<p>The large-scale integration of renewable energy sources has brought significant frequency oscillation issues to power systems, posing severe challenges to the stable operation of power systems. This paper proposes an adaptive control strategy for Virtual Synchronous Generator (VSG) based on Adaptive Model Predictive Control-Radial Basis Function (AMPC-RBF). This method improves the calculation mechanism of traditional Model Predictive Control (MPC) by dynamically adjusting the weight coefficients of the objective function in real time based on frequency variations, thereby achieving adaptive tuning of MPC weight coefficients and significantly enhancing the dynamic response performance of the VSG. Meanwhile, a dual-input and dual-output Radial Basis Function (RBF) neural network is designed to dynamically tune the virtual inertia and damping coefficients of the VSG, achieving a more refined frequency regulation effect. A simulation model is developed in the MATLAB/Simulink environment, and comparative analyses are performed with existing control strategies. The simulation results confirm that the proposed AMPC - RBF method can effectively suppress the frequency and power oscillations of the VSG, decrease the time required for the system to reach a stable state, and notably improve the overall stability of the power system.</p>