Title: A constant temperature control system for indoor environments in buildings using internet of things

Authors: N. Ashokkumar; N.S. Kavitha; M. Lakshmi; Ashok Vajravelu

Addresses: Department of Electronics and Communication Engineering, Mohan Babu University, Tirupathi, Andhra Pradesh, India ' Department of ECE, Kongu Engineering College, Perundurai, Tamil Nadu, India ' Department of Mathematics, S.A. Engineering College, Chennai, Tamil Nadu, India ' Department of Electronics, Faculty of Electrical Engineering, Universiti Tun Hussein Onn Malaysia, Johor, Malaysia

Abstract: The performance of a building's internal environment, which includes the air temperature, lighting and acoustics, is what determines the quality of the environment inside the building. We present a thermal model for achieving thermal comfort in buildings that makes use of a multimodal analytic framework as a solution to this challenge. In this study, a multimodal combination is used to evaluate several temperature and humidity sensors as well as an area image. Additionally, a CNN and LSTM combination is used to process the image and sensor data. The results show that heating setback and interior set point temperatures, as well as mechanical ventilation based on real people's presence and CO₂ levels, are all consistently reduced when ICT-driven intelligent solutions are used. The CNN-LSTM model has a goodness of fit that is 0.7258 on average, which is much higher than both the CNN (0.5291) and LSTM (0.5949) models.

Keywords: environment; thermal model; CNN-LSTM; HVAC control; opening windows.

DOI: 10.1504/IJIPT.2023.139352

International Journal of Internet Protocol Technology, 2023 Vol.16 No.4, pp.217 - 225

Received: 07 Jul 2022
Accepted: 02 Aug 2023
Published online: 01 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article