可再生能源2025，Vol.43Issue(4)：484-490,7.
基于尾流加速估计与强化学习的风机偏航优化方法
An optimization method for wind turbine yaw control based on accelerated wake estimation and reinforcement learning
摘要
Abstract
As China's new energy capacity grows and offshore wind power advances,controlling wind farms becomes more crucial.The study focuses on wake effect modeling and active control strategies within wind farm clusters.It optimizes wake estimation using the Gaussian FLORIDyn model,with search area pruning to speed up calculations without sacrificing precision or efficiency.A novel multi-agent reinforcement learning method,guided by a GCN-based proxy wake model,is introduced.This model,grounded in wind farm wake dynamics,captures complex turbine interactions affecting output.Enhanced by wake-aware reward sharing,the system improves optimization.Simulations test pruning's benefits and validate control strategies,confirming that advanced wake modeling and control tactics significantly contribute to solving wind farm control problems.关键词
偏航优化/尾流估计/高斯FLORIDyn/多智能体强化学习/高性能仿真Key words
yaw optimization/wake estimation/gaussian FLORIDyn/multi-agent reinforcement learning/high-performance simulation分类
能源与动力引用本文复制引用
陈玥,刘洋,陆秋瑜,谢平平,丁俐夫..基于尾流加速估计与强化学习的风机偏航优化方法[J].可再生能源,2025,43(4):484-490,7.基金项目
南方电网公司科技项目资助[项目编号:036000KK52222044(GDKJXM20222430)]. （GDKJXM20222430）
