Artificial intelligence (AI) policy: ASHRAE prohibits the entry of content from any ASHRAE publication or related ASHRAE intellectual property (IP) into any AI tool, including but not limited to ChatGPT. Additionally, creating derivative works of ASHRAE IP using AI is also prohibited without express written permission from ASHRAE.

Close
logoShaping Tomorrow's Built Environment Today

Determining VRF Control Actions Using an Integrated Controls System

Determining VRF Control Actions Using an Integrated Controls System

From ASHRAE Journal Newsletter, December 8, 2020

Past studies about variable refrigerant flow (VRF) controls have used only local state information to determine control variables. In an article from Science and Technology for the Built Environment, researchers used artificial neural network (ANN) simulation models to examine an integrated VRF control where both local information and the dynamics of the room determined the VRF control actions.

Cheol-Soo Park, Ph.D., Professor at the Department of Architecture and Architectural Engineering at the Seoul National University College of Engineering, discusses the research.

1. What is the significance of this research?

Existing studies have treated variable refrigerant flow (VRF) control as a local control problem where control variables are determined using only local state information. This study investigates an integrated VRF control in which the VRF control actions are determined based on not only local information but also the dynamics of the room that the VRF serves.

Based on a comparative experiment, it was found that integrated control could reduce the cooling and compressor energy use of the VRF by 21.6% and 13.1%, respectively, compared to the local control. These energy savings were achieved because the integrated control ANN models were aware of the dynamic relationship between the VRF and the target room.

 

2. Explain the steps of this research project. What did the process look like?

Two artificial neural network simulation models were developed: one to predict indoor air temperature of the room and the other to predict the VRF’s compressor power. The ANN simulation models were validated with 192 experiments conducted in an experimental chamber.

 

3. Why is it important to explore this topic now?

This study signifies the importance of including the dynamic interaction between the VRF system and its target zone environment. When the VRF system is aware of the thermal dynamics of the target room, we can expect better performance of the VRF.

 

4. What lessons, facts, and/or guidance can an engineer working in the field take away from this research?

For better design and control of the VRF, mechanical and/or control engineers must focus the impact of the VRF on thermal behavior of its target room and vice versa.

 

5. How can this research further the industry's knowledge on this topic?

This study brings a new perspective on how to get existing VRF controls to be smart. It can be inferred that the future VRF (or any other heating and cooling system) needs to be integrated to the zone’s thermal dynamics for energy savings and thermal comfort.

6. Were there any surprises or unforeseen challenges for you when preparing this research?

This study was conducted based on the hypothesis (refer to the figure below) that depending on the degree of room dynamics and the prediction horizon, the integrated control approach could far outperform local control. As a result, it was surprising to find a significant performance gap between local and integrated controls.

 

 

Close