OPTIMIZING INDOOR THERMAL COMFORT PREDICTION USING MACHINE LEARNING MODELS

Predicting thermal comfort in indoor environments is important for improving residents’ well-being, productivity, and energy efficiency. This study explores machine learning approaches, specifically Support Vector Machines (SVM) and Random Forest (RF), to improve thermal comfort prediction. Traditional methods rely on subjective assessments, whereas our approach leverages data-driven models trained on large thermal comfort datasets. The dataset underwent rigorous preprocessing, with 80% used for training and 20% for testing. The integration of the Internet of Things (IoT) further enhances predictive accuracy by enabling adaptive control in smart building systems. A comparative analysis of SVM and RF reveals that while both models effectively capture the complex interactions between environmental parameters and resident comfort, RF demonstrates greater stability and higher accuracy in most scenarios. The paper proposes potential strategies for integrating additional predictive features to further enhance model accuracy, demonstrating the advancement of machine learning in optimizing indoor comfort.

1. Milis G.M., Panayiotou C.G., and M.M. Polycarpou. IoT-Enabled Automatic Synthesis of Distributed Feedback Control Schemes in Smart Buildings. IEEE Internet of Things Journal 8 (4), 2615–2626 (2021). https://doi.org/10.1109/JIOT.2020.3019662.

2. Khather S.I., Ibrahim M.A., and A. I. Abdullah. Review and Performance Analysis of Nonlinear Model Predictive Control – Current Prospects, Challenges and Future Directions. Journal Européen des Systèmes Automatisés, 56 (4), 593–603 (2023). https://doi.org/10.18280/jesa.560409.

3. Liu B., Akcakaya M., and T. E. Mcdermott. Automated Control of Transactive HVACs in Energy Distribution Systems. IEEE Transactions on Smart Grid, 12 (3), 2462–2471 (2021). https://doi.org/10.1109/TSG.2020.3042498.

4. Wang H., Amini M.R., Hu Q., Kolmanovsky I., and J. Sun. Eco-Cooling Control Strategy for Automotive Air-Conditioning System: Design and Experimental Validation. IEEE Transactions on Control Systems Technology, 29 (6), 2339–2350 (November 2021). https://doi.org/10.1109/TCST.2020.3038746.

5. Shah Z.A., Sindi H.F., Ul-Haq A., and M.A. Ali. Fuzzy Logic-Based Direct Load Control Scheme for Air Conditioning Load to Reduce Energy Consumption. IEEE Access, 8, 117413–117427 (2020). https://doi.org/10.1109/ACCESS.2020.3005054.

6. Morales Escobar L., Aguilar J., Garcés-Jiménez A., Gutierrez De Mesa J.A., and J.M. Gomez-Pulido. Advanced Fuzzy-Logic-Based Context-Driven Control for HVAC Management Systems in Buildings. IEEE Access, 8, 16111–16126 (2020). https://doi.org/10.1109/ACCESS.2020.2966545.

7. Azuatalam D., Lee W.-L., de Nijs F., and A. Liebman. Reinforcement Learning for Whole-Building HVAC Control and Demand Response. Energy and AI, 2 (2020). https://doi.org/10.1016/j.egyai.2020.100020.

8. Mansy H., and S. Kwon. Optimal HVAC Control for Demand Response via Chance-Constrained TwoStage Stochastic Program. IEEE Transactions on Smart Grid, 12, no. 3, 2188–2200 (May 2021). https://doi.org/10.1109/TSG.2020.3037668.

9. Rabinowitz A., Araghi F.M., Gaikwad T., Asher Z.D., and T.H. Bradley. Development and Evaluation of Velocity Predictive Optimal Energy Management Strategies in Intelligent and Connected Hybrid Electric Vehicles. Energies, 14 (5713) (2021). https://doi.org/10.3390/en14185713.

10. Mohamed Salleh F.H., Saripuddin M.B., and R.B. Omar. Predicting Thermal Comfort of HVAC Building Using 6 Thermal Factors. 2020 8th International Conference on Information Technology and Multimedia (ICIMU) (Selangor, Malaysia, 2020), pp. 170–176. https://doi.org/10.1109/ICIMU49871.2020.9243466.

11. Morresi N., et al. Sensing Physiological and Environmental Quantities to Measure Human Thermal Comfort Through Machine Learning Techniques. IEEE Sensors Journal, 21 (10), 12322–12337 (May 15, 2021). https://doi.org/10.1109/JSEN.2021.3064707.

12. Widiastuti R., Zaini J., Caesarendra W., Shona Laila D., and J. Candra Kurnia. Prediction on the Indoor Thermal Comfort of Occupied Room Based on IoT Climate Measurement Open Datasets. 2020 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) (Jakarta, Indonesia, 2020), pp. 40–45. https://doi.org/10.1109/ICIMCIS51567.2020.9354277.

13. Zhang Z., Lin B., Geng Y., Zhou H., Wu X., and C. Zhang. The Effect of Group Perception Feedbacks on Thermal Comfort. Energy and Buildings, 254 (2022). https://doi.org/10.1016/j.enbuild.2021.111603.

14. Mohamed Salleh F.H., and M.B. Saripuddin. Monitoring Thermal Comfort Level of Commercial Buildings’ Occupants in a Hot-Humid Climate Country Using K-Nearest Neighbors Model. 2020 5th International Conference on Power and Renewable Energy (Shanghai, China, 2020), pp. 209–215. https://doi.org/10.1109/ICPRE51194.2020.9233145.

15. Khalil M., Esseghir M., and L. Merghem-Boulahia. An IoT Environment for Estimating Occupants’ Thermal Comfort. 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications (London, UK, 2020), pp. 1–6. https://doi.org/10.1109/PIMRC48278.2020.9217157.

16. Zhang X., Pipattanasomporn M., Chen T., and S. Rahman. An IoT-Based Thermal Model Learning Framework for Smart Buildings. IEEE Internet of Things Journal, 7 (1), 518–527 (January 2020). https://doi.org/10.1109/JIOT.2019.2951106.

17. Irshad K., Khan A.I., Irfan S.A., Alam M.M., Almalawi A., and M.H. Zahir. Utilizing Artificial Neural Network for Prediction of Occupants Thermal Comfort: A Case Study of a Test Room Fitted With a Thermoelectric Air-Conditioning System. IEEE Access, 8, 99709–99728 (2020). https://doi.org/10.1109/ACCESS.2020.2985036.

18. Gao G., Li J., and Y. Wen. DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings Via Reinforcement Learning. IEEE Internet of Things Journal, 7 (9), 8472–8484 (September 2020). https://doi.org/10.1109/JIOT.2020.2992117.

19. Coutinho Demetrios A.M., D. De Sensi, Lorenzon A.F., Georgiou K., Nunez-Yanez J., Eder K., and S. Xavier-de-Souza. Performance and Energy Trade-Offs for Parallel Applications on Heterogeneous MultiProcessing Systems. Energies, 13 (2409) (2020). https://doi.org/10.3390/en13092409.

20. Wang Z., Onodera H., and R. Matsuhashi. Proposal of Relative Thermal Sensation: Another Dimension of Thermal Comfort and Its Investigation. IEEE Access, 9, 36266–36281 (2021). https://doi.org/10.1109/ACCESS.2021.3062393.

21. Cibin N., Tibo A., Golmohamadi H., Skou A., and M. Albano. Machine Learning-Based Algorithms to Estimate Thermal Dynamics of Residential Buildings with Energy Flexibility. Journal of Building Engineering, 65 (2023). https://doi.org/10.1016/j.jobe.2022.105683.

22. Miller C., Picchetti B., Fu C., and J. Pantelic. Limitations of Machine Learning for Building Energy Prediction: ASHRAE Great Energy Predictor III Kaggle Competition Error Analysis. Science and Technology for the Built Environment, 28 (5), 610–627 (2022). https://doi.org/10.1080/23744731.2022.2067466.

23. Chuang S.-Y., Sahoo N., Lin H.-W., and Y.-H. Chang. Predictive Maintenance with Sensor Data Analytics on a Raspberry Pi-Based Experimental Platform. Sensors, 19 (3884) (2019). https://doi.org/10.3390/s19183884.