Related Experiment Video
Updated: Jun 26, 2026
08:16
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
Published on: October 24, 2025
918
Assessment and optimisation of regional scale wind farm deployment using machine learning.
Simon C Warder1, Mariana C A Clare2, B Bhaskaran3
1Department of Earth Science and Engineering, Imperial College London, London, UK. s.warder15@imperial.ac.uk.
Communications Engineering
|April 29, 2026
Summary
Offshore wind farms face increasing power losses from inter-farm wakes. A new machine learning tool estimates these losses, showing careful planning can reduce them by one third, saving millions.
Area of Science:
- Renewable Energy Engineering
- Computational Fluid Dynamics
- Machine Learning Applications
Background:
- Scaling up offshore wind energy presents challenges, including the significant impact of inter-farm wakes on overall energy production.
- Accurate modeling of wake effects is crucial for effective regional planning and mitigation strategies in large-scale offshore wind deployments.
Purpose of the Study:
- To develop and apply a machine learning-based workflow for estimating power losses caused by inter-farm wakes in offshore wind farms.
- To assess the projected increase in wake-induced power losses for future offshore wind build-out scenarios, specifically in the North Sea.
- To demonstrate the tool's capability in optimizing wind farm fleet design and spatial planning for maximum power output and economic gain.
Main Methods:
- Development of a machine learning workflow to simulate and quantify power losses due to inter-farm wake effects.
- Application of the developed tool to analyze planned offshore wind build-out in the North Sea.
- Optimization of future wind farm locations to minimize wake-induced losses and maximize total fleet power output.
Main Results:
- Estimated power losses due to inter-farm wakes are projected to more than double, reaching 2.4% of total output.
- Increased wake losses are expected during summer, potentially amplifying natural seasonal variations in wind resource availability.
- Optimization of farm locations through spatial planning can reduce wake-induced losses by one third, yielding substantial economic benefits (£160m annually).
Conclusions:
- The developed machine learning tool provides an efficient method for assessing and mitigating inter-farm wake impacts in offshore wind energy.
- Strategic spatial planning of offshore wind farms is critical for minimizing energy losses and maximizing economic returns, especially under future expansion scenarios.
- Addressing wake effects through advanced modeling and planning is essential for the continued growth and efficiency of the offshore wind sector.
