基于数据驱动与知识驱动方法的可再生能源并网系统在线振荡稳定性评估

The increasing integration of renewable energy sources into power networks has elevated the risks of wideband oscillations (WBOs) in modern power systems. Unfortunately, the black/grey-box challenges inherent to renewable energy units (REUs) constrain our ability to effectively address these WBOs. Although impedance measurement or vector fitting methods theoretically offer insights into black/grey-box models, their practical implementations encounter difficulties in real-time online stability assessment. To tackle this problem, a combined data-driven and knowledge-driven method is proposed in this paper to realize the real-time online oscillatory stability assessment of renewable energy integrated systems. Firstly, a data-driven approach is leveraged to develop artificial neural network (ANN)-based wideband impedance identification models (WIIMs) specifically for REUs. Secondly, the real-time wideband impedances of renewable power plants (RPPs) can be obtained online by employing the trained ANN-based WIIMs of REUs, along with physical topology information of RPPs and steady-state operating points of REUs. Subsequently, a practical online oscillatory stability assessment method for complex renewable energy integrated systems is proposed based on the online impedance data of RPPs and other elements in the power systems such as synchronous generator, energy storage system and so on. Finally, a case study of a simplified actual renewable energy integrated system in China is carried out to demonstrate the effectiveness of the proposed method in PSCAD/EMTDC.