PANDEMIC: Occupancy driven predictive ventilation control to minimize energy consumption and infection risk.

Appl Energy

Department of Mechanical & Aerospace Engineering, Syracuse University, Syracuse, NY 13244, United States.

Published: March 2023

AI Article Synopsis

  • During the COVID-19 pandemic, higher outdoor air flow requirements for ventilation systems increased building energy consumption, prompting the need for energy-efficient strategies to mitigate infection risks.
  • The study developed an occupant-number-based model predictive control (OBMPC) algorithm, using occupancy and HVAC data to predict room occupancy with up to 95% accuracy in short-term forecasts.
  • The OBMPC model can significantly reduce energy loads by about 52% while maintaining low infection risk levels, but uncertainties in occupancy predictions can lead to notable variations in ventilation demand, temperature, and airflow rates.

Article Abstract

During the SARS-CoV-2 (COVID-19) pandemic, governments around the world have formulated policies requiring ventilation systems to operate at a higher outdoor fresh air flow rate for a sufficient time, which has led to a sharp increase in building energy consumption. Therefore, it is necessary to identify an energy-efficient ventilation strategy to reduce the risk of infection. In this study, we developed an occupant-number-based model predictive control (OBMPC) algorithm for building ventilation systems. First, we collected the occupancy and Heating, ventilation, and air conditioning system (HVAC) data from March to July 2021. Then, four different models (Auto regression moving average-based multilayer perceptron (ARMA_MLP), Recurrent neural networks (RNN), Long short-term memory networks (LSTM), and Nonhomogeneous Markov with change points detection (NH_Markov)) were used to predict the number of room occupants from 15 min to 24 h ahead with an interval output. We found that each model could predict the number of occupants with 85 % accuracy using a one-person offset. The accuracy of 15 min of the ahead prediction could reach 95 % with a one-person offset, but none of them could track abrupt changes. The occupancy prediction results were used to calculate the ventilation demand using the Wells-Riley equation, and the upper bound can maintain an infection risk lower than 2 % for 93 % of the day. This OBMPC model could reduce the coil load by 52.44 % and shift the peak load by 3 h up to 5 kW compared with 24 × 7 h full outdoor air (OA) system when people wear masks in the space. The occupancy prediction uncertainty could cause a 9 % to 26 % difference in demand ventilation, a 0.3 °C to 2.4 °C difference in zone temperature, a 28.5 % to 44.5 % difference in outdoor airflow rate, and a 10.7 % to 28.2 % difference in coil load.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9867897PMC
http://dx.doi.org/10.1016/j.apenergy.2023.120676DOI Listing

Publication Analysis

Top Keywords

energy consumption
8
infection risk
8
ventilation systems
8
predict number
8
one-person offset
8
occupancy prediction
8
coil load
8
ventilation
7
pandemic occupancy
4
occupancy driven
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!