Searcharxiv⌕ Search

arXiv subjects

Pascal Schirmer

Publications and source records attributed to Pascal Schirmer.

2 recordsLinked to original sources

Transferable Neuromorphic Protection for Distribution Networks

Protection of converter-dominated distribution networks is challenging due to limited fault currents, operating-mode transitions, bidirectional power flow, and heterogeneous network configurations. This paper proposes a scale-invariant neuromorphic protection framework to enable transferable protection decisions across such networks. The framework integrates asset-based normalization, multi-domain disturbance representation, event-driven spike encoding, leaky integrate-and-fire (LIF) dynamics, adaptive threshold regulation, and directional supervision within a unified mathematical formulation. Local voltage, current, active power, and reactive power measurements are transformed into dimensionless disturbance representations, while latency encoding and membrane integration capture disturbance intensity and temporal evolution. The framework is evaluated across four heterogeneous network configurations: a two-DER inverter-interfaced microgrid, an islanded ring microgrid, the IEEE 13-node feeder, and the CIGRE European medium-voltage benchmark. Across 480 cases, it achieves a median operating time of 7.6 ms, with 94.2 % of cases operating within one power cycle. The results demonstrate selective protection across different electrical ratings and network topologies using a common parameterization without network-specific retuning, highlighting the potential of neuromorphic processing for physically interpretable, communication-free protection of converter-dominated distribution networks.

eess.SP↗

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.

eess.SP↗