Back to Observatory
Method of monitoring and detection of failures in PV system based on machine learning techniques
Description of the service
Machine learning methods have been used to solve complicated practical problems in different areas and are becoming increasingly popular. This paper evaluates the prediction of the energy production of three photovoltaic systems and the monitoring of measurement sensors through machine learning and data mining in response to the behavior of the climatic variables of the site under study. It also considers implementing the resulting models in the SCADA system through indicators, allowing the operator to manage the power grid, and offers a real-time simulation and prediction strategy of photovoltaic systems and measurement sensors in the concept of smart grids.
Problem that it solves
To assess energy production prediction of three photovoltaic systems and the monitoring of measurement sensors through machine learning and data mining in response to the behavior of the climatic variables of the site under study.Type of AI app used
Events detection (anomaly detection and early warning), Customization, Prediction
Main results to June 30, 2021
As industrial development increases, automation and processes generate more data and information and require further analysis, interpretation, and communication. This study demonstrated the application of machine learning techniques in analyzing real-life data and developing predictive models. It showed that it is possible to predict the photovoltaic power of three systems using regression models with an excellent approximation.
Three main bottlenecks faced during implementation
- Data quality
- Operating efficiency
Lessons learned in the design or use of AI for social impact
Process monitoring: The application of a fault detection strategy has been demonstrated through predictive modeling techniques in photovoltaic systems, allowing to monitor photovoltaic systems by comparing real-time photovoltaic and the values calculated based on radiation and temperature.
Country of origin
Geographic scope of operations
Cuenca
Type of executing entity
UniversitySector/industry
Sustainable Development Goal(s) to which your AI solution contributes
7 (affordable and clean energy)
IA app developed internally or by a third party
Internally
Name of implementing entity
Universidad de Málaga-Universidad de Cuenca
Stakeholders involved
Dario Javier Benavides, Paul Arévalo-Cordero, Luis G. González.
Percentage of the development team that are women
0%
Year they started using AI-based models
2021It may interest you
Posibilidades y riesgos de la inteligencia artificial en el Estado digital
Marco conceptual y metodológico
This self-assessment tool is designed to allow the mitigation of ethical risks associated with the use/application of new technologies. It is available so that the ethical performance of each system can be evaluated from the beginning.