Design of an Adaptive Neuro-Fuzzy Damping Controller for Grid-Integrated Hybrid Microgrids Incorporating Wind Energy and Battery Storage Systems

The increasing integration of renewable energy sources (RESs), such as wind turbines and photovoltaic (PV) arrays, introduces low-inertia characteristics that negatively affect the dynamic stability of modern power systems. To address this challenge, this study proposes an Adaptive Neuro-Fuzzy Damping Controller (ANFDC) based on a high-voltage direct current (HVDC) link to enhance system damping and stability. The controller employs a fuzzy linguistic rule to tune its parameters, converting dynamic input signals into linguistic variables during an offline training phase. A hybrid microgrid system combining offshore and onshore wind turbines, PV units, and small-scale synchronous generators (SSSGs) is used to train and validate the controller. During real-time operation, the ANFDC adaptively adjusts control signals to mitigate oscillations without relying on an explicit system model. The proposed method effectively integrates the strengths of neural networks and fuzzy logic to achieve fast, robust, and adaptive damping control. Simulation results on a grid-connected hybrid microgrid under various short-circuit faults demonstrate that the ANFDC significantly improves damping performance and maintains high stability margins compared with conventional control approaches.