Predictive Optimal Control Mechanism of Indoor Temperature Using Modbus TCP and Deep Reinforcement Learning
Source abstract
Abstract
This research study proposes an indoor temperature regulation predictive optimal control system that entails the use of both deep reinforcement learning and the Modbus TCP communication protocol. The designed architecture comprises distributed sub-parts, namely, distributed room-level units as well as a centralized main-part AI controller for maximizing efficient HVAC management in single-family residences as well as small-sized buildings. The system utilizes an LSTM model for forecasting temperature trends as well as an optimized control action using an envisaged DQN with predicted states, sensors, as well as user preferences. InfluxDB is utilized for gathering real-time environmental data such as temperature and humidity, as well as consumed power, and storing it. The AI controller processes these data to infer control commands for energy efficiency as well as thermal comfort. Experimentation on an NVIDIA Jetson Orin Nano as well as on a Raspberry Pi 4 proved the efficacy of the system, utilizing 8761 data points gathered hourly over 2023 in Cheonan, Korea. An added hysteresis-based mechanism for controlling power was incorporated to limit device wear resulting from repeated switching. Results indicate that the AI-based control system closely maintains target temperature setpoints with negligible deviations, affirming that it is a scalable, cost-efficient solution for intelligent climate management in buildings.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Building Energy and Comfort Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Smart Information Technology Engineering, Kongju National University, Cheonan 31080, Republic of Korea
Department of Computer Engineering, Jeju National University, Jeju-Si 63243, Republic of Korea
Division of Electrical, Electronics, and Control Engineering, Kongju National University, Cheonan 31080, Republic of Korea
Funding
Korea government (MSIT)
References (28)
Show source-provided references
1. Xiang, X., Zhou, N., Ma, M., Feng, W., and Yan, R. (2023). Global transition of operational carbon in residential buildings since the millennium. Adv. Appl. Energy, 11.10.1016/j.adapen.2023.100145 ↗
2. Multi-objective optimization of PI controller for BLDC motor speed control and energy saving in Electric Vehicles: A constrained swarm-based approach10.1016/j.egyr.2024.06.019 ↗
3. The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver10.1109/TC.1980.1675516 ↗
4. International Energy Agency (2025, May 28). Buildings: A Source of Energy Efficiency. Available online: https://www.iea.org/energy-system/buildings.
5. Optimizing energy efficiency and comfort in smart homes through predictive optimization: A case study with indoor environmental parameter consideration10.1016/j.egyr.2024.05.038 ↗
6. Zubair, S., Hamayat, F., and Nazir, A. (2024, January 28–30). AI-powered thermal comfort: Predicting indoor air temperature for efficient HVAC systems. Proceedings of the 2024 29th International Conference on Automation and Computing (ICAC), Sunderland, UK.10.1109/ICAC61394.2024.10718738 ↗
7. Park, B.K., and Kim, C.-J. (2023). Short-term prediction for indoor temperature control using artificial neural network. Energies, 16.10.3390/en16237724 ↗
8. Ramadan, L., Shahrour, I., Mroueh, H., and Chehade, F.H. (2021). Use of machine learning methods for indoor temperature forecasting. Future Internet, 13.10.3390/fi13100242 ↗
9. Cho, S., Nam, H.J., Shi, C., Kim, C.Y., Byun, S.-H., Agno, K.-C., Lee, B.C., Xiao, J., Sim, J.Y., and Jeong, J.-W. (2023). Wireless, AI-enabled wearable thermal comfort sensor for human-in-the-loop HVAC control. Biosens. Bioelectron., 223.10.1016/j.bios.2022.115018 ↗
10. Silvestri, A., Coraci, D., Brandi, S., Capozzoli, A., Borkowski, E., Köhler, J., Wu, D., Zeilinger, M.N., and Schlueter, A. (2024). Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control. Appl. Energy, 368.10.1016/j.apenergy.2024.123447 ↗
11. Yue, G. (2020, January 13–15). Design of intelligent monitoring and control system based on Modbus. Proceedings of the 2020 5th International Conference on Communication, Image and Signal Processing (CCISP), Chengdu, China.10.1109/CCISP51026.2020.9273500 ↗
12. Mughaid, A., Alzu’bi, S., Alkhatib, A.A.A., AlZioud, A., Al Ghazo, A., and AL-Aiash, I. (2025). Simulation-based framework for authenticating SCADA systems and cyber threat security in edge-based autonomous environments. Simul. Model. Pract. Theory, 140.10.1016/j.simpat.2025.103078 ↗
13. Zhao, Y., Genovese, P.V., and Li, Z. (2020). Intelligent thermal comfort controlling system for buildings based on IoT and AI. Future Internet, 12.10.3390/fi12020030 ↗
14. Palomino Bernal, J.F., Colmenero Fonseca, F., Jalomo Cuevas, J., Carcel-Carrasco, J., and Rodríguez Pérez, R. (2025). Innovation in intelligent temperature management in educational spaces. Buildings, 15.10.3390/buildings15050672 ↗
15. An, W., Zhu, X., Yang, K., Kim, M.K., and Liu, J. (2023). Hourly Heat Load Prediction for Residential Buildings Based on Multiple Combination Models: A Comparative Study. Buildings, 13.10.3390/buildings13092340 ↗
16. Building Cooling Load Forecasting Model Based on LS-SVM
17. Yan, H., Zhu, J., Sun, Y., Tao, Y., and Lan, M. (2019, January 23–27). Design and implementation of intelligent building control system based on real-time database. Proceedings of the 2019 1st International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China.10.1109/ICIAI.2019.8850785 ↗
18. Singh, M., and Shimi, S.L. (2018, January 19–20). Implementation of room automation with cloud-based monitoring system. Proceedings of the 2018 2nd International Conference on Inventive Systems and Control (ICISC), Coimbatore, India.10.1109/ICISC.2018.8398911 ↗
19. Nyasore, O.N., Zavarsky, P., Swar, B., Naiyeju, R., and Dabra, S. (2020, January 25–27). Deep Packet Inspection in Industrial Automation Control System to Mitigate Attacks Exploiting Modbus/TCP Vulnerabilities. Proceedings of the 2020 IEEE 6th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS), Baltimore, MD, USA.10.1109/BigDataSecurity-HPSC-IDS49724.2020.00051 ↗
20. A High Performance Communication Architecture for a Smart Micro-Grid Testbed Using Customized Edge Intelligent Devices (EIDs) with SPI and Modbus TCP/IP Communication Protocols10.1109/OJPEL.2021.3051327 ↗
21. Evaluation of Reinforcement Learning Control for Thermal Energy Storage Systems10.1080/10789669.2003.10391069 ↗
22. Homod, R.Z., Yaseen, Z.M., Hussein, A.K., Almusaed, A., Alawi, O.A., Falah, M.W., Abdelrazek, A.H., Ahmed, W., and Eltaweel, M. (2023). Deep clustering of cooperative multi-agent reinforcement learning to optimize multi chiller HVAC systems for smart buildings energy management. J. Build. Eng., 65.10.1016/j.jobe.2022.105689 ↗
23. A deep LSTM network for the Spanish electricity consumption forecasting10.1007/s00521-021-06773-2 ↗
24. Dubey, A.K., Kumar, A., García-Díaz, V., Sharma, A.K., and Kanhaiya, K. (2021). Study and analysis of SARIMA and LSTM in forecasting time series data. Sustain. Energy Technol. Assess., 47.10.1016/j.seta.2021.101474 ↗
25. Graves, A., and Schmidhuber, J. (2005–4, January 31). Framewise phoneme classification with bidirectional LSTM networks. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada.10.1109/IJCNN.2005.1556215 ↗
26. Insult detection using a partitional CNN-LSTM model
27. Devarajan, G.G., Nagarajan, S.M., Ramana, T.V., Vignesh, T., Ghosh, U., and Alnumay, W.S. (2023). DDNSAS: Deep reinforcement learning based deep Q-learning network for smart agriculture system. Sustain. Comput. Inform. Syst., 39.10.1016/j.suscom.2023.100890 ↗
28. Wang, S., Chen, X., Bu, L., Wang, B., Yu, K., and He, D. (2023, January 15–18). A DQN-Based Coordination Method of HVAC and Energy Storage for Building Energy Management. Proceedings of the 2023 IEEE 7th Conference on Energy Internet and Energy System Integration (EI2), Hangzhou, China.10.1109/EI259745.2023.10512933 ↗