Novel Embedded System for Real-Time Fault Diagnosis of Photovoltaic Modules

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 2, pp. 14-20, February 2026.

https://doi.org/10.58482/ijersem.v2i2.3

This work is licensed under a Creative Commons Attribution 4.0 International License.

Novel Embedded System for Real-Time Fault Diagnosis of Photovoltaic Modules

Full Text PDF

S. Roja

T. Mahesh Babu

T. Prabhavathi

P. Nandhini

P. Madhan

K. Nikhil Varma

Department of ECE, Siddartha Institute of Science and Technology, Puttur, India.

Abstract: Photovoltaic (PV) systems are increasingly deployed for renewable energy generation; however, their performance and reliability are often compromised by electrical faults, environmental stress, overheating, and mechanical disturbances. Undetected faults not only reduce power output but also pose safety risks and increase maintenance costs. To address these challenges, this paper presents a novel embedded system for real-time fault diagnosis and protection of photovoltaic modules, integrating multiple sensors and IoT-based monitoring. The proposed system continuously monitors critical PV parameters, including light intensity, voltage, current, temperature, and mechanical stability, using LDR, voltage and current sensors, DHT11 temperature sensor, and MEMS sensors. An Arduino UNO serves as the central controller for data acquisition, decision-making, and control actions. To enhance energy efficiency and system safety, a servo motor dynamically adjusts panel orientation for optimal sunlight exposure, while an active cooling mechanism that integrates using a DC pump and copper tubing prevents overheating. Real-time sensor data are transmitted to the cloud via a NodeMCU module, enabling remote monitoring, visualisation, and analysis. In the event of abnormal conditions, instant alerts are generated via a GSM module and a buzzer for timely intervention. Experimental implementation and hardware validation demonstrate that the proposed system effectively detects electrical, thermal, and mechanical faults while improving operational efficiency and reliability of PV installations. The developed architecture provides a low-cost, scalable, and intelligent solution for automated photovoltaic fault diagnosis and protection, suitable for both residential and small-scale industrial solar energy systems.

Keywords: Photovoltaic Fault Diagnosis, Embedded Systems, Sensor Integration, Solar Panel Monitoring, IoT-based Energy Management..

References: 

  1. M. I. Shajahan et al., “Edge-integrated IoT framework for real-time fault diagnosis and performance degradation analysis in photovoltaic modules,” Renewable Energy, vol. 258, p. 124928, Dec. 2025, doi: 10.1016/j.renene.2025.124928.
  2. Y. Chen, M. Ma, W. Ma, X. Zhou, R. Zhang, and Z. Fang, “An adaptive four-layer digital twin with segmented diode model for real-time fault diagnosis and output characterization of PV modules,” Solar Energy, vol. 300, p. 113755, Jul. 2025, doi: 10.1016/j.solener.2025.113755.
  3. C. P. Nivarthi, Z. Huang, C. Gruhl, and B. Sick, “TRACE: Time series representation learning with contrastive embeddings for anomaly detection in photovoltaic systems,” Energy and AI, vol. 23, p. 100670, Dec. 2025, doi: 10.1016/j.egyai.2025.100670.
  4. E. H. Sepúlveda-Oviedo, L. Travé-Massuyès, A. Subias, M. Pavlov, and C. Alonso, “Artificial intelligence in photovoltaic fault diagnosis: A Natural Language-Based Topic-tSNE Fusion analysis,” Energy and AI, vol. 21, p. 100558, Jul. 2025, doi: 10.1016/j.egyai.2025.100558.
  5. M. I. Shajahan et al., “Edge-integrated IoT framework for real-time fault diagnosis and performance degradation analysis in photovoltaic modules,” Renewable Energy, vol. 258, p. 124928, Dec. 2025, doi: 10.1016/j.renene.2025.124928.
  6. A. Mellit and S. Kalogirou, “Recent advances in the application of infrared thermographic imaging and embedded artificial intelligence for fault diagnosis and predictive maintenance of photovoltaic plants: Challenges and future directions,” Renewable and Sustainable Energy Reviews, vol. 223, p. 116057, Jul. 2025, doi: 10.1016/j.rser.2025.116057.
  7. Y. Özüpak, “Real-time detection of photovoltaic module faults using a hybrid machine learning model,” Solar Energy, vol. 302, p. 114014, Oct. 2025, doi: 10.1016/j.solener.2025.114014.
  8. A. Teta et al., “Robust and fast fault diagnosis framework for grid-connected photovoltaic systems via adaptive channel-wise representations and transfer learning,” Measurement, vol. 258, p. 119290, Oct. 2025, doi: 10.1016/j.measurement.2025.119290.
  9. A. Mellit, M. Benghanem, S. Kalogirou, and A. M. Pavan, “An embedded system for remote monitoring and fault diagnosis of photovoltaic arrays using machine learning and the internet of things,” Renewable Energy, vol. 208, pp. 399–408, Mar. 2023, doi: 10.1016/j.renene.2023.03.096.
  10. A. Mellit, “An embedded solution for fault detection and diagnosis of photovoltaic modules using thermographic images and deep convolutional neural networks,” Engineering Applications of Artificial Intelligence, vol. 116, p. 105459, Oct. 2022, doi: 10.1016/j.engappai.2022.105459.
  11. S. Titouni et al., “Hybrid CNN-Autoencoder model for accurate and efficient fault diagnosis in grid-connected photovoltaic systems,” International Journal of Electrical Power & Energy Systems, vol. 173, p. 111454, Dec. 2025, doi: 10.1016/j.ijepes.2025.111454.
  12. Q. Navid et al., “Fault diagnosis framework for photovoltaic system using fully connected neural network-based back surface thermal analysis,” Solar Energy, vol. 303, p. 114139, Nov. 2025, doi: 10.1016/j.solener.2025.114139.
  13. C. P. Nivarthi, Z. Huang, C. Gruhl, and B. Sick, “TRACE: Time series representation learning with contrastive embeddings for anomaly detection in photovoltaic systems,” Energy and AI, vol. 23, p. 100670, Dec. 2025, doi: 10.1016/j.egyai.2025.100670.
Download PDF

This article is part of Volume 2, Issue 2 (February 2026)