Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › L1 · Control Plane
L1 · Control Plane

L1 Control Plane Architecture Overview

The L1 tier is Kronos's hard real-time layer: edge FPGAs and PLCs that convert model intent into microsecond-deterministic actuation for both machines.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L1 · CONTROL PLANEHard real-time actuation and the autonomous failsafe.1Edge FPGAµs-determinism2Real-Time Actuationcoils · heating · fuel3Hardware Failsafeautonomous trip4Sync Gatephase-locked timing5Signal I/OADC / DAC6Watchdogliveness & interlocksMACHINE TIEDrives magnets, ice-piston, and gas puff on the sub-10 µs loop.KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORCONTROL PLANESHEET 03REV. 2026-08L1 · AI-NATIVE STACK
L1 · Control Plane — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

What L1 is

The Control Plane (L1) sits between the offline Foundation tier (L0) and the Twin/AI tier (L3), but it is not a place where learning happens. L1 exists to guarantee bounded latency and bounded jitter on every command path that can move energy or open a fault. It hosts the edge FPGA fabric, the deterministic PLC layer, and the actuator drivers that touch the breeder (Hyperion) and the burner (Aegis / MetroVolt).

Kronos's design principle is a strict separation of concerns: intelligence proposes, hardware disposes. L3's model-predictive control (MPC) agents compute setpoint trajectories on a 50–100 ms predictive shadow; L1 accepts those setpoints as advisory targets and enforces them through control loops whose worst-case timing is provable, not statistical.

The layer boundary

Every command crossing into L1 passes a validation gate: range checks, rate-of-change limits, and cross-consistency against the measured state vector. A setpoint that violates a hardware envelope is clamped or rejected at the FPGA edge before it ever reaches a coil supply or a beam modulator. This is why the failsafe path can be certified independently of any machine-learning component.

Both machines, one discipline

The remainder of this category documents each loop, its timing budget, and how determinism is preserved from sensor feedthrough to actuator gate. The organizing constraint throughout is the sub-10µs command boundary.

Content reviewed August 2026 · design-and-simulation stage