INL Cluster

Development of an integrated software tool for PV plant fault prediction using AI

The production of photovoltaic solar energy (PV) has grown significantly and both the associated technology and the configuration of the plants are changing disruptively. Instead of easily accessible megawatt (MW) plants, with only one type of technology available, the new configurations are hundreds of MW installed in various locations, and with various technologies involved. Thus, PV plant operators are not prepared to optimize and maximize the profitability of these new types of assets.
In this context of paradigm shift and the lack of efficient solutions for the management of these new
PV assets, the main target of SMART-PV is to develop a cloud computing platform that will integrate predictive algorithms based on machine learning and Artificial Intelligence, allowing to optimize the
Operation, Preventive Maintenance and Technical Assistance processes in large PV plants. The platform will combine the acquisition and management of information through intrinsic data generated by PV production plants, to generate a preventive maintenance predictive procedure aimed, primarily, at large PV plants located in any location.
SMART-PV results from the partnership and co-promotion between DST SOLAR, a company with extensive experience in planning, managing and commissioning of PV assets, and the project’s leading promoter, and three SCTN entities with relevant skills in monitoring the performance of solar assets through tests and fields measurements (IEP), identifying and characterizing of degradation mechanisms of solar cells and in advanced image recognition techniques (INL) and in intelligent algorithms using machine learning and Artificial Intelligence, applied to energy asset management (INESC TEC).

Total Eligible Budget

1,197,437.56 €

INL Eligible Budget

332,732.53 €

Total Funding

792,383.89 €

INL Funding

249,549.40 €

Start Date


End Date


Type of action

SI – Projetos em Copromoção

Grant Agreement Id


Funding Agency




Funding Framework


INL Role


Intervention Region

North of Portugal