Strict Q-limit enforcement: a converged solution that violates generator Q limits is marked infeasible. Non-negotiable physics. No FDNR shortcuts.
The physics under
Sentinel and Forge.
A reference of the engineering choices Sentinel and Forge share — what makes them defensible at planning-grade fidelity and real-time cadence.
Prevents naïve “infinite Q” hacks while still recovering solvable cases.
Hundreds of full-AC N-1 and escalated N-2 cases in near real-time.
Graph-theory plus operator-defined guardrails — betweenness centrality, electrical distance, critical cut-sets, and historical patterns augment operator judgment.
Correct handling of modern grid elements for accurate contingency screening and ranking.
Greedy reserve dispatch checks whether each flagged contingency can return to normal under LTE within 15 minutes.
Solved state, contingency definition, violation details, topological view, investigation context, and recommended next actions — carried in a single self-describing file.
Roadmap: commitment states plus load forecast plus expected outages and returns at planning-grade fidelity (Sentinel Phase 2, Q3).
AI data centers and other large, voltage-sensitive loads as first-class citizens: voltage profiles, up/down ramps, load reduction schemes.
Deploy where you operate.
- On-prem (RHEL certified)
- Air-gapped
- Cloud (on request)
- Deterministic builds + reproducible pipelines
- No cloud lock-in

Pilot Sentinel on your representative case.
Bring a recent State Estimator export. We will run an exhaustive N-1 + intelligent N-2 with recovery validation and walk through the results with your team — no slide-deck theater.
info@raptrixpower.com · Founder direct: matthew.musto@raptrixpower.com · github.com/RaptrixPowerFlow