Optimal control strategies of eight parallel heat pumps using Gaussian process emulator

Abstract

This study describes the development of the optimal control strategies of eight parallel heat pumps in an existing building. The building consists of seven floors above ground and two floors underground with a total floor area of 22,440 m². The chilled water generated by each of the eight parallel heat pumps runs through a common primary pipe to multiple air-handling units in the building. Because only one flowmeter and two thermometers (entering and exiting) are installed in the primary pipe, the heat removal rate and efficiency of each heat pump are unknown. The existing control of the heat pumps is as follows: if the chilled water return temperature in the primary pipe becomes greater than a predetermined temperature, the controller increases the number of operating heat pumps. The heat removal rate and efficiency of each heat pump were first identified using a Gaussian process (GP) machine-learning algorithm to develop the optimal control strategy of the eight heat pumps. Two GP models, one for estimating the heat removal rate and the other for estimating the coefficient of performance (COP), were developed based on the measured data for 27 days in July at the sampling time of 15 min. After developing the GP models, the authors applied a COP-based sequencing control strategy to the eight parallel heat pumps. The new optimal control strategy is to switch on the heat pumps in order from highest to lowest COP. Compared with the existing control logic, the new optimal control can reduce energy consumption by 20.9%.

Keywords:

• heat pump
• optimal control
• Gaussian process
• machine learning
• COP based sequencing control

Acknowledgements

This work was sponsored by the SK Telecom Co. research grant program. This research was supported by Institute of Construction and Environmental Engineering at Seoul National University. The authors wish to express their gratitude for the support. The Institute of Engineering Research at Seoul National University provided research facilities for this work.

Nomenclature

ANN	=	artificial neural network
$C_{\text{w}}$	=	specific heat of water (J/kg·°C)
COP	=	coefficient of performance
CSC	=	COP-based sequencing control
EKF	=	extended Kalman filter
$\text{Elec\_su}{\mathrm{m}}_T$	=	total electric power of operating heat pumps at time sequence of $T$ (W)
$\text{Ele}{\text{c}}_{\text{HP\# }}$	=	electric power of each heat pump (W)
GP	=	Gaussian process
HP	=	heat pump
$\text{HR\_su}{\mathrm{m}}_T$	=	total heat removal rate of operating heat pumps at time sequence of $T$ (W)
$\text{H}{\text{R}}_{\text{HP\# }}$	=	heat removal rate of each heat pump (W)
KF	=	Kalman filter
$\dot{m}$	=	chilled water flow rate (kg/s)
MCMC	=	Markov chain Monte Carlo
PF	=	particle filter
Q	=	total heat removal rate (W)
R2	=	coefficient of determination
RTSC	=	return-temperature-based sequencing control
RMSE	=	root mean square error
$S_{T,H}$	=	on/off status of heat pump where $H$ is the index of each heat pump (from 1 to 8) at time sequence of $T$
SE	=	squared exponential kernel
SVM	=	support vector machine
$T_{\text{r}}$	=	chilled water return temperature
$T_{\text{s}}$	=	chilled water supply temperature
TDB	=	technical data book

ORCID

Sung Ho Park http://orcid.org/0000-0002-2347-3631

Additional information

Funding

This work was supported by the SK Telecom; Seoul National University.