Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AI

by   Tong Wu, et al.
cornell university
Berkeley Lab

The effective representation, precessing, analysis, and visualization of large-scale structured data over graphs are gaining a lot of attention. So far most of the literature has focused on real-valued signals. However, signals are often sparse in the Fourier domain, and more informative and compact representations for them can be obtained using the complex envelope of their spectral components, as opposed to the original real-valued signals. Motivated by this fact, in this work we generalize graph convolutional neural networks (GCN) to the complex domain, deriving the theory that allows to incorporate a complex-valued graph shift operators (GSO) in the definition of graph filters (GF) and process complex-valued graph signals (GS). The theory developed can handle spatio-temporal complex network processes. We prove that complex-valued GCNs are stable with respect to perturbations of the underlying graph support, the bound of the transfer error and the bound of error propagation through multiply layers. Then we apply complex GCN to power grid state forecasting, power grid cyber-attack detection and localization.


Learning Representations Using Complex-Valued Nets

Complex-valued neural networks (CVNNs) are an emerging field of research...

Building Blocks for a Complex-Valued Transformer Architecture

Most deep learning pipelines are built on real-valued operations to deal...

Spatio-Temporal Graph Scattering Transform

Although spatio-temporal graph neural networks have achieved great empir...

Spatio-Temporal Visualization of Interdependent Battery Bus Transit and Power Distribution Systems

The high penetration of transportation electrification and its associate...

Transferability of Spectral Graph Convolutional Neural Networks

This paper focuses on spectral graph convolutional neural networks (Conv...

On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective

Graph Convolutional Neural Networks (graph CNNs) are a promising deep le...

Please sign up or login with your details

Forgot password? Click here to reset