Post-Fault Power Grid Voltage Prediction via 1D-CNN with Spatial Coupling

Abstract

We propose a one-dimensional convolutional neural network (1D-CNN) with spatial coupling for post-fault power grid voltage prediction. Our proposed deep learning framework was inspired by the celebrated Prony’s method in classical signal processing. Our spatio-temporal model significantly outperforms existing benchmarks, including long short-term memory model, and is applicable to other strong transients in power industries.