Enhancing Transient Stability of Power Synchronization Control via Deep Learning

Transient stability of grid-connected converters has become a critical threat to the power systems with high integration level of renewable power generations. Thus, this paper aims to study the transient stability of power synchronization control (PSC) and propose a developed control system by employing deep learning methods. In order to extract and predict the voltage trajectory of the grid-connected converter system, a long short-term memory (LSTM) network has been trained and then integrated to PSC for adapting the synchronization loop of the converter to the grid condition. In the proposed control system, active power reference and internal voltage of the converter are updated dynamically to both satisfy the low voltage ride through (LVRT) requirements of the grid and prevent the loss of synchronization of the converter. The developed control system is validated by time-domain simulations.