Visibility where it matters most

Intelligent Low-Voltage Grid Monitoring.

Griddle combines precision hardware with advanced data-processing algorithms to give distribution system operators visibility into the status of the low-voltage electricity grid.

Built by GCSC

The Problem

Low-voltage grids are flying blind.

The low-voltage grid was never designed for two-way power flows. As the energy transition accelerates, rooftop solar, EV chargers, and heat pumps are being connected to the low-voltage grid faster than it was designed to handle. Most DSOs have zero real-time visibility below the MV/LV transformer.

The result: voltage violations go undetected, hosting capacity is underestimated, and cable reinforcement decisions are based on assumptions rather than data.

  • No real-time state insight below the transformer
  • Hosting capacity determined by worst-case assumptions
  • Cable reinforcement planned without actual load data
The Solution

Low voltage grid visibility using a sparse sensor network.

Griddle is a low-voltage grid monitoring system that delivers full-network visibility from a fraction of the sensors. Install measurement devices on a small number of feeders. Griddle's state estimation engine infers voltage, current, and power quality across the entire low voltage network.

Precision Hardware

Rogowski coils and voltage probes sample at 8,000 samples per second, capturing up to the 80th harmonic.

Physics-Informed AI

Our PINN-based state estimator enforces Kirchhoff's voltage and current laws as hard constraints, not learned approximations. Accurate voltage and current estimates at every node, even those without a sensor.

Actionable Output

Dynamic Operating Envelopes are computed at the edge, in real time, using live network state rather than static grid models. Connected assets get a DOE that reflects actual network conditions: tighter when the grid is stressed, more generous when it isn't.

Technology

Built for the grid, not the cloud.

Griddle runs inference at the edge. No cloud round-trips, no latency, no dependency on connectivity for critical calculations.

Sampling Rate
8,000 sps
Harmonic Coverage
Up to 80th harmonic
Time Sync
IEEE 1588 PTP (±1 µs)
Connectivity
4G / LTE
State Estimation
PINN with KVL/KCL hard constraints
Detection
Sub-Hz oscillation (0.2–1 Hz)
Output Protocol
IEC 61850 MMS + GOOSE
Inference
Edge-native (on-device)

More insight, fewer sensors.

PQ Meters
  • Single-point measurement only
  • No network state estimation
  • No inter-device synchronisation
  • Manual data collection
Griddle
  • Full-network state estimation
  • Sub-microsecond time sync
  • Edge-native real-time inference
  • IEC 61850 native integration
  • Dynamic Operating Envelopes
Cloud-First IGMs
  • Measured points only — no estimation
  • Cloud-dependent processing
  • Higher latency for critical data
  • Requires more sensors for coverage

Built for the challenges DSOs face today.

Dynamic Operating Envelopes

Set and update connection limits in real time based on actual grid state.

LV Network Visibility

Know voltage and loading at every node, not just the transformer.

Cable Reinforcement Planning

Base investment decisions on measured data, not worst-case assumptions.

Power Quality Monitoring

Detect harmonics, oscillations, and anomalies across the feeder.

Ready to see your grid?

Get in touch to schedule a demo or discuss how Griddle fits your network.