A solar forecast that learns your roof.

How it works

From the physics to your panels.

1. 1

   It starts with the sky

   Keyless Open-Meteo gives the hourly weather at your location: global, direct and diffuse irradiance, the plane-of-array irradiance for each of your orientations, plus cloud cover, temperature, wind and snow. The very data the Helios card reads, and your location is only ever an approximate point.

2. 2

   A real physical model, not a black box

   From that weather, Helios computes the sun's position (checked against NOAA's reference to about 0.3 degrees), transposes the irradiance onto each tilted array, applies a cell-temperature derate, a snow-cover factor, and clips at your inverter limit. A multi-orientation install is summed by each array's share of your kWp.

3. 3

   Then it learns from your roof

   This is where a cloud service can't follow. Helios keeps a rolling 60-day history of what your panels actually produced. For the hour being forecast it finds past hours with a similar sun position, cloud cover and temperature, and reads the spread of what you truly made then. The median becomes a site-calibrated prediction; the 10th and 90th percentiles become a free uncertainty band.

4. 4

   And it tells you how much to trust it

   A reliability score blends how mature the learning is, how close recent predictions landed to reality, and how predictable today's sky is, then decays across the 7-day horizon the way weather-model skill really does. A trend value shows whether today now looks better or worse than it did at 06:00.

All of it runs on your own Home Assistant. Nothing about your production leaves your instance; the only thing that goes out is an approximate location, to fetch the weather from Open-Meteo.