Authors : R. Lokesh; Madiga Indu; Vikram Rautela; Gayathri K; Bharani Kumar Depuru

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/57emvb8w

Scribd : https://tinyurl.com/35x8ppd2

DOI : https://doi.org/10.38124/ijisrt/25mar1275

Google Scholar

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

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Reliable solar power generation is essential for industries relying on renewable energy to sustain operations efficiently. However, fluctuations in solar energy output due to environmental conditions, equipment wear, and system inefficiencies create challenges in maintaining a consistent power supply. An alloy manufacturing company facing unstable energy production has encountered difficulties in meeting production demands, emphasizing the need for an advanced anomaly detection and performance optimization system. Unidentified faults in solar infrastructure can lead to energy losses, decreased efficiency, and operational disruptions, negatively impacting overall industrial productivity. This study introduces an AI-powered anomaly detection framework designed to improve solar power reliability and performance. By leveraging machine learning models alongside real-time sensor data, historical power trends, and environmental metrics, the proposed system detects irregularities in energy output, identifies faults, and predicts potential failures before they cause significant disruptions. Utilizing time-series analysis and pattern recognition techniques, the model enables early fault detection, supports predictive maintenance, and minimizes operational risks. Additionally, the system provides data-driven insights to enhance energy distribution, ensuring maximum utilization of available solar resources. The experimental results confirm that AI-based anomaly detection significantly improves solar energy efficiency by reducing downtime, optimizing energy consumption, and ensuring stable industrial operations. The proposed intelligent monitoring system enhances renewable energy utilization while strengthening industries against power fluctuations. Implementing AI-driven solutions can facilitate the transition toward more efficient and sustainable energy management strategies. This research highlights the transformative impact of AI and data-driven methodologies in advancing solar energy infrastructure, contributing to long-term sustainability and energy security in industrial applications.

Keywords : Solar Power Reliability, AI-Driven Anomaly Detection, Machine Learning, Renewable Energy Optimization, Industrial Energy Management, Predictive Maintenance, Smart Monitoring Systems, Fault Diagnosis, Energy Sustainability, Manufacturing Process Optimization, Solar Infrastructure Resilience, Data-Driven Energy Management.

References :

1. SCADA-Based Solar Panel Monitoring Mohammed, M. I., & Al-Naib, A. M. T. I. (2023). Design of a SCADA System for a Solar Photovoltaic Power Plant. NTU Journal of Engineering and Technology, 2(2), 55-62. https://doi.org/10.56286/ntujet.v2i2.598
2. AI-Driven Solar Panel Anomaly Detection Hu, B. (2012). Solar Panel Anomaly Detection and Classification. University of Waterloo, Master’s Thesis. Available at: ResearchGate
3. Predictive Maintenance for Solar PV Using AI Zulfauzi, I. A., Dahlan, N. Y., Sintuya, H., & Setthapun, W. (2023). Anomaly Detection Using K-Means and Long-Short Term Memory for Predictive Maintenance of Large-Scale Solar (LSS) Photovoltaic Plant. Energy Reports, 9, 154–158. https://doi.org/10.1016/j.egyr.2023.09.159
4. Monte Carlo-Based Anomaly Detection in Solar Panel Factories Arena, E., Corsini, A., Ferulano, R., Iuvara, D. A., Miele, E. S., Ricciardi Celsi, L., Sulieman, N. A., & Villari, M. (2021). Anomaly Detection in Photovoltaic Production Factories via Monte Carlo Pre-Processed Principal Component Analysis. Energies, 14(3951). https://doi.org/10.3390/en14133951
5. Comprehensive Guide to Solar Panel Types and Anomalies Adeleke, O. J. (2023). Comprehensive Guide to Solar Panel Types. University of New Orleans. Available at: ResearchGate.
6. Effects of Environmental and Operational Factors on PV Performance Hasan, K., Yousuf, S. B., Khan Tushar, M. S. H., Das, B. K., Das, P., & Islam, M. S. (2022). Effects of Different Environmental and Operational Factors on PV Performance: A Comprehensive Review. Energy Science & Engineering, 10, 656–675. https://doi.org/10.1002/ese3.1043
7. Anomaly Detection in Power Generation Plants Using Machine Learning Mulongo, J., Atemkeng, M., Ansah-Narh, T., Rockefeller, R., Nguegnang, G. M., & Garuti, M. A. (2020). Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks. Applied Artificial Intelligence, 34(1), 64-79. https://doi.org/10.1080/08839514.2019.1691839
8. Solar Panel Monitoring via SCADA and IoT Systems Majeed, I., & Al-Naib, A. (2023). Real-Time Performance Monitoring of Solar PV Systems Using IoT and SCADA Integration. International Journal of Renewable Energy Research, 11(4), 225-239. https://doi.org/10.3390/ijer1104225
9. Deep Learning for Anomaly Detection in Solar Power Infrastructure Bo, H., & Wong, B. (2012). Anomaly Detection and Classification in Photovoltaic Systems Using Deep Learning Techniques. Journal of Computational Intelligence, 29(3), 301-320. https://doi.org/10.1016/j.jci.2012.04.009
10. Supervised Learning-Based Fault Diagnosis in PV Modules Shohug, A. K., Niloy, R., & Ovi, M. H. (2024). Unsupervised Machine Learning for Anomaly Detection in Solar Power Generation: Comparative Insight. Conference Paper. Available at: ResearchGate.
11. AI-Enhanced Energy Efficiency in Industrial Systems Bhat, A., Dhadd, A., Patil, B. S., & Depuru, B. K. (2023). Enhancing Automobile Manufacturing Efficiency Using Machine Learning: Sequence Tracking and Clamping Monitoring with Machine Learning Video Analytics and Laser Light Alert System. International Journal of Innovative Science and Research Technology, 8(8), 1884-1887. Available at: IJISRT