Smart WI-FI Thermostat-Enabled Thermal Comfort Control Saving for Any Residence Using Long-Short Term Memory

Date of Award

2022

Degree Name

Ph.D. in Mechanical Engineering

Department

Department of Mechanical and Aerospace Engineering

Advisor/Chair

Kevin Hallinan

Abstract

Indoor thermal comfort in residential buildings can not only represented by internal temperature; other factors can affect the thermal satisfaction, such as relative humidity and the Mean Radiant Temperature (MRT). Controlling the HVAC system based on those factors can be implemented these days due the smart technologies afforded. Prior research has explored automated control of thermal comfort based on the concept of a Predicted Mean Vote (PMV) index, which was developed to provide a model of perceived occupant's comfort. However, in previous studies the mean radiant temperature (MRT) was not estimated by adding the effect of the occupant's exposure to the solar irradiance. Research is posed to leverage prior work in automatically estimating the R-values of walls and ceilings using a combination of smart Wi-Fi thermostat, building geometry, and historical energy consumption to estimate the MRT with accuracy and thus provide a means to control for comfort, rather than temperature alone [43]. Further, a machine learning model of the indoor temperature based upon a Long-Short Term Memory Network is employed in order to assess the energy saving potential of comfort control for any residence. The model leveraged historical thermostat, weather, and solar data were used to dynamically predict the interior temperature and relative humidity. With a developed model, it is possible to simulate internal temperature, and thus always quantify the PMV value to maintain a reasonable comfort condition. Application of this thermal comfort control can yield an estimate for minimum cooling energy. The initial results showed cooling energy savings in excess 43%. Based on this research, it is proposed that the approach to control thermal comfort can be used to reduce cooling energy savings and a better representation of human comfort, with only having a smart Wi-Fi thermostat with readily available data.

Keywords

Mechanical Engineering

Rights Statement

Copyright © 2022, author

Link to Full Text

Share

COinS