Related productAvailable today
Solar Intelligence Platform
Physics-calibrated performance intelligence for solar fleets — every megawatt-hour of loss attributed to a cause.
Solar
DeployedThe hardest optimisation problem we could find.
Utility-scale generation, loss attribution, and fleet normalisation.
The operating problem
- 01
Plant-level meters show a shortfall but cannot say whether it is soiling, a shaded string, a drifting inverter, or a failed combiner.
- 02
Inverter-native monitoring alarms on absolutes, so gradual degradation stays below threshold until it has cost a season of generation.
- 03
A fleet assembled over a decade runs four inverter brands and three module vintages, and none of their portals agree on what 'normal' means.
How Peryx applies
- 01
Each plant's PAN/OND configuration becomes a physics model of expected generation under the weather actually observed.
- 02
Every five-minute interval is compared against that model at string, MPPT, and inverter level.
- 03
Residuals are attributed — soiling, mismatch, drift, and failure separated and quantified rather than summed into one number.
Under the hood
The pipeline does not change between sectors.
Only the physics model in the middle is sector-specific. That is the whole argument for expanding beyond solar.
Sensors
Telemetry
Physics model
Digital twin
Insights
Recommendations
Decisions
Where we actually are
DeployedRunning against real operational data.
Deployed and running against real operational data. This is the product you can use today.
See the platform
See what your operation is actually losing.
A walkthrough on your own asset class, with a scoped pilot on one to three sites if it's a fit.