An ultra-fast MMC-HVDC fault location algorithm based on transient voltage features and regression neural network

• This paper proposes an ultra-fast fault location algorithm based on transient voltage features and regression neural network suitable for modular multilevel converter-based high-voltage DC (MMC-HVDC) grids equipped with quick-action hybrid DC circuit breakers (HDCCBs). • The total mean of fault location errors is 0.41 % for all fault locations and transition resistances up to 1005 Ω, so it has quite high accuracy. • It only based on single-ended voltage, which is immune to communication link disturbances. • Its generalization ability, adaptability and anti-noise ability are all excellent. An ultra-fast fault location algorithm based on the single-ended transient voltage features and regression neural network (RNN) is proposed, which utilizes 2.5 ms postfualt data window and is suitable for modular multilevel converter-based high-voltage DC (MMC-HVDC) grids equipped with quick-action protections and hybrid DC circuit breakers (HDCCBs). Firstly, the analyses based on the lumped RLC equivalent circuit demonstrate that the delay time, the first negative peak time and its value all have exact relationships with the fault location. Nevertheless, considering the actual parameters and topology of the MMC-HVDC grid, three features can only be approximately extracted. Thus, RNN is utilized to estimate fault locations. 2.02 × 10 4 distinct fault cases validate the algorithm’s high accuracy across all fault locations and transition resistances up to 1005 Ω. It can well tolerate reasonable deviations of line parameter and current limiting reactor value, as well as 40-dB white noise. Besides, it also has remarkable adaptability, and can be suitable for different systems.