Directionally Supervised Neuromorphic Protection for Distribution Systems Using Local Measurements

Reliable protection under varying power system operating conditions requires rapid fault detection while preserving selectivity against external faults and non-fault disturbances. This requirement is particularly challenging in communication-free schemes, where relays must determine trip conditions solely from local electrical measurements. To address this challenge, this paper proposes a directionally supervised neuromorphic protection scheme that integrates disturbance-responsive leaky integrate-and-fire dynamics with a direction-dependent firing threshold to distinguish internal faults from reverse-direction events. The unified relay architecture combines local disturbance detection, directional discrimination, and spike-based trip generation without requiring inter-relay communication. Its performance is evaluated under grid-connected and islanded conditions using a ring microgrid and the IEEE 13-node distribution feeder. Across 240 evaluated fault scenarios, the framework achieves median operating times of 5.4--7.6 ms across the two networks, with 78% of cases operating within 10 ms and 95% within 20 ms. It also maintains protection security during load disturbances, while fault-resistance analysis confirms its response under high-resistance faults. Controller-hardware-in-the-loop (CHIL) experiments using an RTDS simulator and an external dSPACE controller demonstrate trip-command assertion in approximately 10 ms and 5 ms for the tested single-line-to-ground and three-phase-to-ground faults, respectively. The results establish real-time feasibility within the evaluated conditions and characterize operating-time variability across fault types and resistance levels for different network configurations.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16711
Primary Topic
Power Systems Fault Detection
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Directionally Supervised Neuromorphic Protection for Distribution Systems Using Local Measurements

Subham Sahoo, Saurabh Prabhakar, Bijaya Ketan Panigrahi, Yubo Song et al.
arXiv (Cornell University)
Power Systems Fault Detection
preprint

Directionally Supervised Neuromorphic Protection for Distribution Systems Using Local Measurements

Subham Sahoo, Saurabh Prabhakar, Bijaya Ketan Panigrahi, Yubo Song, Pascal Schirmer
preprint en

Abstract

Reliable protection under varying power system operating conditions requires rapid fault detection while preserving selectivity against external faults and non-fault disturbances. This requirement is particularly challenging in communication-free schemes, where relays must determine trip conditions solely from local electrical measurements. To address this challenge, this paper proposes a directionally supervised neuromorphic protection scheme that integrates disturbance-responsive leaky integrate-and-fire dynamics with a direction-dependent firing threshold to distinguish internal faults from reverse-direction events. The unified relay architecture combines local disturbance detection, directional discrimination, and spike-based trip generation without requiring inter-relay communication. Its performance is evaluated under grid-connected and islanded conditions using a ring microgrid and the IEEE 13-node distribution feeder. Across 240 evaluated fault scenarios, the framework achieves median operating times of 5.4--7.6 ms across the two networks, with 78% of cases operating within 10 ms and 95% within 20 ms. It also maintains protection security during load disturbances, while fault-resistance analysis confirms its response under high-resistance faults. Controller-hardware-in-the-loop (CHIL) experiments using an RTDS simulator and an external dSPACE controller demonstrate trip-command assertion in approximately 10 ms and 5 ms for the tested single-line-to-ground and three-phase-to-ground faults, respectively. The results establish real-time feasibility within the evaluated conditions and characterize operating-time variability across fault types and resistance levels for different network configurations.

arXiv (Cornell University)
Power Systems Fault Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon