Gated Recurrent Unit (GRU)-Based GIC Prediction Using dB/dt as a Proxy

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 perfor...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2024-12, Vol.2915 (1), p.12012
Main Authors: Zainuddin, Aznilinda, Hairuddin, Muhammad Asraf, Latiff, Zatul Iffah Abd, Benavides, Felipe, Jusoh, Mohamad Huzaimy, Yassin, Ahmad Ihsan Mohd
Format: Article
Language:English
Subjects:
Accuracy
Forecasting
Geomagnetic field
Geomagnetism
Magnetic storms
Predictions
Solar cycle
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2915/1/012012