GPU-accelerated wind farm layout search with a distilled endogenous wake model (EndoWake)
Abstract
We build on EndoWake, an endogenous wake model that links the wind speed at every grid cell to its upwind neighbors by linear constraints, so that wake field, siting decisions and project constraints share one mixed-integer model. Its four parameters are calibrated once on the single wake of a Reynolds-averaged Navier-Stokes (RANS) simulation, and a graphics processing unit (GPU) scores over a million layouts per second per wind direction. At Lillgrund, we compare searches guided by EndoWake and by PyWake under a RANS judge that no search calls: the fidelity of a wake model is not the quality of the layouts optimized under it. Two diagnostics separate a quadrature error between the sampled wind directions from a surrogate bias localized off each wake edge, not reported before to our knowledge; at random directions, five paired starts detect no difference between the pipelines. The main result puts the speed to use: EndoWake ranks the moves of a local search on the GPU, and PyWake confirms every accepted move. On twenty unseen starts, with one GPU and thirty CPU processes, screen-and-confirm reaches similar mean gains to a search on PyWake alone, 7.9 times faster at one wind speed and 14.9 times faster on the annual energy (3.0 and 4.7 with a proof of local optimality charged to the timed search); on a second site it keeps its speed, and its local optima fall slightly short of those of PyWake alone. Code and data are deposited on Zenodo.
Related
- EndoWake: Modeling Wind by Linear Programming for Wind Farm Layout Optimization
- A Dantzig-Wolfe reformulation of the EndoWake model for optimal wind farm layouts
- Sparse Regression Distilled from a Single Robust Fit
- Flexible Wing Co-Design with Active Load Alleviation and Control Surface Layout Optimization
- Optimizing Flexibility and Commitments: Partially-Adaptive Multi-Stage Matrix Assembly Layout Design Problem
BibTeX
@misc{fischetti2026gpuaccelerated,
title = {{GPU-accelerated wind farm layout search with a distilled endogenous wake model (EndoWake)}},
author = {Martina Fischetti and Matteo Fischetti},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.07844},
eprint = {2610.07844},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.07844},
}
RIS
TY - UNPB
TI - GPU-accelerated wind farm layout search with a distilled endogenous wake model (EndoWake)
AU - Martina Fischetti
AU - Matteo Fischetti
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.07844
UR - https://arxiv.org/abs/2610.07844
AB - We build on EndoWake, an endogenous wake model that links the wind speed at every grid cell to its upwind neighbors by linear constraints, so that wake field, siting decisions and project constraints share one mixed-integer model. Its four parameters are calibrated once on the single wake of a Reynolds-averaged Navier-Stokes (RANS) simulation, and a graphics processing unit (GPU) scores over a million layouts per second per wind direction. At Lillgrund, we compare searches guided by EndoWake and by PyWake under a RANS judge that no search calls: the fidelity of a wake model is not the quality of the layouts optimized under it. Two diagnostics separate a quadrature error between the sampled wind directions from a surrogate bias localized off each wake edge, not reported before to our knowledge; at random directions, five paired starts detect no difference between the pipelines. The main result puts the speed to use: EndoWake ranks the moves of a local search on the GPU, and PyWake confirms every accepted move. On twenty unseen starts, with one GPU and thirty CPU processes, screen-and-confirm reaches similar mean gains to a search on PyWake alone, 7.9 times faster at one wind speed and 14.9 times faster on the annual energy (3.0 and 4.7 with a proof of local optimality charged to the timed search); on a second site it keeps its speed, and its local optima fall slightly short of those of PyWake alone. Code and data are deposited on Zenodo.
ER -