| 總結: | Geomagnetically induced currents (GICs) pose a significant threat to power systems during geomagnetic storms. This work introduces a GRU approach for GICs forecasting based on the rate of change of the geomagnetic field, dB/dt at two low-latitude stations, Muntinlupa (MUT) and Guam (GUA). The performances of the model were evaluated based on the data collected from the Solar Cycle 23 (SC23) as training data, and Solar Cycle 24 (SC24) at the validation stage. The GRU model demonstrated good predictive accuracy with low RMSE values, particularly for MUT model (RMSE = 0.00917). MUT shows higher predictive accuracy and generalizability across MUT station itself and GUA station. This work underlines the potential of GRU models for GIC prediction, providing a foundation for more robust forecasting tools to mitigate the impacts of geomagnetic disturbances on power systems. © 2024 Institute of Physics Publishing. All rights reserved.
|
|---|