Model-IQ: Uncertainty propagation from sensing to modeling and control in buildings

Behl, Madhur; Nghiem, Truong X.; Mangharam, Rahul

doi:10.1109/iccps.2014.6843707

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the associated control strategy is indeed the optimal strategy for the plant. In reality the quality of data, and modeling errors also affect the performance of the MPC controller [2]. Qualitatively, the DPC-En control input is not much different from that of MPC.…”

Section: B Resultsmentioning

confidence: 98%

Data Predictive Control for building energy management

Jain

Behl

Mangharam

2017

2017 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

Decisions on how to best optimize energy systems operations are becoming ever so complex and conflicting, that model-based predictive control (MPC) algorithms must play an important role. However, a key factor prohibiting the widespread adoption of MPC in buildings, is the cost, time, and effort associated with learning first-principles based dynamical models of the underlying physical system. This paper introduces an alternative approach for implementing finite-time receding horizon control using control-oriented data-driven models. We call this approach Data Predictive Control (DPC). Specifically, by utilizing separation of variables, two novel algorithms for implementing DPC using a single regression tree and with regression trees ensembles (random forest) are presented. The data predictive controller enables the building operator to trade off energy consumption against thermal comfort without having to learn white/grey box models of the systems dynamics. We present a comprehensive numerical study which compares the performance of DPC with an MPC based energy management strategy, using a single zone building model. Our results demonstrate that performance of DPC is comparable to an MPC controller, with only 3.8% additional cost in terms of optimal objective function and within 95% in terms of R2 score, thereby making it an alluring alternative to MPC, whenever the associated cost of learning the model is high. Abstract-Decisions on how to best optimize energy systems operations are becoming ever so complex and conflicting, that model-based predictive control (MPC) algorithms must play an important role. However, a key factor prohibiting the widespread adoption of MPC in buildings, is the cost, time, and effort associated with learning first-principles based dynamical models of the underlying physical system. This paper introduces an alternative approach for implementing finite-time receding horizon control using control-oriented data-driven models. We call this approach Data Predictive Control (DPC). Specifically, by utilizing separation of variables, two novel algorithms for implementing DPC using a single regression tree and with regression trees ensembles (random forest) are presented. The data predictive controller enables the building operator to trade off energy consumption against thermal comfort without having to learn white/grey box models of the systems dynamics. We present a comprehensive numerical study which compares the performance of DPC with an MPC based energy management strategy, using a single zone building model. Our simulations demonstrate that performance of DPC is comparable to an MPC controller, with only 3.8% additional cost in terms of optimal objective function and within 95% in terms of R 2 score, thereby making it an alluring alternative to MPC, whenever the associated cost of learning the model is high.

show abstract

Section: B Resultsmentioning

confidence: 98%

Data Predictive Control for building energy management

Jain

Behl

Mangharam

2017

2017 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the toolbox also has the capability to relate model accuracy to control performance for a complete end-to-end treatment of uncertainty propagation. This is based on our previous work [3], in which we present the method for establishing the relationship between model accuracy and the performance of a model predictive controller. We showed (Figure ?…”

Section: Resultsmentioning

confidence: 99%

“…In [3], we presented a technique to quantify the effect of data uncertainty on building inverse model accuracy and control performance. However, that work only considers uncertainty in the form of fixed biases in sensor data.…”

Section: Introductionmentioning

confidence: 99%

IMpACT: Inverse model accuracy and control performance toolbox for buildings

Behl

Nghiem

Mangharam

2014

2014 IEEE International Conference on Automation Science and Engineering (CASE)

Self Cite

View full text Add to dashboard Cite

Uncertainty affects all aspects of building performance: from the identification of models, through the implementation of model-based control, to the operation of the deployed systems. Learning models of buildings from sensor data has a fundamental property that the model can only be as accurate and reliable as the data on which it was trained. For small and medium size buildings, a low-cost method for model capture is necessary to take advantage of optimal model-based supervisory control schemes. We present IMpACT, a methodology and a toolbox for analysis of uncertainty propagation for building inverse modeling and controls. Given a plant model and real input data, IMpACT automatically evaluates the effect of the uncertainty propagation from sensor data to model accuracy and control performance. We also present a statistical method to quantify the bias in the sensor measurement and to determine near optimal sensor placement and density for accurate signal measurements. In our previous work, we considered the end-to-end propagation of uncertainty in the form of fixed bias in the sensor data. In this paper, we extend the method to work with random errors in the sensor data, which is more realistic. Using a real building test-bed, we show how performing an uncertainty analysis can reveal trends about inverse model accuracy and control performance, which can be used to make informed decisions about sensor requirements and data accuracy.

show abstract

“…The same aspect was treated in a study presented in [6], which underlines that the application of HVAC control rules based on thermal comfort evaluation works well in air-conditioned spaces and could bring good energy saving potential. While [7] showed that a real bias on air temperature measure due to sensors density and placement on a zone can influence the model predictive control accuracy; they also observed that an accurate building inverse model can result in a model predictive control cost reduction of more than 13%. Revel and Arnesano [3] underlined as a detailed evaluation of the comfort level inside sport facilities spaces required a calibrated comfort model, where all the variables have to be measured inside the relative range of accuracy.…”

Section: Introductionmentioning

confidence: 95%