Asynchronous Traveling Wave-based Distribution System Protection with Graph Neural Networks | IEEE Conference Publication | IEEE Xplore

Asynchronous Traveling Wave-based Distribution System Protection with Graph Neural Networks


Abstract:

The paper proposes an implementation of Graph Neural Networks (GNNs) for distribution power system Traveling Wave (TW) - based protection schemes. Simulated faults on the...Show More

Abstract:

The paper proposes an implementation of Graph Neural Networks (GNNs) for distribution power system Traveling Wave (TW) - based protection schemes. Simulated faults on the IEEE 34 system are processed by using the Karrenbauer Transform and the Stationary Wavelet Transform (SWT), and the energy of the resulting signals is calculated using the Parseval's Energy Theorem. This data is used to train Graph Convolutional Networks (GCNs) to perform fault zone location. Several levels of measurement noise are considered for comparison. The results show outstanding performance, more than 90% for the most developed models, and outline a fast, reliable, asynchronous and distributed protection scheme for distribution level networks.
Date of Conference: 25-26 April 2022
Date Added to IEEE Xplore: 06 July 2022
ISBN Information:
Conference Location: Manhattan, KS, USA

Funding Agency:


I. Introduction

Promising changes are occurring in power system protection. Numerous studies that apply Traveling Wave (TW) - based methods to distribution systems will make ultra- fast protection a reality at the distribution level [1]. These approaches are usually based on Machine Learning/Deep Learning methods due to the complexity of the task: the TW propagation in distribution systems is heavily affected by the propagation path characteristics, such as line lengths and elements present in the system [2].

References

References is not available for this document.