GIC prediction for power grid based on ICEEMDAN-CNN-LSTM optimized by improved sparrow search algorithm

The geomagnetic induced current (GIC) generated by changes in the Earth's magnetic field caused by space weather activities such as solar wind poses a great threat to the safety of the power grid. The GIC prediction method is proposed based on an improved adaptive noise set empirical mode decomposition (ICEEMDAN) and an improved sparrow search algorithm (ISSA) to optimize the CNN-LSTM model, addressing the issues of complex and large errors in traditional GIC prediction processes. The results indicate that the ICEEMDAN-ISSA-CNN-LSTM model has more accurate prediction results.