evprof

# evprof ## Overview evprof is part of a suite of packages to analyse, model and simulate the charging behavior of electric vehicle users: - [evprof](https://resourcefully-dev.github.io/evprof/): Electric Vehicle PROFiling - [evsim](https://resourcefully-dev.github.io/evsim/): Electric Vehicle SIMulation evprof aims to provide tools for classifying EV charging sessions into generic groups with similar connection patterns named “user profiles”, using the Gaussian Mixture Models (GMM) clustering method. Moreover, functions to build stochastic models (based on GMM) for every user profile are also provided in order to simulate new EV sessions. The Gaussian Mixture Models clustering technique used in this package aims to accomplish two different tasks that can be useful for multiple purposes: 1. Classification of EV charging sessions into generic user profiles (e.g. working time, dinner, commuters, etc.), allowing to: - Increase the knowledge on the different flexibility potential patterns from a real data set - Define accurate tariffs according to the flexibility potential (implicit demand response scenario) - Reduce the uncertainty of flexibility offers when participating in flexibility markets (explicit demand response scenario) 2. Modeling every user profile with stochastic models, allowing to: - Simulate high penetration of EV to estimate when an existing charging infrastructure will be saturated - Simulate different scenarios of charging rates to analyse the impact of fast charging - Size and plan a public charging infrastructure ## Usage To use this package you will need a data set of EV charging sessions with at least two fundamental variables: **connection start** time and **connection duration**. With these two variables you will be able to classify the sessions into different user profiles, but to generate the EV Gaussian Models you will also need the **energy** values. The package also provides an example open data set of EV charging sessions from the California Technological Institute (Caltech), which can be downloaded from the [ACN-Data website](https://ev.caltech.edu/dataset). For more information about this data set and how to use it, visit the [ACN documentation](https://acnportal.readthedocs.io/en/latest/). Moreover, an example `evmodel` object (EV Gaussian Mixture Models) built with `evprof` functions and the California open data set (see the [California case study](https://resourcefully-dev.github.io/evprof/articles/california.html) article) is also provided. These two demo data objects are provided together with package functions for a better interactive user experience. If you have your own data set, the best place to start is the [Get started chapter](https://resourcefully-dev.github.io/evprof/articles/evprof.html) in the package website. ## Installation You can install the package from CRAN or the latest development version from GitHub: ``` r # CRAN stable release install.packages("evprof") # install.packages("pak") pak::pak("resourcefully-dev/evprof") ``` ## Getting help If you encounter a clear bug, please open an issue with a minimal reproducible example on [GitHub](https://github.com/resourcefully-dev/evprof/issues). For further technical details, you can read the following academic articles about the methodology used in this paper: - **Increasing hosting capacity of low-voltage distribution network using smart charging based on local and dynamic capacity limits**. Sustainable Energy, Grids and Networks, vol. 41. Elsevier BV, p. 101626, March 2025. [DOI link](https://doi.org/10.1016/j.segan.2025.101626). - **Assessment of electric vehicle charging hub based on stochastic models of user profiles**. Expert Systems with Applications (Vol. 227, p. 120318). Elsevier BV. May 2023. [DOI link](https://doi.org/10.1016/j.eswa.2023.120318). - **Potential benefits of scheduling electric vehicle sessions over limiting charging power**. CIRED Porto Workshop 2022: E-mobility and power distribution systems. Institution of Engineering and Technology, 2022. [DOI link](https://ieeexplore.ieee.org/abstract/document/9841653). - **Flexibility management of electric vehicles based on user profiles: The Arnhem case study**. International Journal of Electrical Power and Energy Systems, vol. 133. Elsevier BV, p. 107195, Dec. 2021. [DOI link](https://doi.org/10.1016/j.ijepes.2021.107195). - **Electric vehicle user profiles for aggregated flexibility planning**. IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe). IEEE, Oct. 18, 2021. [DOI link](https://doi.org/10.1109/isgteurope52324.2021.9639931). ## Acknowledgements This work started under a PhD program in the the University of Girona in collaboration with [Resourcefully](https://resourcefully.nl/), the energy transition consulting company that currently supports the development and maintenance. # Package index ## Data exploratory analysis ### Plots - [`plot_points()`](https://resourcefully-dev.github.io/evprof/reference/plot_points.md) : Scatter plot of sessions - [`plot_density_2D()`](https://resourcefully-dev.github.io/evprof/reference/plot_density_2D.md) : Density plot in 2D, considering Start time and Connection duration as variables - [`plot_density_3D()`](https://resourcefully-dev.github.io/evprof/reference/plot_density_3D.md) : Density plot in 3D, considering Start time and Connection duration as variables - [`plot_histogram()`](https://resourcefully-dev.github.io/evprof/reference/plot_histogram.md) : Histogram of a variable from sessions data set - [`plot_histogram_grid()`](https://resourcefully-dev.github.io/evprof/reference/plot_histogram_grid.md) : Grid of multiple variable histograms ### Sessions data set analysis - [`summarise_sessions()`](https://resourcefully-dev.github.io/evprof/reference/summarise_sessions.md) : Statistic summary of sessions features - [`get_charging_rates_distribution()`](https://resourcefully-dev.github.io/evprof/reference/get_charging_rates_distribution.md) : Get charging rates distribution in percentages - [`get_daily_n_sessions()`](https://resourcefully-dev.github.io/evprof/reference/get_daily_n_sessions.md) : Get daily number of sessions given a range of years, months and weekdays - [`get_daily_avg_n_sessions()`](https://resourcefully-dev.github.io/evprof/reference/get_daily_avg_n_sessions.md) : Get the daily average number of sessions given a range of years, months and weekdays - [`round_to_interval()`](https://resourcefully-dev.github.io/evprof/reference/round_to_interval.md) : Round to nearest interval ## Preprocessing ### DBSCAN outliers cleaning - [`cut_sessions()`](https://resourcefully-dev.github.io/evprof/reference/cut_sessions.md) : Cut outliers based on minimum and maximum limits of ConnectionHours and ConnectionStartDateTime variables - [`plot_kNNdist()`](https://resourcefully-dev.github.io/evprof/reference/plot_kNNdist.md) : Plot kNNdist - [`get_dbscan_params()`](https://resourcefully-dev.github.io/evprof/reference/get_dbscan_params.md) : Get the minPts and eps values for DBSCAN to label only a specific percentage as noise - [`plot_outliers()`](https://resourcefully-dev.github.io/evprof/reference/plot_outliers.md) : Plot outlying sessions - [`detect_outliers()`](https://resourcefully-dev.github.io/evprof/reference/detect_outliers.md) : Detect outliers - [`drop_outliers()`](https://resourcefully-dev.github.io/evprof/reference/drop_outliers.md) : Drop outliers ### Sessions division - [`plot_division_lines()`](https://resourcefully-dev.github.io/evprof/reference/plot_division_lines.md) : Iteration over evprof::plot_division_line function to plot multiple lines - [`divide_by_disconnection()`](https://resourcefully-dev.github.io/evprof/reference/divide_by_disconnection.md) : Divide sessions by disconnection day - [`divide_by_timecycle()`](https://resourcefully-dev.github.io/evprof/reference/divide_by_timecycle.md) : Divide sessions by time-cycle ## Clustering - [`choose_k_GMM()`](https://resourcefully-dev.github.io/evprof/reference/choose_k_GMM.md) : Visualize BIC indicator to choose the number of clusters - [`cluster_sessions()`](https://resourcefully-dev.github.io/evprof/reference/cluster_sessions.md) : Cluster sessions with `mclust` package - [`save_clustering_iterations()`](https://resourcefully-dev.github.io/evprof/reference/save_clustering_iterations.md) : Save iteration plots in PDF file - [`plot_bivarGMM()`](https://resourcefully-dev.github.io/evprof/reference/plot_bivarGMM.md) : Plot Bivariate Gaussian Mixture Models ## Profiling - [`define_clusters()`](https://resourcefully-dev.github.io/evprof/reference/define_clusters.md) : Define each cluster with a user profile interpretation - [`set_profiles()`](https://resourcefully-dev.github.io/evprof/reference/set_profiles.md) : Classify sessions into user profiles ## Modeling ### Connection Models - [`get_connection_models()`](https://resourcefully-dev.github.io/evprof/reference/get_connection_models.md) : Get a tibble of connection GMM for every user profile - [`plot_connection_models()`](https://resourcefully-dev.github.io/evprof/reference/plot_connection_models.md) : Plot all bi-variable GMM (clusters) with the colors corresponding to the assigned user profile. This shows which clusters correspond to which user profile, and the proportion of every user profile. ### Energy Models - [`get_energy_models()`](https://resourcefully-dev.github.io/evprof/reference/get_energy_models.md) : Get a tibble of energy GMM for every user profile - [`plot_energy_models()`](https://resourcefully-dev.github.io/evprof/reference/plot_energy_models.md) : Compare density of estimated energy with density of real energy vector ### EV model object - [`get_ev_model()`](https://resourcefully-dev.github.io/evprof/reference/get_ev_model.md) : Get the EV model object of class `evmodel` - [`save_ev_model()`](https://resourcefully-dev.github.io/evprof/reference/save_ev_model.md) : Save the EV model object of class `evmodel` to a JSON file - [`read_ev_model()`](https://resourcefully-dev.github.io/evprof/reference/read_ev_model.md) : Read an EV model JSON file and convert it to object of class `evmodel` # Articles ### Developer - [Standard data format](https://resourcefully-dev.github.io/evprof/articles/sessions-format.md): - [Outliers detection](https://resourcefully-dev.github.io/evprof/articles/outliers.md): - [EV model object](https://resourcefully-dev.github.io/evprof/articles/evmodel.md): ### Study cases - [California case study](https://resourcefully-dev.github.io/evprof/articles/california.md):