A machine learning method for locating subsynchronous oscillation source of VSCs in wind farm induced by open-loop modal resonance based on measurement

In recent years, sub-synchronous oscillation incidents have been reported to happen globally, which seriously threatens the safe and stable operation of power system. It is difficult locate source in practice using parameterized model open-loop modal resonance. Therefore, this paper aims at problem instability caused by interaction between multiple voltage converters wind farm grid-connected system, proposes a method for locating measurement data based on transfer learning algorithm component analysis. At same time, order solve lack inability label real simplified simulation system was proposed generate large batches labeled training samples. Then, common features samples from were learned through analysis algorithm. Afterward, classifier trained classify with features. Finally, two farms VSC access are used verify that has good performance. This important reference value practical application grid dispatching identify sources.