Experimental data-driven model predictive control of a hospital HVAC system during regular use

Maddalena, Emilio T.; Müller, Silvio A.; Santos, Rafael M. dos; Salzmann, Christophe; Jones, Colin N.

doi:10.1016/j.enbuild.2022.112316

Cited by 21 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most authors use MPC for controlling HVAC systems, e.g. Maddalena et al [14], Hu et al [15], Pedersen et al [16], Blum et al [17], Mork et al [20], and Zwickel et al [22]. While model-based approaches generally yield adequate results, they suffer from execution times and require modeling the thermal behavior of a building which is a complex task.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Occupant-Oriented Demand Response with Room-Individual Building Control

Frahm¹,

Zwickel²,

Maaß³

et al. 2023

Preprint

View full text Add to dashboard Cite

In future energy systems with high shares of renewable energy sources, the electricity demand of buildings has to react to the fluctuating electricity generation in view of stability. As buildings consume one-third of global energy and almost half of this energy accounts for Heating, Ventilation, and Air Conditioning (HVAC) systems, HVAC are suitable for shifting their electricity consumption in time. To this end, intelligent control strategies are necessary as the conventional control of HVAC is not optimized for the actual demand of occupants and the current situation in the electricity grid. In this paper, we present the novel multi-zone controller Price Storage Control (PSC) that not only considers room-individual Occupants' Thermal Satisfaction (OTS), but also the available energy storage, and energy prices. The main feature of PSC is that it does not need a building model or forecasts of future demands to derive the control actions for multiple rooms in a building. For comparison, we use an ideal, error-free Model Predictive Control (MPC) and a conventional hysteresis-based two-point control as upper and lower benchmarks, respectively. We evaluate the three controllers in a multi-zone environment for cooling a building in summer and consider two different scenarios that differ in how much the permitted temperatures vary. The results show that PSC strongly outperforms the conventional control approach in both scenarios with regard to the electricity costs and OTS. It leads to 50 % costs reduction and 15 % comfort improvements while the ideal MPC achieves costs reductions of 58 % and comfort improvements of 29 %. Considering that PSC does not need any building model or forecast, as opposed to MPC, the results support the suitability of our developed control strategy for controlling HVAC systems in future energy systems.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Most studies use simulated synthetic data for defining the building model and setting up the simulation. Only Maddalena et al [14] and Michailidis et al [21] also use measured data for evaluating the OTS.…”

Section: Related Workmentioning

confidence: 99%

Occupant-Oriented Demand Response with Room-Individual Building Control

Frahm¹,

Zwickel²,

Maaß³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Like other ANNs, its objective is also to learn and map the relationships between inputs and outputs. Moreover, this network also adjusts the weights and threshold values of the system in such a way as to get the desired results with fewer errors [41].…”

Section: Figure 4 Exploratory Data Analysis Of Hvac Datasetsmentioning

confidence: 99%

Prediction of Electric Power Demand of HVACs for Operating Rooms in Case of Dynamic Set Points of Temperature: A Case Study

Ullah

Ahmad

Yasin

et al. 2022

JCBI

View full text Add to dashboard Cite

In healthcare settings, particularly in areas such as operating rooms and intensive care units, there is a need for a dynamically controlled temperature environment that can adapt to the changing needs of both patients and healthcare workers. This is due to the fact that the desired temperature can vary depending on the condition of the patient and the specific requirements of surgical and treatment procedures. To address this need, our objective is to develop a tool for predicting the electric power needed to maintain a desired temperature in these critical care areas. Previous research has employed artificial learning algorithms and mathematical equations to predict electric power for various types and sizes of buildings, with promising results. However, our study focuses specifically on critical care areas within hospitals and utilizes fluctuating temperature set-points to predict power demand using historical weather data and Building Management System (BMS) data. We employed both Multi-Layer Artificial Neural Network (ML-ANN) and Long short-term memory (LSTM) models for this purpose and found that ML-ANN outperformed LSTM. The results showed that the ML-ANN model performed better than the LSTM model, with a testing accuracy of 96% compared to 78% for the LSTM model. This indicates that the ML-ANN model was more accurate in predicting the power consumption for the desired temperature in the operating room.

show abstract

“…In one of the early works, Liu and Atkeson combined the linear quadratic regulator with unsupervised clustering (k-nearest neighbor) [7]. Other shallow learning applications include Gaussian process modeling for the safe exploration of dynamical systems [8], the optimal energy management in commercial building micro-grids [9], heating, ventilation and airconditioning (HVAC) control of a hospital surgery center [10]; Bayesian regression for safe predictive learning control [11], statistical time series modeling (ARIMA) for optimal energy management [9], random forests for HVAC systems [12] and support vector machines for milling [13]. Feed-forward neural network (NN) applications within an MPC framework can also be found in various disciplines.…”

Section: Introductionmentioning

confidence: 99%

Model Predictive Evolutionary Temperature Control via Neural-Network-Based Digital Twins

Ates,

Bicat,

Yankov

et al. 2023

Algorithms

View full text Add to dashboard Cite

In this study, we propose a population-based, data-driven intelligent controller that leverages neural-network-based digital twins for hypothesis testing. Initially, a diverse set of control laws is generated using genetic programming with the digital twin of the system, facilitating a robust response to unknown disturbances. During inference, the trained digital twin is utilized to virtually test alternative control actions for a multi-objective optimization task associated with each control action. Subsequently, the best policy is applied to the system. To evaluate the proposed model predictive control pipeline, experiments are conducted on a multi-mode heat transfer test rig. The objective is to achieve homogeneous cooling over the surface, minimizing the occurrence of hot spots and energy consumption. The measured variable vector comprises high dimensional infrared camera measurements arranged as a sequence (655,360 inputs), while the control variable includes power settings for fans responsible for convective cooling (3 outputs). Disturbances are induced by randomly altering the local heat loads. The findings reveal that by utilizing an evolutionary algorithm on measured data, a population of control laws can be effectively learned in the virtual space. This empowers the system to deliver robust performance. Significantly, the digital twin-assisted, population-based model predictive control (MPC) pipeline emerges as a superior approach compared to individual control models, especially when facing sudden and random changes in local heat loads. Leveraging the digital twin to virtually test alternative control policies leads to substantial improvements in the controller’s performance, even with limited training data.

show abstract

Experimental data-driven model predictive control of a hospital HVAC system during regular use

Cited by 21 publications

References 33 publications

Occupant-Oriented Demand Response with Room-Individual Building Control

Occupant-Oriented Demand Response with Room-Individual Building Control

Prediction of Electric Power Demand of HVACs for Operating Rooms in Case of Dynamic Set Points of Temperature: A Case Study

Model Predictive Evolutionary Temperature Control via Neural-Network-Based Digital Twins

Contact Info

Product

Resources

About