rdtools.filtering.xgboost_clip_filter

rdtools.filtering.xgboost_clip_filter(power_ac, mounting_type='fixed')

This filter uses and XGBoost model to filter out clipping periods in AC power or energy time series.

Parameters:

• power_ac (pandas.Series) -- Pandas time series, representing PV system power or energy. For best performance, timestamps should be in local time.

• mounting_type (str, default 'fixed') -- String representing the mounting configuration associated with the AC power or energy time series. Can either be "fixed" or "single_axis_tracking".

Returns:

Boolean Series of whether to include the point because it is not clipping. True values delineate non-clipping periods, and False values delineate clipping periods.

Return type:

pandas.Series

References

[1]

Perry K., Muller, M., and Anderson K. "Performance comparison of clipping detection techniques in AC power time series", 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC). DOI: 10.1109/PVSC43889.2021.9518733.