plr_xbx_model {PVplr}

XbX Method for PLR Determination

Description

This function groups data by the specified time interval and performs a linear regression using the formula: P_{pred.} = \beta_0 + \beta_1 G + \beta_2 T + \epsilon. This is the simplest of the PLR determining methods. Predicted values of irradiance, temperature, and wind speed (if applicable) are added to the output for reference. These values are the lowest daily high irradiance reading (over 300), the average temperature over all data, and the average wind speed over all data. Outliers are detected and labeled in a column as TRUE or FALSE.

Usage

plr_xbx_model(
  df,
  var_list,
  by = "month",
  data_cutoff = 30,
  predict_data = NULL
)

Arguments

df

A dataframe containing pv data.

var_list

A list of the dataframe's standard variable names, obtained from the plr_variable_check output.

by

String, either "day", "week", or "month". The time periods over which to group data for regression.

data_cutoff

The number of data points needed to keep a value in the final table. Regressions over less than this number and their data will be discarded.

predict_data

optional; Dataframe; If you have preferred estimations of irradiance, temperature, and wind speed, include them here to skip automatic generation. Format: Irradiance, Temperature, Wind (optional).

Value

Returns dataframe of results per passed time scale from XbX modeling

Examples

# build var_list
var_list <- plr_build_var_list(time_var = "timestamp",
                               power_var = "power",
                               irrad_var = "g_poa",
                               temp_var = "mod_temp",
                               wind_var = NA)
# Clean Data
test_dfc <- plr_cleaning(test_df, var_list, irrad_thresh = 100,
                         low_power_thresh = 0.01, high_power_cutoff = NA)
                         
# Perform the power predictive modeling step
test_xbx_wbw_res <- plr_xbx_model(test_dfc, var_list, by = "week",
                                  data_cutoff = 30, predict_data = NULL)