ARTIFICIAL INTELLIGENCE FOR OPERATION AND MAINTENANCE OF PV PLANTS
The main objective of the AI4PV project is increasing the operational performance of photovoltaic (PV) plants through the application of Artificial Intelligence by combining Digital Twin technologies with SCADA data analysis.
The expected result is a set of tools for PV plant operation and maintenance (O&M) and Asset Managers to:
- Increase operational reliability and efficiency: high precision of early detection of failures and diagnosis.
- Improve economic performance: downtime reduction of elements and detecting performance problems that can affect energy production.
To achieve these objectives, AI4PV will combine AI-based algorithms and physical modelling of components to build digital assets of the PV power plant, using different technologies such as: unsupervised learning (e.g., with neural networks), modelling and simulation, data collection and interoperability. This approach combines the modelling and simulation of the components, which allows predicting the electrical behaviors and their power generation, compared to the real information observed in them. Compared to a traditional approach based on data analysis, a much more precise discrimination of the problems of such is achieved, especially those with similar symptoms for the same problems (e.g., degradation, soiling of panels, inverter power limitations – clipping, etc.).
International consortium made up of entities from Spain and Portugal with wide experience in energy and Artificial Intelligence: EDP Portugal (leader), ISOTROL and INESCTEC.
Implementation period: 2021 – 2023
Centre for Technological and Industrial Development (CDTI), R&D&I Projects Programme; Co-financed by the European Regional Development Fund (ERDF) through Spain’s Multi-regional Operational Programme 2014-2020. International collaborative project EUR 2020058 with the seal of the AI EUREKA CLUSTER.
Total budget: 813,829 €