Research on Security Early Warning Method of Power Secondary System in New Energy Field Stations
New energy field station power secondary system has a large number of equipment.It's safety early warning related data exists obvious high dimensionality,complexity,is not conducive to the efficiency and accuracy of the power secondary system security early warning calculations,resulting in poor early warning performance.For this reason,the new energy field station power secondary system security early warning method is proposed.The Laplace mapping method is used to reduce the dimensionality of the power data in the power secondary system of the new energy field station,and the initial power data in the high-dimensional data source space is mapped to the low-dimensional subspace.The row vectors and diagonal weights of the power data in the x,y and z directions are calculated respectively to obtain the optimized data,which provide training samples for the system security warning.From the three perspectives of fluctuation degree,time series change trend and energy random distribution characteristics,the security warning features of power data are extracted and input into the K-means clustering algorithm to determine the feature clustering center and achieve security warning.The experimental results show that the proposed method has high warning efficiency and accuracy.
New energy field stationsPower secondary systemFeature extractionK-means clustering algorithmSafety warningHigh-dimensional data source space
NETL
NSTL
万方数据
维普
