.png){kind=icon}
.png){kind=icon}
Return
Density-Based Adaptive Protection for HVDC Transmission Lines Using Statistical Learning and Proactive Control
.png){kind=icon}
PRE
AI
J
X
J
DOI：10.1109/tie.2026.3677634.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To enhance the protection reliability of high-voltage direct current (HVDC) transmission lines under high-impedance grounding and complex conditions, this article proposes a novel density-based adaptive protection scheme that integrates statistical learning with proactive control strategies. The method first employs principal component analysis to reduce the dimensionality and visualize the projection of transient fault features, revealing their continuous distribution patterns in the feature space. Subsequently, kernel density estimation is introduced to probabilistically model the projection distribution of fault samples, thereby delineating the internal fault zone, external fault zone, and the fuzzy transition region between them. Based on the relative position of real-time fault characteristics in this probability space, the protection system adaptively triggers a hierarchical action strategy, including millisecond-level fast isolation, cooperative discrimination using information from the remote terminal, or protection blocking. The proposed method is validated through electromagnetic transient simulation and 31 field fault cases, demonstrating the following performance metrics: protection accuracy of 96.8% (14.5% points higher than traditional traveling-wave protection), average response time of 29 ms (meeting the speed requirements of HVDC line protection), and maloperation rate of 1.9%. Moreover, the scheme effectively identifies faults with transition resistance up to 300 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol{\Omega}$</tex-math> </inline-formula> and maintains stable performance under noise interference, achieving a desirable balance among reliability, speed, and adaptability.
Keywords:
Adaptive protection
high-impedance faults (HIF)
high-voltage direct current (HVDC) transmission lines
kernel density estimation (KDE)
statistical learning
Journal
IF:
7.2
Papers:
1.8W
Citations:
9.8W
Organization
Cited Papers