model_with_TOWT: Time-of-Week and Temperature.

In kW-Labs/nmecr: An implementation of peer-reviewed energy data analysis algorithms for site-specific M&V

Time-of-Week and Temperature.

Description

This function builds an energy use/demand models using two algorithms: TOWT and MW. This function is adapted from work by LBNL: https://lbnl-eta.github.io/RMV2.0/

Usage

model_with_TOWT(
  training_data = NULL,
  prediction_data = NULL,
  model_input_options = NULL,
  occupancy_info = NULL
)

Arguments

training_data	Training dataframe.Output from create_dataframe function
prediction_data	Prediction dataframe. Output from create_dataframe function
model_input_options	List with model inputs specified using assign_model_inputs function
occupancy_info	An nx2 dataframe with the occupancy information of the training dataset. Column names should be: uniq_time_of_week and ok_occ uniq_time_of_week is the unique time of week (1 through 7 for daily data and 1 through 168 for hourly data). ok_occ is a binary: 1 for occupied and 0 for unoccupied

Value

a list with the following components:

model_occupied

an lm object generated when using Time-of-Week and TIme-of-Week & Temperature algorithms

model_unoccupied

an lm object generated when using TOWT algorithm when the unoccupied period is discernably different from the occupied period

training_data

training dataframe along with the model_fit values

prediction_data

prediction dataframe along with the model prediction values. Only generated when prediction_list is supplied to the algorithm

model_input_options

model_input_options from the input along with additional model specifications.

Note

training_data and model_input_options are required arguments for the function.

kW-Labs/nmecr documentation built on May 6, 2024, 9:28 p.m.