Adaptive Thermostat Systems: Bridging Control Theory and Behavioral Learning for Sustainable Smart Homes

References

[1] Bueno, A. M., Xavier, A.A., and Broday, E. E. (2021). Evaluating the connection between thermal comfort and productivity in buildings: A systematic literature review. Buildings, 2075- 5309, 11 (6), 244, 10.3390/buildings11060244

[2] Hassan, A., Gunay, B., Ouf, M. M., Chong, A., and Markus, A. A. (2025). Nudging window use behaviour through algorithmic setpoint adjustments. Build. Environ., 275 , 112810.

[3] Schiavon, S., and Lee K. H. (2013). Dynamic predictive clothing insulation models based on outdoor air and indoor operative temperatures. Build. Environ., 59. 250-260.

[4] Peng, Y., Nagy, Z., and Schlüter, A. (2019). Temperature-preference learning with neural networks for occupant-centric building indoor climate controls. Build. Environ., 154, 296-308.

[5] Assaf, S., and Srour I. (2021). Using a data driven neural network approach to forecast building occupant complaints. Build. Environ., 200, 107972.

[6] Tamas, R., Ouf, M. M., and O’Brien, W. (2020). A field study on the effect of building automation on perceived comfort and control in institutional buildings. Archit. Sci. Rev., 63 (1), 74-86.

[7] Karjalainen, S. (2010). Usability guidelines for room temperature controls. Intell. Build. Int., 2 (2), 85-97.

[8] O’Brien, W., Wagner, A., Schweiker, M., Mahdavi, A., Day, J., Kjærgaard, M.B., Carlucci, S., Dong, B., Tahmasebi, F., Yan, D., (2020). Introducing IEA EBC annex 79: key challenges and opportunities in the field of occupant-centric building design and operation. Build. Environ., 178,106738.

[9] . Zhong, Z., Lei, Z., and Shengchen, Z. (2019). "Thermostat Temperature Adaptive Control Based on Relay Feedback Identification," 2019 12th Asian Control Conference (ASCC), Kitakyushu, Japan, pp. 421-425.

[10] Brandi S., Piscitelli, M. S., Martellacci, M., and Capozzoli, A. (2020). Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings. Energy Build, 0378-7788, 224, 110225, 10.1016/j.enbuild.2020.110225.

[11] Payam Karjou, P., Stupperich, F., Stoffel, P., and Muller, D. (2025). Human-in-the-loop control strategy for IoT-based smart thermostats with Deep Reinforcement Learning. Energy and AI, Elsevier, 20, 100490. https://

[12] . Hussein Elehwany, Andre Markus, Burak Gunay, Mohamed Ouf, Nunzio Cotrufo, Jean- Simon Venne, and Junfeng Wen. (2026). Adaptive thermostat preference learning using behaviour nudging and multi-armed bandits: A field implementation. Energy and Buildings, Elsevier, 355, 117030. https://

[13] Stopps, H., & Touchie, M., (2021). Residential smart thermostat use: An exploration of thermostat programming, environmental attitudes, and the influence of smart controls on energy savings. Energy and Buildings, 238, 110834. https://

[14] Pang, Z., Chen, Y., Zhang, J., O'Neill, Z., Cheng, H., & Dong, B., (2021). How much HVAC energy could be saved from the occupant-centric smart home thermostat: A nationwide simulation study. Applied Energy, 283, 116391. https://

[15] José David Bienvenido Huertas (2021). Influence of the type of thermostat on the energy saving obtained with adaptive setpoint temperatures: Analysis in the current and future scenario. Energy and Buildings, 244(111024).

[16] Merabet, G. H., Essaaidi, M., Ben Haddou, M., et al. (2021). Intelligent Building Control Systems for Thermal Comfort and Energy- Efficiency: A Systematic Review of Artificial Intelligence-Assisted Techniques. Energies, 14(22), 7622. https://

[17] Wang, C., Jiang, J., Roth, T., Nguyen, C., Liu, Y., & Lee, H. (2021). *Integrated Sensor Data Processing for Occupancy Detection in Residential Buildings. Energy and Buildings, 237, 110810. https://

[18] Li, X., Wen, J., & others. (2021). Occupancy- based HVAC control systems in buildings: A state -of-the-art review. Building and Environment, 197, 107810. https:// 10

[19] . Jin, Y., Yan, D., Chong, A., et al. (2021). Building occupancy forecasting: A systematical and critical review. Energy and Buildings, 251, 111345. https://

[20] . Pinheiro, L., Wang, Z., O'Neill, Z., & Pang, Z., (2026). Quantifying the impact of occupancy sensor errors on energy savings, thermal comfort, and peak demand in residential smart thermostats. Journal of Building Performance Simulation. https:// 562

[21] . Bourgoin, G., Micheneau, K., Boodi, A., et al. (2026). A comprehensive framework for modeling building occupancy: Technologies, methods, and research challenges. Energy Informatics, 9, 54. https://

[22] . Åström, K. J., & Hägglund, T. (1995). PID Controllers: Theory, Design, and Tuning (2nd ed.). Research Triangle Park, NC: Instrument Society of America. ISBN: 1-55617-516-7.

[23] . GuideSpot. (2026). Smart Thermostart Energy Saving Features Guide 2026. https://www.guidespot.com/smart-thermostat- energy-saving-features/

[24] . Heater Guides. (2025). How Adaptive Learning Thermostats Work & Why You Need One. https://heaterguides.com/what-is-adaptive- learning-in- thermostats?utm_source=copilot.com

[25] W.-K. Chen, Linear Networks and Systems (Book style). Belmont, CA: Wadsworth, 1993, pp. 123–135.

@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}
  }