The large random volatility of wind power and photovoltaic power generation connected to the grid results in the subsynchronous oscillation of the power system exhibiting the characteristics of random time-varying amplitude and frequency. Accurately identifying the subsynchronous oscillation mode is monitoring the subsynchronous harmonic transmission and suppression. The basics. Aiming at the limitations of the existing subsynchronous oscillation mode identification method in analyzing the time-varying amplitude frequency signal and the problem of insufficient identification accuracy, this paper proposes an improved Hilbert-Huang transform (HHT) using the image extension method. The stochastic time-varying subsynchronous oscillation mode is identified. The simulation example shows that the method can not only accurately identify the frequency and damping ratio of the subsynchronous harmonics, but also improve the HHT endpoint effect and improve the accuracy of subsynchronous oscillation mode identification.