Authors : Usha Rani K.; Santhoshini S. G.; Shalini K. S.

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/4cc5urft

Scribd : https://tinyurl.com/mshdeyc2

DOI : https://doi.org/10.38124/ijisrt/26mar1081

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Efficient monitoring of system temperature and workload is essential for maintaining performance, reliability, and hardware safety in modern computing devices. Conventional monitoring tools only display current CPU and memory usage, but they do not provide intelligent prediction, automated alerts, or historical analysis of overheating events. This project proposes Thermal Guard, an AI-based system overheating prediction and live monitoring framework that combines machine learning, real-time system monitoring, database logging, and email alerts. The system predicts overheating levels such as Low, Medium, High, and Overload using workload parameters including heat, RAM usage, processor speed, disk usage, GPU load, CPU cores used, battery level, system uptime, fan speed, and ambient temperature. In addition to offline prediction, the system performs live monitoring using real-time CPU and RAM data, classifies the current thermal condition, predicts future risk, stores overheating logs, and provides safety precautions. Experimental results show that Thermal Guard can effectively support intelligent monitoring, early warning, and safety management for computing devices.

Keywords : Thermal Guard, System Overheating Prediction, Live Monitoring, Machine Learning, CPU Usage, RAM Usage, Risk Classification, Flask, SQLite, Email Alert, Predictive Maintenance.

References :

1. Zhang, Y., Li, H., and Wang, X., “Machine Learning-Based Thermal Prediction for Data Center Servers,” IEEE Access, Vol. 11, pp. 34562-34572, 2023.
2. Kumar, R., Sharma, P., and Singh, A., “Real-Time CPU Temperature Monitoring and Prediction Using Machine Learning Techniques,” Journal of Computer Systems and Applications, Vol. 15, No. 2, pp. 120-129, 2024.
3. Liu, J., Chen, Q., and Zhao, Y., “Deep Learning-Based Thermal Anomaly Detection in High-Performance Computing Systems,” IEEE Transactions on Computers, Vol. 72, No. 5, pp. 1456-1467, 2023.
4. Pang, L., Luo, C., and Pan, W., “Research on the Impact of Indoor Control Quality Monitoring Based on Internet of Things,” IEEE Access, Vol. 11, pp. 45671-45681, 2023.
5. Singh, V., Gupta, N., and Verma, S., “Predictive Monitoring of System Overheating Using Artificial Intelligence,” International Journal of Advanced Computer Science and Applications, Vol. 14, No. 3, pp. 210-218, 2023.
6. Wang, T., Zhou, Y., and Li, M., “Thermal Management in Data Centers Using AI-Driven Predictive Models,” IEEE Transactions on Cloud Computing, Vol. 12, No. 1, pp. 112-123, 2024.
7. Chen, L., Huang, X., and Yang, J., “Intelligent System Health Monitoring Using Machine Learning and Sensor Data,” Sensors Journal, Vol. 23, No. 6, pp. 3342-3351, 2023.
8. Gupta, R., Mehta, P., and Jain, A., “Anomaly Detection in System Performance Using Random Forest and Neural Networks,” International Journal of Computer Applications, Vol. 185, No. 12, pp. 10-17, 2024.
9. Patel, K., Shah, R., and Patel, H., “Real-Time Hardware Monitoring and Fault Prediction Using Data Analytics,” Journal of Intelligent Systems, Vol. 33, No. 4, pp. 556-565, 2024.
10. Zhao, D., Liu, K., and Wang, S., “AI-Based Predictive Maintenance for Computing Infrastructure,” IEEE Access, Vol. 12, pp. 26789-26799, 2024.
11. Rahman, M., Islam, S., and Hossain, M., “A Smart Monitoring Framework for Detecting Hardware Failures in Computer Systems,” Future Generation Computer Systems, Vol. 144, pp. 90-101, 2023.
12. Kumar, S., Patel, R., and Desai, P., “Temperature Prediction and System Reliability Analysis Using Machine Learning,” International Journal of Engineering Research & Technology, Vol. 13, No. 5, pp. 876-882, 2024.
13. Al-Fuqaha, A., Guizani, M., and Mohammadi, M., “Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications,” IEEE Communications Surveys & Tutorials, Vol. 25, No. 2, pp. 1387-1425, 2023.
14. Lin, C., Zhang, H., and Xu, J., “Energy-Efficient Thermal Management for High-Performance Computing Systems,” Journal of Parallel and Distributed Computing, Vol. 178, pp. 45-56, 2024.
15. Sun, Y., Li, Q., and Chen, Z., “Deep Learning Approaches for Predicting System Performance and Thermal Behavior,” ACM Computing Surveys, Vol. 56, No. 7, pp. 1-32, 2024.