Home / Current Issue / Paper 1720133
Adaptive Thermostat Systems: Bridging Control Theory and Behavioral Learning for Sustainable Smart Homes
Subject area: Science,Engineering and Technology · Area of research: Smart Technology
DOI: https://doi.org/10.64388/IREV10I1-1720133
Abstract
This research presents the development of a thermostat system with adaptive temperature control, integrating intelligent algorithms, sensor feedback, and behavioral learning. The prototype utilizes an ESP32 microcontroller, digital sensors, and relay modules to regulate indoor climate based on real-time data and user preferences. Adaptive PID control and relay feedback identification ensure precise temperature regulation, while a learning mechanism based on multi-armed bandit algorithms enables the system to predict and adapt to user behavior. Experimental results demonstrate a mean absolute error of 0.42°C, energy savings of up to 21.1%, and learning accuracy reaching 100% by Week 4. These findings establish the effectiveness of adaptive thermostats in enhancing comfort and energy efficiency, offering a scalable solution for modern smart building environments.
Keywords
Adaptive Thermostat, PID Control, Relay Feedback, Energy Efficiency, Behavioral Learning.
How to cite this paper
@article{1720133,
author = {Adesina, Morenikeji Dele, Bello Saheed Akinbola, Adegoke Benjamin Olusesan},
title = {Adaptive Thermostat Systems: Bridging Control Theory and Behavioral Learning for Sustainable Smart Homes},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {1},
pages = {3239-3245},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1720133.pdf},
abstract = {This research presents the development of a thermostat system with adaptive temperature control, integrating intelligent algorithms, sensor feedback, and behavioral learning. The prototype utilizes an ESP32 microcontroller, digital sensors, and relay modules to regulate indoor climate based on real-time data and user preferences. Adaptive PID control and relay feedback identification ensure precise temperature regulation, while a learning mechanism based on multi-armed bandit algorithms enables the system to predict and adapt to user behavior. Experimental results demonstrate a mean absolute error of 0.42°C, energy savings of up to 21.1%, and learning accuracy reaching 100% by Week 4. These findings establish the effectiveness of adaptive thermostats in enhancing comfort and energy efficiency, offering a scalable solution for modern smart building environments.},
keywords = {Adaptive Thermostat, PID Control, Relay Feedback, Energy Efficiency, Behavioral Learning.},
month = {July},
doi = {https://doi.org/10.64388/IREV10I1-1720133}
}