Review on Dynamic Inflow Sensing Layout Optimization for Large-Scale Wind Farms: Wake Modeling, Data-Driven Prediction, and Multi-Objective Uncertainty Optimization

Large-scale wind farms operate under highly unsteady atmospheric inflows, where transient turbulence, dynamic wake interactions, and inflow-wake coupling reduce energy production and exacerbate turbine loads. Over the past five years, advances in high-fidelity computational fluid dynamics (CFDs), large eddy simulation (LES), machine learning (ML)-based wake modeling, and multi-objective optimization have reshaped wind farm layout optimization under dynamic inflow conditions. This review synthesizes recent progress in five key areas: dynamic inflow and high-fidelity wake modeling (including LES-driven transient wake evolution and turbulence-resolved inflow generation), data-driven wake prediction, multi-objective layout optimization (considering the annual energy production (AEP), fatigue load constraints, and the levelized cost of energy (LCOE)), blockage modeling for complex terrain and yaw misalignment, and real-time optimization addressing inflow, turbine performance, and modeling uncertainties. Coupling transient wake models with surrogate-assisted multi-objective optimization enables a computationally efficient and physically consistent layout design. Key open challenges (dynamic wake controllability, real-time optimization under uncertainty, and integration with next-generation farm-level control systems) and future directions for enhancing large-scale wind farm resilience and cost-competitiveness are also identified. However, despite significant progress, existing models still face fundamental limitations, such as oversimplified treatment of complex turbulence structures, poor generalization under extreme or atypical conditions, and inadequate capture of long-timescale dynamic responses, which constrain their reliability in practical optimization settings.