Automated Runtime Verification of EV-Charging Software Using Physics-Informed Oracles and Search-Based Threshold Synthesis

This paper presents an automated runtime verification approach for electric vehicle charging software that checks Open Charge Point Protocol (OCPP) telemetry against an independent physical oracle at the edge. Integrity faults or attacks can preserve statistical plausibility while violating the physical charging process, which limits software-side anomaly monitors that observe only reported data. The proposed approach treats the charging station as a cyber-physical software system and combines two executable runtime oracles: a protocol and statistical oracle over OCPP MeterValues and a physics-informed oracle derived from local hardware power measurements and constant-current/constant-voltage charging dynamics. Their scores are normalized and fused by a transparent decision rule. Two decision thresholds are synthesized automatically with particle swarm optimization under a shared false-alarm budget, turning calibration into a small search-based software engineering problem. A seeded simulation benchmark evaluates five telemetry mutation operators: scaling, bias, replay, stealthy value manipulation, and protocol-timing corruption. At a 5% target false-positive rate, the cross-layer monitor detects 93.1% of attacks with a 4.6% false-positive rate and an area under the ROC curve of 0.953, compared with 72.8% and 0.845 for the physics-only monitor and 44.1% and 0.691 for the cyber-only monitor. Average detection latency is 2.36 min and processing cost is 50.8 \textmu{}s per session. The results show that physics-informed runtime oracles can strengthen automated software assurance for cyber-physical telemetry while remaining interpretable and lightweight. External validation on measured charging-station data remains future work.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-20
DOI
https://doi.org/10.21203/rs.3.rs-11027842/v1
Primary Topic
Smart Grid Security and Resilience
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Automated Runtime Verification of EV-Charging Software Using Physics-Informed Oracles and Search-Based Threshold Synthesis

Ferdaws Ben Naceur, Chokri Ben Salah, Mahmoud El Amri
1 links
Research Square
Smart Grid Security and Resilience
preprint

Automated Runtime Verification of EV-Charging Software Using Physics-Informed Oracles and Search-Based Threshold Synthesis

Ferdaws Ben Naceur, Chokri Ben Salah, Mahmoud El Amri
preprint en

Abstract

This paper presents an automated runtime verification approach for electric vehicle charging software that checks Open Charge Point Protocol (OCPP) telemetry against an independent physical oracle at the edge. Integrity faults or attacks can preserve statistical plausibility while violating the physical charging process, which limits software-side anomaly monitors that observe only reported data. The proposed approach treats the charging station as a cyber-physical software system and combines two executable runtime oracles: a protocol and statistical oracle over OCPP MeterValues and a physics-informed oracle derived from local hardware power measurements and constant-current/constant-voltage charging dynamics. Their scores are normalized and fused by a transparent decision rule. Two decision thresholds are synthesized automatically with particle swarm optimization under a shared false-alarm budget, turning calibration into a small search-based software engineering problem. A seeded simulation benchmark evaluates five telemetry mutation operators: scaling, bias, replay, stealthy value manipulation, and protocol-timing corruption. At a 5% target false-positive rate, the cross-layer monitor detects 93.1% of attacks with a 4.6% false-positive rate and an area under the ROC curve of 0.953, compared with 72.8% and 0.845 for the physics-only monitor and 44.1% and 0.691 for the cyber-only monitor. Average detection latency is 2.36 min and processing cost is 50.8 \textmu{}s per session. The results show that physics-informed runtime oracles can strengthen automated software assurance for cyber-physical telemetry while remaining interpretable and lightweight. External validation on measured charging-station data remains future work.

Research Square
University of Monastir (TN), University of Sousse (TN)
Industry, innovation and infrastructure
Smart Grid Security and Resilience
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
Automated Runtime Verification of EV-Charging Software Using Physics-Informed Oracles and Search-Based Threshold Synthesis — Ferdaws Ben Naceur, Chokri Ben Salah, et al. · Research Square (2026) | TGRS Research Map | TGRS