PLL Cyber-Guard

An OpenEnv environment for cyber-attack detection on grid-connected inverters · v{{VERSION}}

Grid-following inverters synchronise to the grid with a phase-locked loop. An attacker who can rewrite its voltage measurements (false-data injection) can desynchronise the inverter from the real grid. The agent watches PLL signals simulated at 5 kHz plus a trusted but delayed PMU stream. Every 50 ms it must decide whether an attack is under way, classify it, and engage a protective action in time. It must also avoid alarming on real grid events: phase jumps, sags, single-phase faults, harmonic steps and frequency events.

Tasks

easy · task 0

Sinusoidal FDI detection. Spot an interharmonic injection on one phase quickly. Some episodes have no attack.

medium · task 1

Classify under disturbances. Tell sinusoidal, ramp and pulse injections apart while natural grid events happen.

hard · task 2

Stealthy phase spoofing. A balanced angle drift the PLL tracks perfectly. Cross-check against the PMU and hold over before 10° of desync.

Live demo · physics-heuristic baseline

idle
local PLL frequency PMU frequency (delayed, trusted) attack onset agent alarm raised

Quick start

curl -X POST $URL/reset -H 'content-type: application/json' -d '{"task_id": 2, "seed": 7, "session_id": "me"}'
curl -X POST $URL/step  -H 'content-type: application/json' \
     -d '{"session_id": "me", "action": {"attack_detected": false, "attack_type": 0, "confidence": 0.9, "protective_action": 0}}'

Endpoints: POST /reset POST /step GET /state GET /tasks GET /schema GET /metadata GET /health WS /ws · OpenAPI docs · source