
Agile Europe Ltd.
DOCK in Five, reception C
Boudnikova 2538/13
Prague 8, 180 00
Czech Republic, EU
ID number: 28236891
Tax ID: CZ28236891
Services
Copyright © 2023 Agile Europe - All Rights Reserved!
Many years of experience in the operation of different types of solar power plants in various environments allow us to use artificial intelligence methods applied to detailed operational data in order to anticipate possible risk situations and eliminate them by proactive service intervention.
Predictive AGL Solar Monitoring uses advanced analysis tools based on machine learning methods and our many years of experience in operating various types of solar photovoltaic power plants.
Input data is a time series of operational data from inverters, charging controllers and batteries, lighting and weather sensors, which provides a basic monitoring system for predictive analysis.
An important parameter is the estimation of future production based on weather forecast, power plant status and historical operating data. This estimation can be used both to identify failures in predictive monitoring and, on the other hand, by the investor for other purposes.
The system can identify substandard behavior and increased risk of failure of power plant components. The recommendations of the predictive monitoring system are then assessed by the technician, who proposes to the plant operator a proactive intervention on site with possible repair or replacement of the risk component. The purpose of the service is to optimize production by eliminating the probable cause of the malfunction before the failure occurs.
As a result, we are able to respond effectively to changes and adapt to new situations that arise in each project.
We consider reliability to be the foundation of trust and, above all, reliability significantly reduces the stress that is also present in any project.
Because we believe in our products, services and solutions, we are ready to take responsibility for their quality, which is corner stone of our efforts.
For optimal operation and utilization of power resources supplied by us, we employ machine learning methods in applications of predictive maintenance, management of solar hybrid and battery systems or estimation of future power generation.