Research on Forecasting Method of GIC Caused by Gradual Commencement Magnetic Storm

摘要

The mechanism of power grid GIC is complex and has multiple factors. The geomagnetic activity is one of the main factors. In this paper, by using the wavelet neural network, a forecasting model for GIC caused by gradual commencement magnetic storm is introduced. The GIC data and geomagnetic data monitored during the magnetic storms are the basic data of the model. The GIC data collected in Ling'ao nuclear power station, April 2006, is tested to detect the accuracy of the trained model. The analysis of forecasting results shows that the model can provide a comparatively accurate result for GIC in power grid.