Data

Tools

Indexes

Applications

Experiments

Open Source Science

pcrl

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks

https://github.com/ashusao/pcrl

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.3%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks

Basic Info
  • Host: GitHub
  • Owner: ashusao
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 386 KB
Statistics
  • Stars: 11
  • Watchers: 3
  • Forks: 4
  • Open Issues: 10
  • Releases: 0
Created over 3 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

PCRL

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks

Description

This repository is the implementation of the project "Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks" by Leonie von Wahl, Nicolas Tempelmeier, Ashutosh Sao and Elena Demidova. In this project, we train a model with Deep Q Network Reinforcement Learning to place charging stations in a road network.

Installation

We use Stable Baselines3 as Reinforcement training framework. Moreover, we use Gym to create the RL environment and OSMnx to work with road networks. We use Python 3.8.10.

To install the requirements bash git clone git@github.com:frantz03/PCRL.git pip install -r final_requirements.txt

Toy Example Dataset

Before training the models, some data are needed. The data preparation can be done with load_graph.py and nodes_preparation.py. However, we will not upload our own data here. Instead, we offer a preprocessed toy example of fake data. With this toy example, the training and evaluation can be tested.

Training & Evaluation

To train a model on an example raod network run reinforcement.py. The custom environment is described in env_plus.py.

To generate a charging plan from the model run model_eval.py.

Finally, to evaluate the charging plan with the metrics from the utility model ( in evaluation_framework.py) run test_solution.py.

Visualisation

To visulalise the results, run visualise.py.

Folder structure

For the data: Graph/<location>/

For the images: Images/<location>/

For the results: Results/<location>/

Owner

  • Name: Ashutosh Sao
  • Login: ashusao
  • Kind: user
  • Location: Hannover, Germany

A Machine Learning Enthusiast, pursuing PhD. in the same at L3S Research Cebter, Hannover.

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Reinforcement Learning-based Placement of Charging
  Stations in Urban Road Networks
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Leonie
    family-names: von Wahl
    orcid: 'https://orcid.org/0000-0003-0013-831X'
  - given-names: 'Nicolas '
    family-names: Tempelmeier
  - given-names: Ashutosh
    family-names: Sao
  - given-names: 'Elena '
    family-names: Demidova
repository-code: 'https://github.com/ashusao/PCRL'
license: MIT
date-released: '2022-11-04'

GitHub Events

Total
  • Issues event: 1
  • Watch event: 8
Last Year
  • Issues event: 1
  • Watch event: 8

Dependencies

final_requirements.txt pypi
  • Fiona ==1.8.21
  • Pillow ==9.1.1
  • Rtree ==1.0.0
  • Shapely ==1.8.2
  • attrs ==21.4.0
  • certifi ==2022.6.15
  • charset-normalizer ==2.1.0
  • click ==8.1.3
  • click-plugins ==1.1.1
  • cligj ==0.7.2
  • cloudpickle ==2.1.0
  • cycler ==0.11.0
  • fonttools ==4.33.3
  • geopandas ==0.11.0
  • gym ==0.21.0
  • gym-notices ==0.0.7
  • idna ==3.3
  • importlib-metadata ==4.12.0
  • kiwisolver ==1.4.3
  • matplotlib ==3.5.2
  • munch ==2.5.0
  • networkx ==2.8.4
  • numpy ==1.23.0
  • osmnx ==1.2.1
  • packaging ==21.3
  • pandas ==1.4.3
  • pyparsing ==3.0.9
  • pyproj ==3.3.1
  • python-dateutil ==2.8.2
  • pytz ==2022.1
  • requests ==2.28.1
  • six ==1.16.0
  • stable-baselines3 ==1.5.0
  • torch ==1.12.0
  • typing_extensions ==4.2.0
  • urllib3 ==1.26.9
  • zipp ==3.8.0