AC With Predictive Control And Temperature Sensor
Abstract
Air Conditioners are a staple aspect in many com- mon households of today especially for their capabilities to counteract extreme temperatures. However, ACs are also prone to malfunctions due to not only their high power consumption but also of basic control systems causing extreme fluctuations. This study addresses these problems by developing a simulation tool of an AC with temperature sensors and a controller based on Model Predictive Control. The main tool used to develop was with Python through Google Colab and the dataset used to test the model was taken from Kaggle. The study also modeled a standard On/Off controller with fixed deadband settings to be compared against. And the results showed that Model Predictive Control gained more stable results and less extreme fluctuations in power output compared to standard On/Off models. This shows that software modifications like Model Predictive Control can help ACs by actively optimizing their output based on temperature data recorded in realtime.
Index Terms—Air Conditioners, Model Predictive Control, Simulation, On/Off Controller, Temperature Control.
References
B. Hanani. Suhu panas di batam 33 derajat, bmkg imbau masyarakat perbanyak minum air. Sept. 2024. Diakses pada 16 Mei 2025.
F. M. J. M. Shamrat, M. Hasan, M. A. R. Sarkar, M. M. Hasan, A. K. Das, and A. B. M. A. A. Islam. An intelligent embedded ac automation model with temperature prediction and human detection. In Emerging Technologies in Data Mining and Information Security, pages 769–779. Springer, 2021.
S. Mostafavi, H. Doddi, K. Kalyanam, and D. Schwartz. Nonlinear moving horizon estimation and model predictive control for buildings with unknown hvac dynamics. arXiv preprint arXiv:2211.10097, 2022.
S. M. Kargar and M. Bahamin. Advanced model predictive control strategy for thermal management in multi-zone buildings with energy storage and dynamic pricing. Proceedings of the Institution of Mechan- ical Engineers, Part C: Journal of Mechanical Engineering Science, 239(3):1234–1245, 2025.
S. H. Pramono, A. Zainuri, and M. F. E. Purnomo. Temperature and humidity optimization of air conditioner for saving electrical energy using wireless sensor network method. International Journal on Ad- vanced Science, Engineering and Information Technology, 11:1474– 1480, August 2021.
Z. An, X. Ding, and W. Du. Go beyond black-box policies: Rethinking the design of learning agent for interpretable and verifiable hvac control. arXiv preprint arXiv:2403.00172, 2024.
X. Ding, Z. An, A. Rathee, and W. Du. A safe and data-efficient model- based reinforcement learning system for hvac control. arXiv preprint arXiv:2407.12195, 2024.
Y. Ozawa, D. Zhao, D. Watari, I. Taniguchi, T. Suzuki, Y. Shimoda, and
T. Onoye. Data-driven hvac control using symbolic regression: Design and implementation. arXiv preprint arXiv:2304.03078, 2023.
K. Irshad, A. Almalawi, A. I. Khan, M. M. Alam, M. H. Zahir, and A. Ali. An iot-based thermoelectric air management framework for smart building applications: A case study for tropical climate. Sustainability, 12(4):1564, 2020.
H. Wang, D. Mai, Q. Li, and Z. Ding. Evaluating machine learning models for hvac demand response: The impact of prediction accuracy on model predictive control performance. Buildings, 14(7):2212, 2024.
P. Hua, H. Wang, Z. Xie, and R. Lahdelma. Multi-criteria evaluation of novel multi-objective model predictive control method for indoor thermal comfort. Energy, 289:129883, 2024.
M. H. Cucei. Modeling of air-conditioning for energy savings. Kaggle, [Online]. Available: https://www.kaggle.com/datasets/marcohernandezcucei/modeling-
of-air-conditioning-for-energy-savings. [Accessed: May 20, 2025].
L. W. Chew, C. Chen, C. Yuan, and C. Gorle. Quantifying Convective Heat Transfer Coefficients During Natural Ventilation in a Full Scale Operational Building. In Building Simulation, volume 211, pages 671– 738. Cambridge University Press, 2021.
V. Kumar V. M., A. Kumar S., and R. Vikas. Natural convective heat transfer analysis of a vertical tapered inner annulus tube with dual inverted frusto-conical turbulator using CFD. Engineering Applications of Computational Fluid Mechanics, 18(1):2422997, 2024.
A. H. P. Farha, D. Ziviani, K. J. Kircher, and E. A. Groll. Performance Comparison of a Residential Split-System Heat Pump Powered on AC versus DC Power. In International Refrigeration and Air Conditioning Conference at Purdue, Paper 2545, 2024.
F. Alghamdi and M. Krarti. Review Analysis for the Energy Performance of Integrated Air-Conditioning Systems. Energies, 18(7):1611, 2025.
ASHRAE. Thermal Environmental Conditions for Human Occupancy. ANSI/ASHRAE Standard 55-2023. American Society of Heating, Re- frigerating and Air-Conditioning Engineers, Atlanta, GA, 2023.
