Towards a standardized building assessment for demand response. In Proceedings of the IEEE Conference on Decision and Control.

[25]

Alberto Nai Oleari, Jose Ramon D. Frejo, Eduardo F. Camacho, and Antonella Ferrara. 2015. A model predictive control scheme for freeway traffic systems based on the classification and regression trees methodology. In Proceedings of the, 2015 European Control Conference (ECC’15). IEEE, 3459--3464.

[26]

PJM Interconnection. 2014. 2014 demand response operations markets activity report. Retrieved from https://so-ups.ru/fileadmin/files/company/markets/dr/dr_pjm/dr_pjm_otchet_2014.pdf.

[27]

Joshua New, Jibonananda Sanyal, Mahabir Bhandari, and Som Shrestha. 2012. Autotune e+ building energy models. Proceedings of the 5th National SimBuild of IBPSA-USA.

[28]

Brian D. Ripley. 2007. Pattern Recognition and Neural Networks. Cambridge University Press.

Digital Library

[29]

D. Sturzenegger, D. Gyalistras, M. Morari, and R. S. Smith. 2015. Model predictive climate control of a swiss office building: Implementation, results, and cost-benefit analysis. IEEE Trans. Control Syst. Technol. PP, 99 (2015), 1--1.

[30]

A. Vaghefi, M. A. Jafari, E. Bisse, Y. Lu, and J. Brouwer. 2014. Modeling and forecasting of cooling and electricity load demand. Appl. Energy 136 (2014), 186--196.

[31]

Peng Xu, Philip Haves, Mary Ann Piette, and James Braun. 2004. Peak demand reduction from pre-cooling with zone temperature reset in an office building. Berkeley National Laboratory (2004).

[32]

Wei Yin, Yogesh Simmhan, and Viktor K. Prasanna. 2012. Scalable regression tree learning on hadoop using OpenPlanet. In Proceedings of 3rd International Workshop on MapReduce and Its Applications Date. ACM, 57--64.

Digital Library

[33]

Eva Zavcekova, Zdenvek Vavna, and Jivri Cigler. 2014. Towards the real-life implementation of MPC for an office building-identification issues. Appl. Energy 135 (2014), 53--62.

Cited By

Tungom CNiu BWang H(2025)SWAPP: Swarm precision policy optimization with dynamic action bound adjustment for energy management in smart citiesApplied Energy10.1016/j.apenergy.2024.124410377(124410)Online publication date: Jan-2025
https://doi.org/10.1016/j.apenergy.2024.124410
Rani GPriya P(2024)Data-Driven Model Predictive Control for Hybrid Charging Stations Using Ensemble LearningIEEE Transactions on Artificial Intelligence10.1109/TAI.2024.34049135:10(5304-5313)Online publication date: Oct-2024
https://doi.org/10.1109/TAI.2024.3404913
de Rubeis TSmarra FFranchi FDi Battista DD’Innocenzo AAmbrosini DDe Berardinis P(2024)A pilot project for energy retrofit of educational buildings - The engineering campus of the University of L’AquilaE3S Web of Conferences10.1051/e3sconf/202452302006523(02006)Online publication date: 7-May-2024
https://doi.org/10.1051/e3sconf/202452302006
Show More Cited By

Index Terms

Data-Driven Model Predictive Control with Regression Trees—An Application to Building Energy Management
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Classification and regression trees

Recommendations

Data Predictive Control for Peak Power Reduction
BuildSys '16: Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments

Decisions on how best to optimize today's energy systems operations are becoming ever so complex and conflicting such that model-based predictive control algorithms must play a key role. However, learning dynamical models of energy consuming systems ...
Predictive Control Based on Fuzzy Supervisor for PWARX Hybrid Model
Abstract
In this paper, the problem of hybrid model predictive control (HMPC) strategy based on fuzzy supervisor for piecewise autoregressive with exogenous input (PWARX) models is addressed. We first represent the nonlinear behavior of the system with a ...
Building simulation weather forecast files for predictive control strategies
SimAUD '13: Proceedings of the Symposium on Simulation for Architecture & Urban Design

Model-Based Predictive Control (MPC) has received significant attention in recent years as a tool for load management in buildings. MPC is based on predicting the response of a system based on knowledge of future inputs, such as weather and occupancy. ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Cyber-Physical Systems

ACM Transactions on Cyber-Physical Systems Volume 2, Issue 1

Special Issue on ICCPS 2016

January 2018

140 pages

ISSN:2378-962X

EISSN:2378-9638

DOI:10.1145/3174275

Editor:
Tei-Wei Kuo
National Taiwan University, and Academia Sinica, Taiwan

Issue’s Table of Contents

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Journal Family

ACM Journals for the Design of Smart and Connected Systems

Publication History

Published: 22 January 2018

Accepted: 01 July 2017

Revised: 01 April 2017

Received: 01 July 2016

Published in TCPS Volume 2, Issue 1

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Funding Sources

ItalianGovernment under Cipe
INnovating City Planning through Information and Communication Technologies (INCIPICT)

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

48
Total Citations
View Citations
846
Total Downloads

Downloads (Last 12 months)58
Downloads (Last 6 weeks)6

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Tungom CNiu BWang H(2025)SWAPP: Swarm precision policy optimization with dynamic action bound adjustment for energy management in smart citiesApplied Energy10.1016/j.apenergy.2024.124410377(124410)Online publication date: Jan-2025
https://doi.org/10.1016/j.apenergy.2024.124410
Rani GPriya P(2024)Data-Driven Model Predictive Control for Hybrid Charging Stations Using Ensemble LearningIEEE Transactions on Artificial Intelligence10.1109/TAI.2024.34049135:10(5304-5313)Online publication date: Oct-2024
https://doi.org/10.1109/TAI.2024.3404913
de Rubeis TSmarra FFranchi FDi Battista DD’Innocenzo AAmbrosini DDe Berardinis P(2024)A pilot project for energy retrofit of educational buildings - The engineering campus of the University of L’AquilaE3S Web of Conferences10.1051/e3sconf/202452302006523(02006)Online publication date: 7-May-2024
https://doi.org/10.1051/e3sconf/202452302006
Tungom CWang HBeata KNiu B(2024)SWOAM: Swarm optimized agents for energy management in grid-interactive connected buildingsEnergy10.1016/j.energy.2024.131399301(131399)Online publication date: Aug-2024
https://doi.org/10.1016/j.energy.2024.131399
Agarwal A(2024)FAlloc: A Fair Power Limit Allocation-Based Approach to Implement BrownoutJournal of Control, Automation and Electrical Systems10.1007/s40313-024-01077-x35:2(361-375)Online publication date: 7-Mar-2024
https://doi.org/10.1007/s40313-024-01077-x
Chen CHong ILi Y(2024)Decision Trees and Multi-objective Optimization to Calibrate Process ParametersFlexible Automation and Intelligent Manufacturing: Manufacturing Innovation and Preparedness for the Changing World Order10.1007/978-3-031-74485-3_52(476-483)Online publication date: 13-Dec-2024
https://doi.org/10.1007/978-3-031-74485-3_52
Salatiello AWang YWichern GKoike-Akino TOhta YKaneko YLaughman CChakrabarty A(2023)Synthesizing Building Operation Data with Generative Models: VAEs, GANs, or Something In Between?Companion Proceedings of the 14th ACM International Conference on Future Energy Systems10.1145/3599733.3600260(125-133)Online publication date: 20-Jun-2023
https://dl.acm.org/doi/10.1145/3599733.3600260
Tjen JIskandar RWillay TDarmanto T(2023)Electric Power Consumption Prediction from Scarce Dataset with Entropy-Based Subset Selection Regression Tree (e-ss RT)2023 14th International Conference on Information & Communication Technology and System (ICTS)10.1109/ICTS58770.2023.10330843(182-187)Online publication date: 4-Oct-2023
https://doi.org/10.1109/ICTS58770.2023.10330843
Willay TTjen JKartini P(2023)Understanding Human Daily Activity Pattern Inside a Structure Via Power Consumption Modeling2023 14th International Conference on Information & Communication Technology and System (ICTS)10.1109/ICTS58770.2023.10330827(211-216)Online publication date: 4-Oct-2023
https://doi.org/10.1109/ICTS58770.2023.10330827
Deng ZWang XJiang ZZhou NGe HDong B(2023)Evaluation of deploying data-driven predictive controls in buildings on a large scale for greenhouse gas emission reductionEnergy10.1016/j.energy.2023.126934270(126934)Online publication date: May-2023
https://doi.org/10.1016/j.energy.2023.126934
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Issue’s Table of Contents