Fault location for MMC–MTDC transmission lines based on least squares-support vector regression

Abstract

The dc transmission line protection plays a crucial role in the secure operation of a multi-terminal modular-multilevel-converter-based high-voltage direct current (MMC–MTDC) system, which is increasingly adopted as a promising option in the power transmission fields. However, the MTDC is the most vulnerable to a dc fault, which paralyses all of the MMCs until the dc fault is cleared out. It is a huge challenge that how to locate and isolate dc fault current and ensure the continuous operation of the healthy part of the MMC–MTDC system under dc faults. This study proposes a least-squares-based ɛ-support vector regression scheme, which captures fault features via the Hilbert–Huang transform. Fault features are used as the inputs of ɛ-support vector regression to obtain fault distance. Then, least-squares method is utilised to optimise the parameters of the model so that it can meet the demand on fault location for MMC–MTDC transmission lines. In the end, the simulation model of the multi-terminal MMC–HVDC system using PSCAD/EMTDC is built to demonstrate that the proposed method has well reliability and accuracy for fault location.

Keywords

• fault location
• power transmission protection
• power system simulation
• power transmission faults
• regression analysis
• fault currents
• power convertors
• support vector machines
• Hilbert transforms
• least squares approximations
• DC power transmission
• power engineering computing
• fault location
• MMC–MTDC transmission lines
• squares-support vector regression
• dc transmission line protection
• multiterminal modular-multilevel-converter-based high-voltage
• direct current system
• power transmission fields
• dc fault
• fault current
• MMC–MTDC system
• fault features
• fault distance
• multiterminal MMC–HVDC system
• least-squares-based-support vector regression scheme