Improving Solar Energy Reliability with Data-Driven Anomaly Detection Techniques
DOI:
https://doi.org/10.46604/aiti.2026.15951Keywords:
solar photovoltaic (PV) systems, anomaly detection, K-means clustering, isolation forest, renewable energy monitoringAbstract
This study investigates unsupervised machine learning (ML) for anomaly detection in solar photovoltaic (PV) power generation data from 2019 to 2023. An unsupervised approach is selected to overcome the absence of pre-labeled fault data, enabling the autonomous identification of operational patterns. Following data preparation, K-means clustering (k=3) identifies distinct operational patterns, specifically characterizing regimes such as optimal performance (Cluster 2) and low energy output attributed to adverse weather conditions (Cluster 1). These clusters are subsequently visualized using principal component analysis (PCA) to validate their distinct separation. An isolation forest model is then employed for anomaly detection, identifying 17 significant deviations. These anomalies occur most frequently in 2020, coinciding with the COVID-19 pandemic period. Many fall outside the typical energy range of 2.0–3.2 kWh/day and are associated with non-ideal weather conditions. This finding demonstrates that unsupervised ML provides a scalable framework for monitoring PV system health, enhancing reliability, and supporting preventive strategies.
References
A. A. Bayod-Rújula, “Solar Photovoltaics (PV),” in Solar Hydrogen Production: Processes, Systems and Technologies, Elsevier, pp. 237-295, 2019.
E. Jiménez-Delgado, C. Meza, A. Méndez-Porras, and J. Alfaro-Velasco, “Data Management Infrastructure from Initiatives on Photovoltaic Solar Energy,” Proceedings of International Conference on Information Technology & Systems, pp. 113-121, 2019.
M. A. Koondhar, I. A. Laghari, B. M. Asfaw, R. Reji Kumar, and A. H. Lenin, “Experimental and Simulation-Based Comparative Analysis of Different Parameters of PV Module,” Scientific African, vol. 16, article no. e01197, 2022.
R. S. Hansen, A. A. Munaf, H. L. Allasi, S. Endro, J. Leno, and S.K. R. Kanna, “Experimental and Theoretical Optimization of an Inclined Type Solar Still Using PV Sustainable Recirculation Technique,” Materials Today: Proceedings, vol. 45, Part 7, pp. 7063-7071, 2021.
E. Koubli, D. Palmer, P. Rowley, and R. Gottschalg, “Inference of Missing Data in Photovoltaic Monitoring Datasets,” Institution of Engineering and Technology Renewable Power Generation, vol. 10, no. 4, pp. 434-439, 2016.
S. Touzani, A. K. Prakash, Z. Wang, S. Agarwal, M. Pritoni, M. Kiran, et al., “Controlling Distributed Energy Resources via Deep Reinforcement Learning for Load Flexibility and Energy Efficiency,” Applied Energy, vol. 304, article no. 117733, 2021.
T. Park, K. Song, J. Jeong, and H. Kim, “Convolutional Autoencoder-Based Anomaly Detection for Photovoltaic Power Forecasting of Virtual Power Plants,” Energies, vol. 16, no. 14, article no. 5293, 2023.
E. Sarmas, N. Matias, C. Pereira, and A. R. Antunes, “Photovoltaic Power Production Dataset,” Mendeley Data, vol. 3, 2025.
J. L. de S. Silva, M. V. de Paula, J. De S. G. Barros, and T. A. Dos S. Barros, “Anomaly Detection Workflow Using Random Forest Regressor in Large-Scale Photovoltaic Power Plants,” IEEE Access, vol. 13, pp. 54168-54176, 2025.
I. H. Adil, A. Wahid, and E. H. Mantell, “Split Sample Skewness,” Communications in Statistics - Theory and Methods, vol. 50, no. 22, pp. 5171-5188, 2021.
C. M. Chang, D. Cheng, R. E. Smith, S. G. Tan, and A. Hossain, “SMART Quality Control Analysis of Pavement Condition Data for Pavement Management Applications,” International Journal of Transportation Science and Technology, vol. 18, pp. 227-244, 2024.
W. Cui and H. Wang, “A New Anomaly Detection System for School Electricity Consumption Data,” Information, vol. 8, no. 4, article no. 151, 2017.
P. Schober, C. Boer, and L. A. Schwarte, “Correlation Coefficients: Appropriate Use and Interpretation,” Anesthesia & Analgesia, vol. 126, no. 5, pp. 1763-1768, 2018.
O. Azeroual, A. Nikiforova, and K. Sha, “Overlooked Aspects of Data Governance: Workflow Framework for Enterprise Data Deduplication,” Proceedings of 2023 International Conference on Intelligent Computing, Communication, Networking and Services (ICCNS), IEEE, pp. 65-73, 2023.
V. B. Sorkhabi, M.-R. F. Derakhshi, and H. Shahamfar, “An Algorithm for Detecting Similar Data in Replicated Databases Using Multi Criteria Decision Making,” Proceedings of 2009 Second International Conference on Environmental and Computer Science, IEEE, pp. 199-203, 2009.
H. Qi, X. Di, J. Li, and H. Ma, “Improved K-Means Algorithm and Its Application to Vehicle Steering Identification,” Proceedings of International Conference on Advanced Hybrid Information Processing, pp. 378-386, 2018.
S. Buschjager, P.-J. Honysz, and K. Morik, “Generalized Isolation Forest: Some Theory and More Applications Extended Abstract,” Proceedings of 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, pp. 793-794, 2020.
F. P. Monteiro, S. Monteiro, C. Rodrigues, J. Reis, U. Bezerra, M. E. Tostes, Frederico, et al., “A Hybrid Methodology Using Machine Learning Techniques and Feature Engineering Applied to Time Series for Medium- and Long-Term Energy Market Price Forecasting,” Energies, vol. 18, no. 6, article no. 1387, 2025.
M. Usmani, Z. A. Memon, A. Zulfiqar, and R. Qureshi, “Preptimize: Automation of Time Series Data Preprocessing and Forecasting,” Algorithms, vol. 17, no. 8, article no. 332, 2024.
A. Sleiman and W. Su, “Combined K-Means Clustering with Neural Networks Methods for PV Short-Term Generation Load Forecasting in Electric Utilities,” Energies, vol. 17, no. 6, article no. 1433, 2024.
J. -F. Wu, C. -C. Huang, and M. -Y. Cheng, “DBSCAN-Based Minimum Enclosing Ellipse Using the Control Barrier Function for Safe Navigation of Mobile Robots,” Advances in Technology Innovation, vol. 10, no. 4, pp. 358-369, 2025.
G. Liu, L. Zhu, X. Wu, and J. Wang, “Time Series Clustering and Physical Implication for Photovoltaic Array Systems with Unknown Working Conditions,” Solar Energy, vol. 180, pp. 401-411, 2019.
M. A. M. Ramli, E. Prasetyono, R. W. Wicaksana, N. A. Windarko, K. Sedraoui, Y. A. Al-Turki, “On the Investigation of Photovoltaic Output Power Reduction Due to Dust Accumulation and Weather Conditions,” Renewable Energy, vol. 99, pp. 836-844, 2016.
H. A. H. Al-Hilfi, A. Abu-Siada, and F. Shahnia, “Estimating Generated Power of Photovoltaic Systems During Cloudy Days Using Gene Expression Programming,” IEEE Journal of Photovoltaics, vol. 11, no. 1, pp. 185-194, 2021.
S. Saha, M.E. Haque, C.P. Tan, M.A. Mahmud, M.T. Arif, S. Lyden, et al., “Diagnosis and Mitigation of Voltage and Current Sensors Malfunctioning in a Grid Connected PV System,” International Journal of Electrical Power & Energy Systems, vol. 115, article no. 105381, 2020.
B. M. Ali, T. J. Al-Musawi, A. Mohammed, H. F. Fakhruldeen, T. M. Hanoon, A. Khurramov, et al., “Sustainable Strategies for Preventive Maintenance and Replacement in Photovoltaic Power Systems: Enhancing Reliability, Efficiency, and System Economy,” Unconventional Resources, vol. 6, article no. 100170, 2025.
D. Deshwal, P. Sangwan, and N. Dahiya, “How Will COVID-19 Impact Renewable Energy in India? Exploring Challenges, Lessons and Emerging Opportunities,” Energy Research & Social Science, vol. 77, article no. 102097, 2021.
J. Wang, X. Teng, and X. Zhang, “Coordinated Control Strategy Based on Photovoltaic Generation Integration,” Proceedings of 11th IET International Conference on Developments in Power Systems Protection (DPSP 2012), IET, pp. 1-4, 2012.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Zakiyyan Zain Alkaf, Bhre Wangsa Lenggana, A'isya Nur Aulia Yusuf, Elsa Sari Hayunah Nurdiniyah, Tri Wisudawati, Ameliyana Rizky Syamara Putri Akhmad Yani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Submission of a manuscript implies: that the work described has not been published before that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication. Authors can retain copyright in their articles with no restrictions. is accepted for publication. Authors can retain copyright of their article with no restrictions.
Since Jan. 01, 2019, AITI will publish new articles with Creative Commons Attribution Non-Commercial License, under The Creative Commons Attribution Non-Commercial 4.0 International (CC BY-NC 4.0) License.
The Creative Commons Attribution Non-Commercial (CC-BY-NC) License permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
