Abstract

Self-optimizing efficiency of vapor compression cycles (VCCs) involves assigning multiple decision variables simultaneously in order to minimize power consumption while maintaining safe operating conditions. Due to the modeling complexity associated with cycle dynamics (and other smart building energy systems), online self-optimization requires algorithms that can safely and efficiently explore the search space in a derivative-free and model-agnostic manner. This makes Bayesian optimization (BO) a strong candidate for self-optimization. Unfortunately, classical BO algorithms ignore the relationship between consecutive optimizer candidates, resulting in jumps in the search space that can lead to fail-safe mechanisms being triggered, or undesired transient dynamics that violate operational constraints. To this end, we propose safe local search region (LSR)-BO, a global optimization methodology that builds on the BO framework while enforcing two types of safety constraints including black-box constraints on the output and LSR constraints on the input. We provide theoretical guarantees that under standard assumptions on the performance and constraint functions, LSR-BO guarantees constraints will be satisfied at all iterations with high probability. Furthermore, in the presence of only input LSR constraints, we show the method will converge to the true (unknown) globally optimal solution. We demonstrate the potential of our proposed LSR-BO method on a high-fidelity simulation model of a commercial vapor compression system with both LSR constraints on expansion valve positions and fan speeds, in addition to other safety constraints on discharge and evaporator temperatures.

References

1.
She
,
X.
,
Cong
,
L.
,
Nie
,
B.
,
Leng
,
G.
,
Peng
,
H.
,
Chen
,
Y.
,
Zhang
,
X.
,
Wen
,
T.
,
Yang
,
H.
, and
Luo
,
Y.
,
2018
, “
Energy-Efficient and-Economic Technologies for Air Conditioning With Vapor Compression Refrigeration: A Comprehensive Review
,”
Appl. Energy
,
232
, pp.
157
186
.10.1016/j.apenergy.2018.09.067
2.
Jain
,
N.
,
Koeln
,
J. P.
,
Sundaram
,
S.
, and
Alleyne
,
A. G.
,
2014
, “
Partially Decentralized Control of Large-Scale Variable-Refrigerant-Flow Systems in Buildings
,”
J. Process Control
,
24
(
6
), pp.
798
819
.10.1016/j.jprocont.2014.02.001
3.
Wallace
,
M.
,
Das
,
B.
,
Mhaskar
,
P.
,
House
,
J.
, and
Salsbury
,
T.
,
2012
, “
Offset-Free Model Predictive Control of a Vapor Compression Cycle
,”
J. Process Control
,
22
(
7
), pp.
1374
1386
.10.1016/j.jprocont.2012.06.011
4.
Jäschke
,
J.
, and
Skogestad
,
S.
,
2011
, “
Nco Tracking and Self-Optimizing Control in the Context of Real-Time Optimization
,”
J. Process Control
,
21
(
10
), pp.
1407
1416
.10.1016/j.jprocont.2011.07.001
5.
Garriga
,
J. L.
, and
Soroush
,
M.
,
2010
, “
Model Predictive Control Tuning Methods: A Review
,”
Ind. Eng. Chem. Res.
,
49
(
8
), pp.
3505
3515
.10.1021/ie900323c
6.
Paulson
,
J. A.
, and
Mesbah
,
A.
,
2021
, “
Data-Driven Scenario Optimization for Automated Controller Tuning With Probabilistic Performance Guarantees
,”
IEEE Control Syst. Lett.
,
5
(
4
), pp.
1477
1482
.10.1109/LCSYS.2020.3040599
7.
Paulson
,
J. A.
,
Shao
,
K.
, and
Mesbah
,
A.
,
2021
, “
Probabilistically Robust Bayesian Optimization for Data-Driven Design of Arbitrary Controllers With Gaussian Process Emulators
,”
Proceedings of the Conference on Decision and Control, IEEE
, Austin, TX, Dec. 14–17, pp.
3633
3639
.10.1109/CDC45484.2021.9683046
8.
Xu
,
W.
,
Jones
,
C. N.
,
Svetozarevic
,
B.
,
Laughman
,
C. R.
, and
Chakrabarty
,
A.
,
2022
, “
VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization With Unmodeled Constraints
,” Proceedings of American Control Conference (
ACC
), IEEE, pp.
5288
5293
.https://www.researchgate.net/publication/355236811_VABO_Violation-Aware_Bayesian_Optimization_for_Closed-Loop_Control_Performance_Optimization_with_Unmodeled_Constraints
9.
Rios
,
L. M.
, and
Sahinidis
,
N. V.
,
2013
, “
Derivative-Free Optimization: A Review of Algorithms and Comparison of Software Implementations
,”
J. Global Optim.
,
56
(
3
), pp.
1247
1293
.10.1007/s10898-012-9951-y
10.
Shahriari
,
B.
,
Swersky
,
K.
,
Wang
,
Z.
,
Adams
,
R. P.
, and
De Freitas
,
N.
,
2016
, “
Taking the Human Out of the Loop: A Review of Bayesian Optimization
,”
Proc. IEEE
,
104
(
1
), pp.
148
175
.10.1109/JPROC.2015.2494218
11.
Frazier
,
P. I.
,
2018
, “
A Tutorial on Bayesian Optimization
,” arXiv Preprint
arXiv:1807.02811
.https://arxiv.org/abs/1807.02811
12.
Baheri
,
A.
, and
Vermillion
,
C.
,
2020
, “
Waypoint Optimization Using Bayesian Optimization: A Case Study in Airborne Wind Energy Systems
,”
Proceedings of the American Control Conference
,
IEEE
,
Denver, CO
, July 1–3, pp.
5102
5017
.10.23919/ACC45564.2020.9147518
13.
Pal
,
A.
,
Zhu
,
L.
,
Wang
,
Y.
, and
Zhu
,
G. G.
,
2020
, “
Multi-Objective Stochastic Bayesian Optimization for Iterative Engine Calibration
,”
Proceedings of the American Control Conference
,
IEEE
,
Denver, CO
, July 1–3, pp.
4893
4898
.10.23919/ACC45564.2020.9147983
14.
Chakrabarty
,
A.
,
Danielson
,
C.
,
Bortoff
,
S. A.
, and
Laughman
,
C. R.
,
2021
, “
Accelerating Self-Optimization Control of Refrigerant Cycles With Bayesian Optimization and Adaptive Moment Estimation
,”
Appl. Therm. Eng.
,
197
, p.
117335
.10.1016/j.applthermaleng.2021.117335
15.
Chakrabarty
,
A.
,
Burns
,
D. J.
,
Guay
,
M.
, and
Laughman
,
C. R.
,
2022
, “
Extremum Seeking Controller Tuning for Heat Pump Optimization Using Failure-Robust Bayesian Optimization
,”
J. Process Control
,
120
, pp.
86
96
.10.1016/j.jprocont.2022.11.006
16.
Duivenvoorden
,
R. R.
,
Berkenkamp
,
F.
,
Carion
,
N.
,
Krause
,
A.
, and
Schoellig
,
A. P.
,
2017
, “
Constrained Bayesian Optimization With Particle Swarms for Safe Adaptive Controller Tuning
,”
IFAC-PapersOnLine
,
50
(
1
), pp.
11800
11807
.10.1016/j.ifacol.2017.08.1991
17.
Khosravi
,
M.
,
Eichler
,
A.
,
Schmid
,
N.
,
Smith
,
R. S.
, and
Heer
,
P.
,
2019
, “
Controller Tuning by Bayesian Optimization an Application to a Heat Pump
,”
Proceedings of the European Control Conference, IEEE
, Naples, Italy, June 25–28, pp.
1467
1472
.10.23919/ECC.2019.8795801
18.
Lederer
,
A.
,
Capone
,
A.
, and
Hirche
,
S.
,
2020
, “
Parameter Optimization for Learning-Based Control of Control-Affine Systems
,”
Learning for Dynamics and Control
,
PMLR
, pp.
465
475
.https://proceedings.mlr.press/v120/lederer20a/lederer20a.pdf
19.
Khosravi
,
M.
,
Behrunani
,
V. N.
,
Myszkorowski
,
P.
,
Smith
,
R. S.
,
Rupenyan
,
A.
, and
Lygeros
,
J.
,
2022
, “
Performance-Driven Cascade Controller Tuning With Bayesian Optimization
,”
IEEE Trans. Ind. Electron.
,
69
(
1
), pp.
1032
1042
.10.1109/TIE.2021.3050356
20.
Piga
,
D.
,
Forgione
,
M.
,
Formentin
,
S.
, and
Bemporad
,
A.
,
2019
, “
Performance-Oriented Model Learning for Data-Driven MPC Design
,”
IEEE Control Syst. Lett.
,
3
(
3
), pp.
577
582
.10.1109/LCSYS.2019.2913347
21.
Sorourifar
,
F.
,
Makrygirgos
,
G.
,
Mesbah
,
A.
, and
Paulson
,
J. A.
,
2021
, “
A Data-Driven Automatic Tuning Method for MPC Under Uncertainty Using Constrained Bayesian Optimization
,”
IFAC-PapersOnLine
,
54
(
3
), pp.
243
250
.10.1016/j.ifacol.2021.08.249
22.
Lu
,
Q.
,
González
,
L. D.
,
Kumar
,
R.
, and
Zavala
,
V. M.
,
2021
, “
Bayesian Optimization With Reference Models: A Case Study in MPC for HVAC Central Plants
,”
Comput. Chem. Eng.
,
154
, p.
107491
.10.1016/j.compchemeng.2021.107491
23.
Paulson
,
J. A.
,
Makrygiorgos
,
G.
, and
Mesbah
,
A.
,
2022
, “
Adversarially Robust Bayesian Optimization for Efficient Auto-Tuning of Generic Control Structures Under Uncertainty
,”
AIChE J.
,
68
(
6
), p.
e17591
.10.1002/aic.17591
24.
Krishnamoorthy
,
D.
, and
Doyle
,
F. J.
,
2022
, “
Safe Bayesian Optimization Using Interior-Point Method - Applied to Personalized Insulin Dose Guidance
,”
IEEE Control Syst. Lett.
,
6
, pp.
2834
2839
.10.1109/LCSYS.2022.3179330
25.
Berkenkamp
,
F.
,
Krause
,
A.
, and
Schoellig
,
A. P.
,
2023
, “
Bayesian Optimization With Safety Constraints: Safe and Automatic Parameter Tuning in Robotics
,”
Mach. Learn.
,
112
(
10
), pp.
3713
3747
.10.1007/s10994-021-06019-1
26.
Paulson
,
J. A.
,
Sorouifar
,
F.
,
Laughman
,
C. R.
, and
Chakrabarty
,
A.
,
2023
, “
LSR-BO: Local Search Region Constrained Bayesian Optimization for Performance Optimization of Vapor Compression Systems
,” American Control Conference (
ACC
),
IEEE
,
San Diego, CA
, May 31–June 2, pp.
576
582
.10.23919/ACC55779.2023.10155821
27.
Williams
,
C. K.
, and
Rasmussen
,
C. E.
,
2006
,
Gaussian Processes for Machine Learning
, Vol.
2
,
MIT Press
,
Cambridge, MA
.
28.
Jones
,
D. R.
,
Schonlau
,
M.
, and
Welch
,
W. J.
,
1998
, “
Efficient Global Optimization of Expensive Black-Box Functions
,”
J. Global Optim.
,
13
(
4
), pp.
455
492
.10.1023/A:1008306431147
29.
Gardner
,
J. R.
,
Kusner
,
M. J.
,
Xu
,
Z. E.
,
Weinberger
,
K. Q.
, and
Cunningham
,
J. P.
,
2014
, “
Bayesian Optimization With Inequality Constraints
,” Proceedings of 31st International Conference on Machine Learning (
ICML
), Vol.
32
, pp.
937
945
.https://proceedings.mlr.press/v32/gardner14.pdf
30.
Nocedal
,
J.
, and
Wright
,
S. J.
,
2006
, “
Numerical Optimization
,” 2nd ed.,
Springer
,
New York
.
31.
Rasmussen
,
C. E.
, and
Williams
,
C. K. I.
,
2006
,
Gaussian Processes for Machine Learning
,
MIT Press
,
Cambridge, MA
.
32.
Gelbart
,
M. A.
,
2015
, “
Constrained Bayesian Optimization and Applications
,” Ph.D. dissertation,
Harvard University
,
Cambridge, MA
.
33.
Letham
,
B.
,
Karrer
,
B.
,
Ottoni
,
G.
, and
Bakshy
,
E.
,
2019
, “
Constrained Bayesian Optimization With Noisy Experiments
,” Preprint
arXiv:1706.07094
.https://doi.org/10.48550/arXiv.1706.07094
34.
Chowdhury
,
S. R.
, and
Gopalan
,
A.
,
2017
, “
On Kernelized Multi-Armed Bandits
,”
International Conference on Machine Learning
,
PMLR
,
Sydney, Australia
, pp.
844
853
.https://proceedings.mlr.press/v70/chowdhury17a/chowdhury17a.pdf
35.
Srinivas
,
N.
,
Krause
,
A.
,
Kakade
,
S. M.
, and
Seeger
,
M. W.
,
2012
, “
Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
,”
IEEE Trans. Inf. Theory
,
58
(
5
), pp.
3250
3265
.10.1109/TIT.2011.2182033
36.
Berkenkamp
,
F.
,
Schoellig
,
A. P.
, and
Krause
,
A.
,
2019
, “
No-Regret Bayesian Optimization With Unknown Hyperparameters
,”
J. Mach. Learn. Res.
,
20
, pp.
1
24
.https://jmlr.org/papers/v20/18-213.html
37.
Vazquez
,
E.
, and
Bect
,
J.
,
2010
, “
Convergence Properties of the Expected Improvement Algorithm With Fixed Mean and Covariance Functions
,”
J. Stat. Plann. Inference
,
140
(
11
), pp.
3088
3095
.10.1016/j.jspi.2010.04.018
38.
Bull
,
A. D.
,
2011
, “
Convergence Rates of Efficient Global Optimization Algorithms
,”
J. Mach. Learn. Res.
,
12
(
10
), pp. 2879−2904.https://www.jmlr.org/papers/v12/bull11a.html
39.
Lu
,
C.
, and
Paulson
,
J. A.
,
2022
, “
No-Regret Bayesian Optimization With Unknown Equality and Inequality Constraints Using Exact Penalty Functions
,”
IFAC-PapersOnLine
,
55
(
7
), pp.
895
902
.10.1016/j.ifacol.2022.07.558
40.
Xu
,
W.
,
Jiang
,
Y.
, and
Jones
,
C. N.
,
2022
, “
Constrained Efficient Global Optimization of Expensive Black-Box Functions
,” arXiv Preprint
arXiv:2211.00162
.https://doi.org/10.48550/arXiv.2211.00162
41.
Balandat
,
M.
,
Karrer
,
B.
,
Jiang
,
D.
,
Daulton
,
S.
,
Letham
,
B.
,
Wilson
,
A. G.
, and
Bakshy
,
E.
,
2020
, “
BoTorch: A Framework for Efficient Monte Carlo Bayesian Optimization
,”
Adv. Neural Inform. Process. Syst.
,
33
, pp.
21524
21538
.
42.
Liu
,
D. C.
, and
Nocedal
,
J.
,
1989
, “
On the Limited Memory BFGS Method for Large Scale Optimization
,”
Math. Program.
,
45
(
1–3
), pp.
503
528
.10.1007/BF01589116
43.
Paulson
,
J. A.
,
Sorouifar
,
F.
, and
Chakrabarty
,
A.
,
2022
, “
Efficient Multi-Step Lookahead Bayesian Optimization With Local Search Constraints
,”
Proceedings of the Conference on Decision and Control, IEEE
, Cancun, Mexico, Dec. 6–9, pp.
123
129
.10.1109/CDC51059.2022.9992943
44.
Eriksson
,
D.
,
Pearce
,
M.
,
Gardner
,
J.
,
Turner
,
R. D.
, and
Poloczek
,
M.
,
2019
, “
Scalable Global Optimization Via Local Bayesian Optimization
,”
Advances in Neural Information Processing Systems
, pp.
5497
5508
.
45.
Modelica Association
,
2017
, “
Modelica Specification, Version 3.4
.”
46.
Dassault Systemes
,
2019
, “
Dymola 2020
.”
47.
Modelica Association
,
2019
, “
Functional Mockup Interface for Model Exchange and Co-Simulation, Version 2.0.1
.”
You do not currently have access to this content.