Bayesian Ridge Regression Based Model to Predict Fault Location in HVdc Network

TL;DR

This paper introduces a Bayesian Ridge Regression model for precise fault location prediction in multi-terminal HVdc networks using single-ended measurements, addressing challenges posed by measurement noise and network parameters.

Contribution

The paper presents a novel data-driven Bayesian Ridge Regression approach specifically designed for fault location estimation in multi-terminal HVdc systems, improving accuracy and robustness.

Findings

Effective fault location prediction with high accuracy.

Robustness to measurement noise demonstrated.

Validated on a three-terminal MTdc network in PSCAD/EMTdc.

Abstract

This paper discusses a method for accurately estimating the fault location in multi-terminal High Voltage direct current (HVdc) transmission network using single ended current and voltage measurements. The post-fault voltage and current signatures are a function of multiple factors and thus accurately locating faults on a multi-terminal network is challenging. We discuss a novel data-driven Bayes Regression based method for accurately predicting fault locations. The sensitivity of the proposed algorithm to measurement noise, fault location, resistance and current limiting inductance are performed on a radial three-terminal MTdc network. The test system is designed in Power System Computer Aided Design (PSCAD)/Electromagnetic Transients including dc (EMTdc).