Journal Home > Volume 14 , Issue 1
Building Simulation 2021, 14(1): 219-235 https://doi.org/10.1007/s12273-020-0638-x
Research Article | Issue | Published: 13 May 2020

A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development

Show Author's Information Yuan Jin1,  Da Yan1( ),  Xingxing Zhang2,  Jingjing An1,  Mengjie Han2
School of Architecture, Tsinghua University, Beijing 100084, China
School of Industrial Technology and Business Studies, Dalarna University, Falun 79188, Sweden
Keywords:
data-driven, model predictive control, occupant behavior, lighting system
Cite this article:
Jin Y, Yan D, Zhang X, et al. A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development. Building Simulation, 2021, 14(1): 219-235. https://doi.org/10.1007/s12273-020-0638-x
Download citation
EndNote(RIS)
BibTeX

585

Views

23

Downloads

Citations

32

Crossref

N/A

WoS

38

Scopus

9

CSCD

Abstract Full text About this article

The lighting system accounts for 8% of the total electricity consumption in commercial buildings in the United States and 12% of the total electricity consumption in public buildings globally. This consumption share can be effectively reduced using the demand-response control. The traditional lighting system control method commonly depends on the real-time occupancy data collected using the passive infrared (PIR) sensor. However, the detection inaccuracy of the PIR sensor usually results in false-offs. To diminish the false-error frequency, the existing lighting system control simply deploys a delayed reaction period (e.g., 5 to 20 min), which is not sufficiently accurate for the demand-response operation. Therefore, in this research, a novel data-driven model predictive control (MPC) method that is based on the temporal sequential-based artificial neural network (TS-ANN) is proposed to overcome this challenge using an updated historical occupancy status. Using an office as case study, the proposed model is also compared with the traditional lighting system control method. In the proposed model, the occupancy data was trained to predict the occupancy pattern to improve the control. It was found that the occupancy prediction mainly correlates with the historical occupancy ratio and the time sequential feature. The simulation results indicated that the proposed method achieved higher accuracy (97.4%) and fewer false-offs (from 79.5 with traditional time delay method to 0.6 times per day) are achieved by the MPC model. The proposed TS-ANN-MPC method integrates the analysis of the occupant behavior routine into on-site control and has the potential to further enhance the control performance practice for maximum energy conservation.


menu
Abstract
Full text
Outline
About this article

A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development

Show Author's information Yuan Jin1, Da Yan1( ), Xingxing Zhang2, Jingjing An1, Mengjie Han2
School of Architecture, Tsinghua University, Beijing 100084, China
School of Industrial Technology and Business Studies, Dalarna University, Falun 79188, Sweden

Abstract

The lighting system accounts for 8% of the total electricity consumption in commercial buildings in the United States and 12% of the total electricity consumption in public buildings globally. This consumption share can be effectively reduced using the demand-response control. The traditional lighting system control method commonly depends on the real-time occupancy data collected using the passive infrared (PIR) sensor. However, the detection inaccuracy of the PIR sensor usually results in false-offs. To diminish the false-error frequency, the existing lighting system control simply deploys a delayed reaction period (e.g., 5 to 20 min), which is not sufficiently accurate for the demand-response operation. Therefore, in this research, a novel data-driven model predictive control (MPC) method that is based on the temporal sequential-based artificial neural network (TS-ANN) is proposed to overcome this challenge using an updated historical occupancy status. Using an office as case study, the proposed model is also compared with the traditional lighting system control method. In the proposed model, the occupancy data was trained to predict the occupancy pattern to improve the control. It was found that the occupancy prediction mainly correlates with the historical occupancy ratio and the time sequential feature. The simulation results indicated that the proposed method achieved higher accuracy (97.4%) and fewer false-offs (from 79.5 with traditional time delay method to 0.6 times per day) are achieved by the MPC model. The proposed TS-ANN-MPC method integrates the analysis of the occupant behavior routine into on-site control and has the potential to further enhance the control performance practice for maximum energy conservation.

Keywords: data-driven, model predictive control, occupant behavior, lighting system

References(56)

Aghemo C, Blaso L, Pellegrino A (2014). Building automation and control systems: A case study to evaluate the energy and environmental performances of a lighting control system in offices. Automation in Construction, 43: 10-22.
DOI Google Scholar
Araji MT, Darragh SP, Boyer JL (2012). Paradigm in sustainability and environmental design: lighting utilization contributing to surplus-energy office buildings. Leukos, 9: 25-45.
DOI Google Scholar
Beccali M, Bonomolo M, Lo Brano V, Ciulla G, Di Dio V, Massaro F, Favuzza S (2019). Energy saving and user satisfaction for a new advanced public lighting system. Energy Conversion and Management, 195: 943-957.
DOI Google Scholar
Benya J (2001). Advanced lighting guidelines. New Buildings Institute.
Bottou L (2010). Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010, pp. 177-186.
DOI
Bourgeois D, Reinhart C, MacDonald I (2006). Adding advanced behavioural models in whole building energy simulation: a study on the total energy impact of manual and automated lighting control. Energy and Buildings, 38: 814-823.
DOI Google Scholar
Buckley A, LeNir A (1985). Algorithm 630: BBVSCG-a variable-storage algorithm for function minimization. ACM Transactions on Mathematical Software (TOMS), 11: 103-119.
DOI Google Scholar
Chen Y, Hong T, Luo X (2018). An agent-based stochastic Occupancy Simulator. Building Simulation, 11: 37-49.
DOI Google Scholar
Chenaru O, Hanganu CE, Popescu D, Ichim L (2019). Virtual sensor for behavior pattern identification in a smart home application In: Proceedings of the 8th International Conference on Systems and Control (ICSC), Marrakesh, Morocco.
DOI
Chew I, Karunatilaka D, Tan CP, Kalavally V (2017). Smart lighting: The way forward? Reviewing the past to shape the future. Energy and Buildings, 149: 180-191.
DOI Google Scholar
de Bakker C, Aries M, Kort H, Rosemann A (2017). Occupancy-based lighting control in open-plan office spaces: a state-of-the-art review. Building and Environment, 112: 308-321.
DOI Google Scholar
Dubois M-C, Blomsterberg Å (2011). Energy saving potential and strategies for electric lighting in future North European, low energy office buildings: A literature review. Energy and Buildings, 43: 2572-2582.
DOI Google Scholar
EIA (2019). Annual Energy Outlook 2019. Available at https://www.eia.gov/outlooks/aeo/index.php
Fawcett T (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27: 861-874.
DOI Google Scholar
Galasiu AD, Newsham GR, Suvagau C, Sander DM (2007). Energy saving lighting control systems for open-plan offices: A field study. Leukos, 4: 7-29.
DOI Google Scholar
Gardner M, Dorling S (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environment, 32: 2627-2636.
DOI Google Scholar
Goyal S, Ingley HA, Barooah P (2013). Occupancy-based zone-climate control for energy-efficient buildings: Complexity vs. performance. Applied Energy, 106: 209-221.
DOI Google Scholar
Guo X (2007). FOccupancy sensor networks for improved lighting system controlF. PhD Thesis, The University of Nebraska-Lincoln, USA.
Guo X, Tiller DK, Henze GP, Waters CE (2010). The performance of occupancy-based lighting control systems: A review. Lighting Research & Technology, 42: 415-431.
DOI Google Scholar
Hong T, Yan D, D'Oca S, Chen CF (2017). Ten questions concerning occupant behavior in buildings: The big picture. Building and Environment, 114: 518-530.
DOI Google Scholar
Hong T, Chen Y, Belafi Z, D’Oca S (2018). Occupant behavior models: A critical review of implementation and representation approaches in building performance simulation programs. Building Simulation, 11: 1-14.
DOI Google Scholar
Hunter JD (2007). Matplotlib: A 2D graphics environment. Computing in Science & Engineering, 9: 90-95.
DOI Google Scholar
IEA (2017a). Energy Efficiency 2017. International Energy Agency. Available at https://www.iea.org/efficiency2017/.
IEA (2017b). Energy Technology Perspectives 2017. International Energy Agency.
Jain AK, Mao J, Mohiuddin KM (1996). Artificial neural networks: A tutorial. Computer, 29: 31-44.
DOI Google Scholar
Kim SH, Moon HJ (2018). Case study of an advanced integrated comfort control algorithm with cooling, ventilation, and humidification systems based on occupancy status. Building and Environment, 133: 246-264.
DOI Google Scholar
Kim S, Kang S, Ryu KR, Song G (2019). Real-time occupancy prediction in a large exhibition hall using deep learning approach. Energy and Buildings, 199: 216-222.
DOI Google Scholar
Kingma D, Ba J (2015). Adam: A method for stochastic optimization. In: Proceedings of the 3rd International Conference for Learning Representations, San Diego, USA.
Kumar R (2017). Occupancy Sensor with Improved Functionality. In: Google Patents.
Kwok SSK, Lee EWM (2011). A study of the importance of occupancy to building cooling load in prediction by intelligent approach. Energy Conversion and Management, 52: 2555-2564.
DOI Google Scholar
Le QV, Ngiam J, Coates A, Lahiri A, Prochnow B, Ng AY (2011). On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning, Bellevue, WA, USA.
Li Z, Jiang Y (2006). Investigation methods of air conditioning energy consumption in residential buildings in summer. Journal of HV&AC, 36(9): 35-37. (in Chinese)
Google Scholar
Liu DC, Nocedal J (1989). On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45: 503-528.
DOI Google Scholar
Magno M, Polonelli T, Benini L, Popovici E (2015). A low cost, highly scalable wireless sensor network solution to achieve smart LED light control for green buildings. IEEE Sensors Journal, 15: 2963-2973.
DOI Google Scholar
Mandil C (2006). Light’s labour’s lost: Policies for energy-efficient lighting. Energy World, 343: 14-15.
Google Scholar
Maniccia D, Tweed A, Bierman A, Von Neida B (2001). The effects of changing occupancy sensor time-out setting on energy savings, lamp cycling and maintenance costs. Journal of the Illuminating Engineering Society, 30: 97-110.
DOI Google Scholar
Manzoor F, Linton D, Loughlin M (2012). Occupancy monitoring using passive rfid technology for efficient building lighting control. In: Proceedings of the 4th International EURASIP Workshop on RFID Technology, Torino, Italy.
DOI
Mirakhorli A, Dong B (2016). Occupancy behavior based model predictive control for building indoor climate—A critical review. Energy and Buildings, 129: 499-513.
DOI Google Scholar
Nagy Z, Yong FY, Frei M, Schlueter A (2015). Occupant centered lighting control for comfort and energy efficient building operation. Energy and Buildings, 94: 100-108.
DOI Google Scholar
Oldewurtel F, Sturzenegger D, Morari M (2013). Importance of occupancy information for building climate control. Applied Energy, 101: 521-532.
DOI Google Scholar
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12: 2825-2830.
Google Scholar
Peng Y, Rysanek A, Nagy Z, Schlüter A (2018). Using machine learning techniques for occupancy-prediction-based cooling control in office buildings. Applied Energy, 211: 1343-1358.
DOI Google Scholar
Pham GN, Nguyen PH, Kwon KR (2019). Brief paper: Combining object detection and hand gesture recognition for automatic lighting system control. Journal of Multimedia Information System, 6: 329-332.
DOI Google Scholar
Power DM (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37-63.
Google Scholar
Qiu S, Feng F, Li Z, Yang G, Xu P, Li Z (2019). Data mining based framework to identify rule based operation strategies for buildings with power metering system. Building Simulation, 12: 195-205.
DOI Google Scholar
Richman EE, Dittmer AL, Keller JM (1996). Field analysis of occupancy sensor operation: parameters affecting lighting energy savings. Journal of the Illuminating Engineering Society, 25: 83-92.
DOI Google Scholar
Rubinstein F, Enscoe A (2010). Saving energy with highly-controlled lighting in an open-plan office. Leukos, 7: 21-36.
DOI Google Scholar
Rummelhart DE (1986). Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL, Parallel Distributed Processing: I. Foundations. Cambridge, MA, USA: MIT Press. 318-362.
DOI
Schalkoff R (1992). Pattern Classification: Statistical, Structural and Neural Approaches. New York: John Wiley & Sons.
Tabak V, de Vries B (2010). Methods for the prediction of intermediate activities by office occupants. Building and Environment, 45: 1366-1372.
DOI Google Scholar
Tetlow RM, Beaman CP, Elmualim AA, Couling K (2014). Simple prompts reduce inadvertent energy consumption from lighting in office buildings. Building and Environment, 81: 234-242.
DOI Google Scholar
Wanjiru EM, Zhang L, Xia X (2016). Model predictive control strategy of energy-water management in urban households. Applied Energy, 179: 821-831.
DOI Google Scholar
Yan D, O’Brien W, Hong T, Feng X, Burak Gunay H, Tahmasebi F, Mahdavi A (2015). Occupant behavior modeling for building performance simulation: Current state and future challenges. Energy and Buildings, 107: 264-278.
DOI Google Scholar
Yan D, Hong T, Dong B, Mahdavi A, D’Oca S, Gaetani I, Feng X (2017). IEA EBC Annex 66: Definition and simulation of occupant behavior in buildings. Energy and Buildings, 156: 258-270.
DOI Google Scholar
Yin C, Dadras S, Huang X, Mei J, Malek H, Cheng Y (2017). Energy- saving control strategy for lighting system based on multivariate extremum seeking with Newton algorithm. Energy Conversion and Management, 142: 504-522.
DOI Google Scholar
Zhou X, Yan D, Hong T, Ren X (2015). Data analysis and stochastic modeling of lighting energy use in large office buildings in China. Energy and Buildings, 86: 275-287.
DOI Google Scholar
Publication history
Copyright
Acknowledgements

Publication history

Received: 18 September 2019
Accepted: 26 March 2020
Published: 13 May 2020
Issue date: February 2021

Copyright

© Tsinghua University Press and Springer-Verlag GmbH Germany, part of Springer Nature 2020

Acknowledgements

This study was supported by the National Natural Science Foundation of China (No. 51778321): Research on the quantitative description and simulation methodology of occupant behavior in buildings; the Innovative Research Groups of the National Natural Science Foundation of China (No. 51521005); also the Tsinghua University tutor research fund.

Return