Gpu speeds wind farm design search nearly ten times faster
GPU-accelerated wind farm layout search with a distilled endogenous wake model (EndoWake)
Computational Engineering, Finance, and Science
Summary
Deciding the best places to put wind turbines to capture the most energy is a complex task because of how wind slows down behind turbines, called wake effects. The authors improved a computer model, EndoWake, that runs on graphics cards (GPUs) to rapidly test many turbine arrangements. They found this method, combined with a detailed check, produces designs as good as traditional slower methods but much faster. Their work also discovered new subtle issues in existing models, helping future improvements.
What this means in practice
- •For wind farm planners: Test many wind turbine placements quickly to find energy-maximizing designs without expensive detailed simulations.
- •For renewable energy software developers: Integrate GPU-accelerated wake modeling to speed up turbine layout optimization tools while maintaining design quality.
Authors
Martina Fischetti, Matteo Fischetti
Abstract
Wind farm layout optimization decides where to place turbines to maximize annual energy production, and wake effects decide how much of that energy is produced. Accurate wake models are too slow for a search. We build on EndoWake, an endogenous wake model in which the wind speed at every grid cell is a variable linked 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 against the single-wake field of a Reynolds-averaged Navier-Stokes (RANS) simulation, and a GPU scores over a million layouts per second per wind direction. Comparing EndoWake-guided searches with a PyWake-based pipeline at Lillgrund, under a RANS judge that no search calls, revealed that the fidelity of a wake model is not the quality of the layouts optimized under it. A search is drawn to the gaps between sampled wind directions, the sirens; a diagnostic of the field finds a second artifact, an optimistic band off each wake edge, the mermaid cells, not reported before to our knowledge. Judged at random directions, the two pipelines are statistically indistinguishable. Our main result puts this speed to use: EndoWake screens the candidate 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, this screen-and-confirm search matches the PyWake value of a search on PyWake alone 7.9 times faster, and 14.9 times faster on the annual energy.