Deeptrack: Enhancing Solar Energy Efficiency With AI-Optimized PV Tracking Systems In Germany – SolarQuarter

Photovoltaic (PV) systems equipped with solar trackers have been shown to increase energy yield by 20 to 30 percent compared to fixed ground-mounted systems. These systems not only maximize energy output but also consider other factors in their design and alignment, such as the light requirements for specific plant varieties in agrivoltaic (APV) and biodiversity-PV systems, as well as the timing of grid feed-in during different times of the day.

In the research project “DeepTrack,” Zimmermann PV-Tracker GmbH, a division of the Zimmermann PV-Steel Group, and the Fraunhofer Institute for Solar Energy Systems ISE are collaborating to enhance tracking algorithms. They are utilizing a digital twin powered by deep learning to develop optimized control strategies. This digital twin learns from data collected by its “real” counterpart, a PV tracker built by Zimmermann PV-Tracker, which is located at Fraunhofer ISE’s Outdoor Performance Lab in Merdingen near Freiburg, Germany.

According to the International Technology Roadmap for Photovoltaics, published by the German Engineering Federation (VDMA), it is predicted that 60 percent of all PV power plants worldwide will use tracker systems in the future. In countries with high solar radiation levels, like Spain, such systems already dominate the newly built ground-mounted PV installations. Germany is also expected to see significant growth in APV systems with trackers following the incorporation of “Solar Package I” into the German Renewable Energy Sources Act (EEG). Hannes Elsen, product manager at Zimmermann PV, highlights the potential for optimized tracking algorithms in APV systems, given the diversity of crops and systems involved.

In the “DeepTrack” project, Zimmermann PV-Tracker GmbH installed one of its tracking PV systems at Fraunhofer ISE’s outdoor test field to gather real-world data. Using these measurements, the project consortium developed a digital twin that integrates PV monitoring and modeling tools with weather forecasts through deep learning. This allows for the calculation of optimal tracking positions for the PV modules in various scenarios.

Dr. Matthew Berwind, team leader at Fraunhofer ISE, explains that the initial control sequences were designed to maximize electricity yield from bifacial solar modules or to create the best conditions for the plants beneath the APV system. The next challenge is to combine these two approaches to optimize both aspects simultaneously. Achieving this balance is complex but feasible with the AI-based approach being developed.

The “DeepTrack” research project is supported by the InvestBW funding program of the Baden-Wuerttemberg Ministry of Economic Affairs, Labor and Tourism and is scheduled to run until early 2025. Throughout this period, researchers will continue to refine and validate the digital twin model by consistently comparing it with actual performance data. This continuous comparison ensures the reliability and effectiveness of this innovative technology.

The importance of such advancements cannot be overstated. As the demand for renewable energy sources increases globally, the optimization of PV systems becomes crucial. The ability to accurately track and adjust PV modules based on real-time data and forecasts significantly enhances energy efficiency and yield. This, in turn, supports broader goals of sustainability and energy independence.

Moreover, the integration of these advanced tracking systems in APV settings presents a unique opportunity to combine agriculture and energy production harmoniously. By ensuring that crops receive adequate sunlight while simultaneously generating solar power, these systems promote a more sustainable and efficient use of land. This dual benefit is particularly relevant in regions where land resources are limited, and the need for both food and energy security is high.

The “DeepTrack” project represents a significant step forward in the development of smarter, more efficient PV systems. By leveraging the power of deep learning and digital twins, researchers and industry partners are paving the way for a future where solar energy production is maximized, and the environmental impact is minimized. As the project progresses, it promises to deliver valuable insights and technologies that could be adopted on a wider scale, contributing to the global transition towards clean and renewable energy sources.

Related

This post was originally published on 3rd party site mentioned in the title of this site