Benchmarking Time-Series Anomaly Detection Algorithms for Photovoltaic Plants
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Photovoltaic (PV) systems are increasingly important for renewable energy generation, but faults can reduce yield if they remain undetected. This paper presents a benchmark of multivariate time-series anomaly detection (TSAD) methods for PV monitoring using two complementary datasets: a newly collected real-world twin-plant PV dataset (FHC), in which controlled faults were physically introduced during operation and additional anomalies were injected after data collection, and the publicly available PV fault dataset (UTFPR). Using the TimeEval framework, we evaluate a broad range of unsupervised and semi-supervised TSAD algorithms on the FHC dataset, and only unsupervised algorithms on the UTFPR dataset, as the latter does not contain fault-free days required for semi-supervised training. On the FHC dataset, the highest performance is achieved by semi-supervised reconstruction-based methods. On the UTFPR dataset, fully unsupervised distance- and density-based methods perform best. The ablation study further shows that environmental features do not necessarily improve detection performance and may introduce confounding operating-regime structure for some algorithms. These findings highlight the importance of dataset characteristics and feature selection when applying TSAD methods to PV monitoring.
How to Cite
##plugins.themes.bootstrap3.article.details##
photovoltaic fault detection, time-series anomaly detection, PV monitoring, semi-supervised learning, unsupervised learning, anomaly detection benchmarking
Alhazmi, A., Kholoud, M., & Eke, C. I. (2025). A systematic review of advances in deep learning architectures for efficient and sustainable photovoltaic solar tracking: Research challenges and future directions. Sustainability, 17(21), 9625.
Amiri, A. F., Kichou, S., Oudira, H., Chouder, A., & Silvestre, S. (2024). Fault detection and diagnosis of a photovoltaic system based on deep learning using the combination of a convolutional neural network (CNN) and bidirectional gated recurrent unit (Bi-GRU). Sustainability, 16(3), 1012.
Bashar, M. A., & Nayak, R. (2020). TAnoGAN: Time series anomaly detection with generative adversarial networks. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1778–1785).
Berghout, T., Benbouzid, M., Bentrcia, T., Ma, X., Djurović, S., & Mouss, L.-H. (2021). Machine learning-based condition monitoring for PV systems: State of the art and future prospects. Energies, 14(19), 6316.
Bradl, H., Hofer-Schmitz, K., Grippa, P., & Hofer, G. (2026). FHC Twin-Plant Photovoltaic Anomaly Detection Dataset [Data set]. Zenodo. doi: 10.5281/zenodo.18979877
Branco, P., Gonçalves, F., & Costa, A. C. (2020). Tailored algorithms for anomaly detection in photovoltaic systems. Energies, 13(1), 225.
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). LOF: Identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data (pp. 93–104).
Chen, Q., Zhang, A., Huang, T., He, Q., & Song, Y. (2020). Imbalanced dataset-based echo state networks for anomaly detection. Neural Computing and Applications, 32(8), 3685–3694.
Cheng, Z., Zou, C., & Dong, J. (2019). Outlier detection using isolation forest and local outlier factor. In Proceedings of the Conference on Research in Adaptive and Convergent Systems (pp. 161–168). Association for Computing Machinery. doi: 10.1145/3338840.3355641
Ember. (2026). European electricity review 2026 [Technical report]. Ember. Retrieved from https://ember-energy.org/app/uploads/2026/01/EMBER-Report-European-Electricity-Review-2026.pdf
Gaviria, J. F., Narváez, G., Guillen, C., Giraldo, L. F., & Bressan, M. (2022). Machine learning in photovoltaic systems: A review. Renewable Energy, 196, 298–318.
Goldstein, M., & Dengel, A. (2012). Histogram-based outlier score (HBOS): A fast unsupervised anomaly detection algorithm. In Proceedings of the German Conference on Artificial Intelligence (KI) Poster and Demo Track (pp. 59–63).
Hariri, S., Kind, M. C., & Brunner, R. J. (2021). Extended isolation forest. IEEE Transactions on Knowledge and Data Engineering, 33(4), 1479–1489. doi: 10.1109/TKDE.2019.2947676
He, Z., Xu, X., & Deng, S. (2003). Discovering cluster-based local outliers. Pattern Recognition Letters, 24(9–10), 1641–1650.
Heim, N., & Avery, J. E. (2019). Adaptive anomaly detection in chaotic time series with a spatially aware echo state network. arXiv preprint arXiv:1909.01709.
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., & Soderstrom, T. (2018). Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 387–395).
Khandeparkar, V., Shreshtha, & Ramu, S. K. (2025). Effectiveness of supervised machine learning models for electrical fault detection in solar PV systems. Scientific Reports, 15(1), 34919.
Lazzaretti, A. E., Costa, C. H. d., Rodrigues, M. P., Yamada, G. D., Lexinoski, G., Moritz, G. L., ... others. (2020). A monitoring system for online fault detection and classification in photovoltaic plants. Sensors, 20(17), 4688.
Li, B., Delpha, C., Diallo, D., & Migan-Dubois, A. (2021). Application of artificial neural networks to photovoltaic fault detection and diagnosis: A review. Renewable and Sustainable Energy Reviews, 138, 110512.
Li, Z., Zhao, Y., Botta, N., Ionescu, C., & Hu, X. (2020). COPOD: Copula-based outlier detection. In 2020 IEEE International Conference on Data Mining (ICDM) (pp. 1118–1123). doi: 10.1109/ICDM50108.2020.00135
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining (pp. 413–422). doi: 10.1109/ICDM.2008.17
Liu, Y., Duran, E., Bruce, A., Yildiz, B., Severiano, B. M., Ibrahim, I. A., ... Rougieux, F. (2025). A methodological review of cost-effective data-driven fault detection and diagnosis in distributed photovoltaic systems. Applied Energy, 401, 126636.
Lu, Y., Wu, R., Mueen, A., Zuluaga, M. A., & Keogh, E. (2022). Matrix profile XXIV: Scaling time series anomaly detection to trillions of datapoints and ultrafast arriving data streams. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 1173–1182). Association for Computing Machinery. doi: 10.1145/3534678.3539271
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016). LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148.
Malhotra, P., Vig, L., Shroff, G., Agarwal, P., et al. (2015). Long short-term memory networks for anomaly detection in time series. In Proceedings (Vol. 89, p. 94).
Miraftabzadeh, S. M., Longo, M., Leva, S., & Matera, N. (2025). Data anomaly detection in photovoltaic power time series via unsupervised deep learning with insufficient information. Sustainable Energy, Grids and Networks, 43, 101769.
Munir, M., Siddiqui, S. A., Dengel, A., & Ahmed, S. (2018). DeepAnT: A deep learning approach for unsupervised anomaly detection in time series. IEEE Access, 7, 1991–2005.
Paffenroth, R., Kay, K., & Servi, L. (2018). Robust PCA for anomaly detection in cyber networks. arXiv preprint arXiv:1801.01571.
Ramaswamy, S., Rastogi, R., & Shim, K. (2000). Efficient algorithms for mining outliers from large data sets. In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data (pp. 427–438).
Rousseeuw, P. J., & Driessen, K. V. (1999). A fast algorithm for the minimum covariance determinant estimator. Technometrics, 41(3), 212–223. doi: 10.1080/00401706.1999.10485670
Sakurada, M., & Yairi, T. (2014). Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis (pp. 4–11).
Schmidl, S., Wenig, P., & Papenbrock, T. (2022). Anomaly detection in time series: A comprehensive evaluation. Proceedings of the VLDB Endowment, 15(9), 1779–1797.
Seghiour, A., Bendjeddou, Y., Mostefaoui, I. M., Chouder, A., Alharbi, H., Humayd, A. S. B., ... Babqi, A. (2026). Fault detection and diagnosis in photovoltaic systems using artificial intelligence and time–frequency analysis. Scientific Reports.
Senin, P., Lin, J., Wang, X., Oates, T., Gandhi, S., Boedihardjo, A. P., ... Frankenstein, S. (2015). Time series anomaly discovery with grammar-based compression. In Proceedings of the International Conference on Extending Database Technology (EDBT). doi: 10.5441/002/edbt.2015.42
Shyu, M.-L., Chen, S.-C., Sarinnapakorn, K., & Chang, L. (2003). A novel anomaly detection scheme based on principal component classifier. In Proceedings of the IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 172–179).
Song, H., Jiang, Z., Men, A., & Yang, B. (2017). A hybrid semi-supervised anomaly detection model for high-dimensional data. Computational Intelligence and Neuroscience, 2017(1), 8501683.
Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., & Pei, D. (2019). Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2828–2837).
Tang, J., Chen, Z., Fu, A. W.-C., & Cheung, D. W. (2002). Enhancing effectiveness of outlier detections for low-density patterns. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 535–548).
Toche Tchio, G. M., Kenfack, J., Kassegne, D., Menga, F.-D., & Ouro-Djobo, S. S. (2024). A comprehensive review of supervised learning algorithms for the diagnosis of photovoltaic systems, proposing a new approach using an ensemble learning algorithm. Applied Sciences, 14(5), 2072.
Wenig, P., Schmidl, S., & Papenbrock, T. (2022). TimeEval: A benchmarking toolkit for time series anomaly detection algorithms. Proceedings of the VLDB Endowment, 15(12), 3678–3681. doi: 10.14778/3554821.3554873
Yairi, T., Kato, Y., & Hori, K. (2001). Fault detection by mining association rules from housekeeping data. In Proceedings of the 6th International Symposium on Artificial Intelligence, Robotics and Automation in Space (Vol. 18, p. 21).
Yeh, C.-C. M., Zhu, Y., Ulanova, L., Begum, N., Ding, Y., Dau, H. A., ... Keogh, E. (2016). Matrix profile I: All pairs similarity joins for time series: A unifying view that includes motifs, discords and shapelets. In 2016 IEEE 16th International Conference on Data Mining (ICDM) (pp. 1317–1322). doi: 10.1109/ICDM.2016.0179
Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2024). Deep learning for time series anomaly detection: A survey. ACM Computing Surveys, 57(1), 1–42.
Zhao, H., Wang, Y., Duan, J., Huang, C., Cao, D., Tong, Y., ... Zhang, Q. (2020). Multivariate time-series anomaly detection via graph attention network. In 2020 IEEE International Conference on Data Mining (ICDM) (pp. 841–850).
Ziegelmeir, J. (2019). Development and comparison of self-learning modules for automated bench test data analysis of transient flight engine development tests [Master’s thesis, Technische Universität Berlin].
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.