Lune

KDD2025Top-tier venue

Wind Farm Layout Optimization with Diffusion Models

Yujin Shin, Taeyoung Yun, Sujin Yun, Sungpil Woo, Sunhwan Lim, Jinkyoo Park

Abstract

Wind farms generate electricity from wind, offering a sustainable and eco-friendly power source. In wind farms, determining the positions of wind turbines is crucial for high energy production due to complex wake interactions. However, optimizing wind farm layouts for given wind conditions remains challenging. While existing methods try to solve the problem by training a surrogate model and employing optimization algorithms based on the model, these methods require a large number of simulations to obtain highly productive layouts, which is time-consuming in large-scale tasks. Furthermore, they mostly yield less diverse layouts, making the deployment of such layouts into real-world scenarios difficult. To address these challenges, we introduce a novel conditional generative modeling approach to find wind farm layouts that maximize energy production. Our method consists of four stages. First, we collect datasets that consist of layouts and their corresponding annual energy production (AEP). Then, we train a diffusion model conditioned on AEP and wind scenarios using the collected dataset. Specifically, we use a Graph Neural Network as the backbone for the denoising network to ensure permutation invariance. Next, we sample promising layouts from the trained diffusion model by conditioning with a high AEP and given wind scenario. We also introduce a local search algorithm, which enables us to adjust layouts that violate design constraints. Finally, we evaluate the generated layouts and augment the dataset. We repeat these processes iteratively to further optimize the layouts. Throughout these processes, we effectively generate highly productive and diverse wind farm layouts in a sample-efficient manner. Experimental results demonstrate that our approach outperforms state-of-the-art methods in maximizing energy production across various scenarios.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Elucidating the Design Space of Diffusion-Based Generative Models cites Denoising Diffusion Probabilistic Models
  • Conservative Objective Models for Effective Offline Model-Based Optimization cites Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
  • Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization cites Conservative Objective Models for Effective Offline Model-Based Optimization
  • Diffusion Models Beat GANs on Topology Optimization cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on6

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Elucidating the Design Space of Diffusion-Based Generative ModelsTero Karras, Miika Aittala, Timo Aila, Samuli LaineNeurIPS 2022 · 3,959 citations
  3. Diffusion Models Beat GANs on Topology OptimizationFrançois Mazé, Faez AhmedAAAI 2023 · 128 citations
  4. Design-Bench: Benchmarks for Data-Driven Offline Model-Based OptimizationBrandon Trabucco, Xinyang Geng, Aviral Kumar, Sergey LevineICML 2022 · 126 citations
  5. Conservative Objective Models for Effective Offline Model-Based OptimizationBrandon Trabucco, Aviral Kumar, Xinyang Geng, Sergey LevineICML 2021 · 119 citations

Related papers

  1. LayoutDM: Transformer-based Diffusion Model for Layout GenerationShang Chai, Liansheng Zhuang, Fengying YanCVPR 2023
  2. Generative Layout Modeling using Constraint GraphsWamiq Para, Paul Guerrero, Tom Kelly, Leonidas J. Guibas et al.ICCV 2021 · 93 citations
  3. DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion ModelsSohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee et al.ICLR 2024 · 21 citations
  4. Cons2Plan: Vector Floorplan Generation from Various Conditions via a Learning Framework based on Conditional Diffusion ModelsShibo Hong, Xuhong Zhang, Tianyu Du, Sheng Cheng et al.ACM MM 2024 · 6 citations
  5. UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout GenerationZeyang Liu, Le Wang, Sanping Zhou, Yuxuan Wu, Xiaolong Sun, Gang Hua, Haoxiang LiCVPR Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines