energy_analysis.timestral_solar_case#

An audited search and chronological solar-generation forecasting case.

June selected the plant; June/July selected the Timestral size and inputs. August is the final evaluation period. Saved neural forecasts are real inference, bound to the exact context; other models are fitted again on every replay.

energy_analysis.timestral_solar_case.run_solar_case(directory, *, connector=None)[source]#

Reproduce the frozen case; do not search or optimize on the final holdout.

Generation context and calibration span 14 days. If a same-clock resource reading is absent throughout that window, weather-dependent models may use older, pre-issue measurements. If accepted calibration power has zero Q95, retain the last informative calibration for all three fitted comparators. These safeguards keep every holdout label, including the sensor-data gap.

Parameters:
Return type:

DataFrame

energy_analysis.timestral_solar_case.solar_case_scores(predictions)[source]#

Separate selection dates from the final month; score identical model keys.

Parameters:

predictions (DataFrame)

Return type:

DataFrame

energy_analysis.timestral_solar_case.daily_errors(predictions)[source]#

Daily MAE for every model, after checking common and complete coverage.

Parameters:

predictions (DataFrame)

Return type:

DataFrame