The week's pick
Random Articles
Reseach Article
Methodology for Anomaly Detection and Alert Generation in Photovoltaic Systems
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 36 |
| Year of Publication: 2024 |
| Authors: Roberto Alexandre Dias, Mário de Noronha Neto, Gregory Chagas da Costa Gomes, Fernando Benites, Stefan Gürtler, Siqueira de Moraes Neto, Níkola Zaia de Figueiredo |
10.5120/ijca2024923966
|
Roberto Alexandre Dias, Mário de Noronha Neto, Gregory Chagas da Costa Gomes, Fernando Benites, Stefan Gürtler, Siqueira de Moraes Neto, Níkola Zaia de Figueiredo . Methodology for Anomaly Detection and Alert Generation in Photovoltaic Systems. International Journal of Computer Applications. 186, 36 ( Aug 2024), 9-15. DOI=10.5120/ijca2024923966
Abstract
This article presents a methodology for identifying anomalies and generating alerts during the management of photovoltaic plants. The approach is mainly based on the analysis of AC power from inverters, eliminating the need for additional instrumentation. The methodology can be enhanced with solar irradiance data, enabling more precise anomaly detection and alert generation based on the Performance Ratio (PR) concept. The autoencoder technique was employed to detect anomalies in inverters using custom models based on equipment size, region, as well as specific times of day and year. Alert generation considers the quantity of detected anomalies and PR variation over a 30-day period. To validate the results, plants with previously recorded shading and 5k inverters in the regions of Santa Catarina and São Paulo (Brazil) were used. The obtained results demonstrated excellent performance in plant management, allowing for the analysis of anomaly recurrence and alert level variations over time.
References
- Barraz, Z., Ait Abdelmoula, I., Lamrini, N., & Sebari, I. (2023). Production-Ready Deep Learning Model Optimization for Anomaly Detection in Photovoltaic Systems.
- Miraftabzadeh, S., Longo, M., Foiadelli, F., & Bracco, S. (2023). Anomaly Detection in Photovoltaic Systems via Deep Learning Autoencoder.
- Doukha, R., Mahmoudi, S., Zbakh, M., & Manneback, P. (2020). Deployment of Containerized Deep Learning Applications in the Cloud.
- Livera, A.; Theristis, M.; Makrides, G.; Georghiou, G.E. Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems. Renewable Energy, v. 133, p. 126-143, 2019.
- Tsafarakis, O.; Sinapis, K.; van Sark, W.G.J.H.M. A Time-Series Data Analysis Methodology for Effective Monitoring of Partially Shaded Photovoltaic Systems. Energies, v. 12, n. 1722, 2019. DOI: 10.3390/en12091722.
- Platon, R.; Martel, J.; Woodruff, N.; Chau, T.Y. Detecção de Falhas Online em Sistemas PV. IEEE Transactions on Sustainable Energy, v. 6, n. 4, outubro de 2015. DOI: 10.1109/TSTE.2015.2421447.
- Park, T.; Song, K.; Jeong, J.; Kim, H. "Convolutional Autoencoder-Based Anomaly Detection for Photovoltaic Power Forecasting of Virtual Power Plants". Energies, v. 16, n. 5293, 2023. DOI:10.3390/en16145293.
- A. Chouder, S. Silvestre, "Automatic supervision and fault detection of FV systems based on power losses analysis," in Energy Conversion and Management, vol. 51, pp. 1929-1937, 2010
- S. Hawkins, H. He, G. Williams, & R. Baxter. “Outlier detection using replicator neural networks.” In International Conference on Data Warehousing and Knowledge Discovery (pp. 170-180). Berlin, Heidelberg: Springer Berlin Heidelberg, 2002.
Index Terms
Keywords