tutorials.scenario_generation package

Submodules

tutorials.scenario_generation.scenario_generation_conditional_pdfs module

src.tutorials.scenario_generation.scenario_generation_conditional_pdfs.main()[source]

Example script for the usage of conditional pdfs scenario generator.

In this tutorial, these operations are carried out in this order:

  • The data from Excel input file ‘tutorials/scenario_generation/input_generator_conditional_pdfs.xlsx’ is read.

  • The data provided by Excel is converted to dictionary datatype with ‘utils.excel_to_sceneration_input_conditional_pdfs’ function.

  • Electric Vehicle Dataframe, which is an electric vehicle fleet scenario, is generated via ‘sceneration.generate_fleet_from_conditional_pdfs’ function with converted dictionary inputs

  • The statistical distribution of generated arrival and departure times and SoCs are visualized via ‘utils.visualize_statistical_generation’ function under ‘/results’.

  • Generated statistical output dataframe is converted into an input dataframe for simulators, which are explained under ‘tutorials/simulations’.

tutorials.scenario_generation.scenario_generation_simple_pdfs module

src.tutorials.scenario_generation.scenario_generation_simple_pdfs.main()[source]

Example script for the usage of simple pdfs scenario generator.

In this tutorial, these operations are carried out in this order:

  • The data from Excel input file ‘tutorials/scenario_generation/input_generator_simple_pdfs.xlsx’ is read.

  • The data provided by Excel is converted to dictionary datatype with ‘utils.excel_to_sceneration_input_simple_pdfs’ function.

  • Electric Vehicle Dataframe, which is an electric vehicle fleet scenario, is generated via ‘sceneration.generate_fleet_from_simple_pdfs’ function with converted dictionary inputs

  • The statistical distribution of generated arrival and departure times and SoCs are visualized via ‘utils.visualize_statistical_generation’ function under ‘/results’.

  • Generated statistical output dataframe is converted into an input dataframe for simulators, which are explained under ‘tutorials/simulations’.

The statistical data for both arrival and departure times are based on a research Takahashi, Tamura, et al., ‘Day-Ahead Planning for EV Aggregators Based on Statistical Analysis of Road Traffic Data in Japan’ in 2020 International Conference on Smart Grids and Energy Systems (SGES), 2020, DOI 10.1109/SGES51519.2020.00028. The rest of the data is not based on any research, the purpose of this tutorial is just to provide the user an example use-case.