基于EWOA-RBFNN的光储VSG自适应控制策略OA

Power disturbances in the grid induce dynamic coupling imbalances between inertia and damping coeffi-cients,resulting in active power overshoot and significant frequency fluctuations in conventional photovoltaic-storage Virtual Synchronous Generators(VSGs).This paper proposes an adaptive control strategy for inertia and damping of photovoltaic-storage VSGs based on an Enhanced Whale Optimization Algorithm(EWOA)combined with a Radial Basis Function(RBF)neural network.By integrating the VSG mathematical and small-signal models,the methods for adjusting inertia and damping parameters and their feasible ranges are analyzed.The EWOA en-hances global optimization of RBF weights through dynamic parameter adaptation and elite individual guidance mechanisms,thereby improving the network's approximation accuracy and generalization capability for nonlinear systems.The optimized RBF neural network dynamically adjusts the VSG's inertia and damping parameters in real time to achieve adaptive control of system dynamic characteristics.Simulation results demonstrate that the proposed strategy effectively suppresses active power overshoot and frequency deviation;although frequency fluctuation slightly increases,the frequency overshoot remains within 0.5%,meeting operational requirements.Moreover,the approach significantly shortens system settling time and enhances transient response performance and overall dy-namic stability.