How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

Last update: Nov 30, 2022

Related tags

Overview

EV-charging-impact

This repository contains the code that has been used for the Queue modelling for the paper "How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach" by Artur Grigorev, Tuo Mao, Adam Berry, Joachim Tan, Loki Purushothaman, Adriana-Simona Mihaita. The paper has been published and presented during the IEEE ITSC 2021 conference. The preprint is available: https://arxiv.org/abs/2110.14064 .

You can find a working queue model in "queue_model.py" file.

This EV charging station queue simulation program reads file "Northern_Sydney_EV_charger_list.csv" and outputs queue simulation results into file "q2080_2016_seq.csv". It relies on multiprocessing package to perform parallel simulation.

Input parameters of the model:

Duration of modeling (day, week, month)
Number of plugs on EV stations
Distribution of time intervals between arrivals
Distribution of charging time: normaly distributed between 20% and 80%.
Max queue size
Power supply at EV charger: KW/h

Model output:

(O1) Mean queue length of an EV station [n]'] = HOURQUEUE[i]
(O2) Mean waiting time in queue at an EV station [hours]
(O3) Mean service time to charge at an EV station [hours]
(O4) Total time spent overall at an EV station [hours]
(O5) Total energy consumption of an EV station [kWh]
(O6) Maximum recorded queue length of an EV station [n]
(O7) Maximum waiting time in queue at an EV station [hours]
(O8) Maximum time spent overall at an EV station [hours]
(O9) Maximal energy consumption of an EV station [kW]
Consumed electricity by hour [kWh]
Total waiting time (minutes) by hour
Overall Mean Service time/day'

To perform calculations for specific OD traffic flow (2016, OD15, OD30) change the line: DICT['StationFlow'] = float(dt[dt.Name==N]['2016 volume']) at the "Setup" section (to 2016, 15 or 30).

The structure of the framework:

The code to produce lineplots is in "lineplots.ipynb":

The code to produce supplementary animation is in "anim.ipynb":

How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

Related tags

Overview

EV-charging-impact

Input parameters of the model:

Model output:

Owner

Exploration & Research into cross-domain MEV. Initial focus on ETH/POLYGON.

A project for developing transformer-based models for clinical relation extraction

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

DTCN IJCAI - Sequential prediction learning framework and algorithm

This porject is intented to build the most accurate model for predicting the porbability of loan default

Generate fine-tuning samples & Fine-tuning the model & Generate samples by transferring Note On

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

3.8% and 18.3% on CIFAR-10 and CIFAR-100

This is a code repository for paper OODformer: Out-Of-Distribution Detection Transformer

HyperDict - Self linked dictionary in Python

Official PyTorch implementation of BlobGAN: Spatially Disentangled Scene Representations

Web-interface + rest API for classification and regression (https://jeff1evesque.github.io/machine-learning.docs)

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Losslandscapetaxonomy - Taxonomizing local versus global structure in neural network loss landscapes

Official Implementation of VAT

This is the official repository of XVFI (eXtreme Video Frame Interpolation)

Official implementation of Deep Burst Super-Resolution

UFPR-ADMR-v2 Dataset

Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

Code for ICDM2020 full paper: "Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning"