get_emos_ts: Get time-series forecast using EMOS post-processing of NWP...

In kdayday/ppnwp: Post-Process Numerical Weather Prediction ensembles

Description

This method trains EMOS models for each time-point using a sliding or time-of-day training method, then forecasts using the current NWP ensemble.

Usage

get_emos_ts(issue, t_idx_series, ens_test, ensemble, telemetry, sun_up,
  site, max_power, metadata)

Arguments

issue	A time stamp
t_idx_series	Series of time indices to forecast, relative to the telemetry time indices
ens_test	[time x member] matrix of ensemble data for test period
ensemble	A list of data=[issue x step x member] array of all ensemble data (historical + test) and issuetime=vector of POSIXct time stamps
telemetry	A list of data=vector of telemetry and validtime=vector of POSIXct times
sun_up	A vector of booleans, indexed by telemetry valid times
site	String, site name
max_power	Site's AC power rating or maximum load
metadata	A data.frame of forecast parameters

Value

A ts_forecast object

See Also

Other ts_training_forecast: get_binned_ts, get_bma_ts, get_chpeen_ts, get_clim_ts, get_peen_ts, get_raw_ts

kdayday/ppnwp documentation built on Oct. 8, 2020, 8:47 a.m.