Intelligent optimal stepwise inertial control for wind power frequency regulation: a fuzzy logic and SDAE-DNN framework

The rapid integration of wind power into modern power systems, while essential for decarbonization, significantly reduces grid inertia, leading to critical frequency stability challenges following disturbances. Traditional stepwise inertial control (SIC) strategies for wind turbines (WT) often fail to prevent secondary frequency drops (SFD) due to their fixed parameters and lack of synchronization with synchronous generator (SG) recovery dynamics. To address these limitations, this paper proposes a novel optimal SIC framework that leverages fuzzy logic control and a stacked denoising autoencoder-deep neural network (SDAE-DNN) to dynamically adapt wind turbine power output in response to real-time grid conditions. The fuzzy controller intelligently balances grid frequency support with turbine safety by prioritizing rotor speed recovery when approaching critical limits, effectively eliminating SFD. The SDAE-DNN enhances adaptability by learning optimal control parameters across diverse operating scenarios, enabling real-time, computationally efficient implementation. Extensive simulations on the IEEE 39-bus system demonstrate that the proposed strategy can effectively improve the frequency nadir compared to conventional methods and completely avoid SFD. The framework is successfully scaled to wind farm level, ensuring coordinated, secure, and optimal frequency support under high renewable penetration, offering a practical solution for enhancing grid resilience.