get_energy_models: Get a tibble of energy GMM for every user profile

In evprof: Electric Vehicle Charging Sessions Profiling and Modelling

Get a tibble of energy GMM for every user profile

Description

This function simulates random energy values, makes the density curve and overlaps the simulated density curve with the real density curve of the user profile's energy values. This is useful to appreciate how the modeled values fit the real ones and increase or decrease the number of Gaussian components.

Usage

get_energy_models(sessions_profiles, log = TRUE, by_power = FALSE)

Arguments

sessions_profiles	tibble, sessions data set in evprof standard format with user profile attribute Profile
log	logical, whether to transform ConnectionStartDateTime and ConnectionHours variables to natural logarithmic scale (base = exp(1)).
by_power	Logical, true to fit the energy models for every charging rate separately

Value

tibble

Examples

library(dplyr)

# Classify each session to the corresponding user profile
sessions_profiles <- california_ev_sessions_profiles %>%
  dplyr::sample_frac(0.05)

# Get a table with the energy GMM parameters
get_energy_models(sessions_profiles, log = TRUE)

# If there is a `Power` variable in the data set
# you can create an energy model per power rate and user profile
# First it is convenient to round the `Power` values for more generic models
sessions_profiles <- sessions_profiles %>%
  mutate(Power = round_to_interval(Power, 3.7)) %>%
  filter(Power < 11)
sessions_profiles$Power[sessions_profiles$Power == 0] <- 3.7
get_energy_models(sessions_profiles, log = TRUE, by_power = TRUE)

evprof documentation built on May 29, 2024, 2:36 a.m.