The new Machine Learning forecast module is here!
This will provide a better forecast model for the load power consumption forecast.
Improvement
- A brand new load forecast module and more... The new forecast module can actually be used to forecast any Home Assistant variable. The API provides fit, predict and tune methods. By the default it provides a more efficient way to forecast the power load consumption. It is based on the skforecast module that uses scikit-learn regression models considering auto-regression lags as features. The hyperparameter optimization is proposed using bayesian optimization from the optuna module.
- A new documentation section covering the new forecast module.
Fix
- Fixed Solar.Forecast issues with lists of parameters.
- Fixed latex equations rendering on documentation, dropped Mathjax.
- Refactored images in documentation, now using only SVG for plotly figures.
- Bumped requirements to latest non-conflicting versions.
What's Changed
- Update jinja2 requirement from <3.1 to <3.2 by @dependabot in #53
- Bump markupsafe from 2.0.1 to 2.1.2 by @dependabot in #52
- Dev/new forecast part1 by @davidusb-geek in #57
- Dev/new forecast part2 by @davidusb-geek in #59
Full Changelog: v0.3.36...v0.4.0