Transient Stability Prediction of Power System Combined with Noise Filtering
In order to solve the problem that there is a lot of output noise in actual operation of power system,a transient stability prediction framework for power systems is proposed combined with noise filtering.This framework is based on the generated Covering Distance Filter(CDF)which is combined with the Optimal Sample Selection(OSS)method and Covering Distance(CD)for noise filtering.Then the Light Gradient Boosting Machine(LightGBM)model is used for power system transient stability prediction.The test are conducted on 23-bus system provided by the simulation software and 500-bus real grid in South Carolina,USA.It is shown that the proposed power system transient stability prediction framework can effectively filter noise and has strong robustness.
NETL
NSTL
万方数据
