Imagine a wind farm as a team of athletes where the ones in front block the wind for those behind. This project creates a digital brain that coordinates all turbines together instead of letting them act alone. It uses a virtual copy of the farm to predict wind patterns and adjust each turbine in real-time to get the most energy possible while reducing wear and tear.
Wind farms lose energy due to wake effects where front turbines block wind for those behind. Current controls are rule-based and individual, ignoring the farm-wide interaction and leading to higher maintenance costs and lower yields.
An AI-based wind farm control system and multi-scale digital twins (farm, turbine, and component levels) including the DeepWake hybrid 3D wake model.
If you are an operator dealing with wake effects that reduce energy yield—this project developed AI-based cooperative control that can increase farm-wide power production by 15-20% under optimal conditions.
If you are a manufacturer dealing with component degradation in 20MW turbines—this project developed digital twins for load estimation and Remaining Useful Life prediction to enable condition-based maintenance.
If you are a software provider dealing with fragmented and proprietary data infrastructures—this project developed an open, cybersecure software toolchain compatible with industrial SCADA systems.
The project targets a reduction in the Levelized Cost of Energy (LCOE) of at least 6% compared to current industry tools.
Yes, the project specifically includes extensions of the solutions to future 20MW turbines.
Based on available project data, the project aims to deliver an open, cybersecure software toolchain to foster innovation and transparency.
The toolchain is designed to be compatible with industrial SCADA systems.
The project period runs from December 1, 2023, to November 30, 2027.
The consortium is highly industry-weighted with 8 industrial partners (50% of the total), including major players like BP and C-Power. With 16 partners across 7 countries, the project balances academic research from 6 universities with practical industrial application, ensuring the resulting tools are compatible with real-world SCADA systems and operational needs.
Contact Universiteit Gent for technical specifications on the DeepWake model.
Contact us to connect with the ICONIC consortium for early adoption of AI-driven wind control.
