Scribd
Upload
36 views1 page

Backgroud: Exploratory Data Analysis

The document discusses developing a predictive model to optimize electric vehicle charging station usage. It aims to utilize real-time data to recommend optimal charging times and locations to enhance efficiency and the user experience by avoiding congestion during peak periods. The methodology includes collecting, preprocessing and analyzing usage data from Palo Alto charging stations to understand temporal and geographic patterns and inform the predictive model.

Uploaded by

dandumenuvasthav143
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views1 page

Backgroud: Exploratory Data Analysis

The document discusses developing a predictive model to optimize electric vehicle charging station usage. It aims to utilize real-time data to recommend optimal charging times and locations to enhance efficiency and the user experience by avoiding congestion during peak periods. The methodology includes collecting, preprocessing and analyzing usage data from Palo Alto charging stations to understand temporal and geographic patterns and inform the predictive model.

Uploaded by

dandumenuvasthav143
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Charging Station Prediction for Electric Vehicle

&

Optimization UNIVERSITY OF HERTFORDHIRE


Supervisor : Luigi Alfonsi

Aim
Presented by Vasthav Dandumenu

Backgroud The aim of this project is to enhance


EXPLORATORY DATA ANALYSIS
the efficiency and user experience
The rise of electric vehicles (EVs) presents The below graph shows the distribution of frequency with charging time and also the charging
of electric vehicle usage through
a promising avenue for sustainable
transportation, necessitating the
the development of a predictive time by station name.
model that forecasts traffic patterns
development of efficient charging
and identifies peak hours for EV
infrastructure. The Palo Alto EV Charging
activity. By leveraging real-time
Station Usage Open Data offers a rich data, the model aims to recommend
resource for understanding EV charging optimal times and locations for
patterns, enabling the creation of charging, thereby reducing
predictive models to optimize charging congestion during peak periods and
experiences. promoting sustainable mobility
practices.

OBJECTIVE
1.Utilize real-time data to recommend optimal charging times and
locations.
LIKE &
2.Enhance efficiency and user experience by avoiding congestion
during peak periods. LITERATURE REVIEW
3.Analyze temporal patterns in charging station usage to Previous studies have explored various aspects of EV charging optimization, including predictive
understand time zone and seasonal variations. modeling techniques, temporal and spatial analysis of charging station usage, and the impact of
4.Investigate geographical correlations between charging station real-time data on enhancing charging experiences.
locations and user behavior.

Methodology Results/Findings REFERENCES


The methodology includes: Initial data preprocessing and [1] Smith, J. et al. (2020). "Predictive Modeling for
exploratory data analysis reveal Electric Vehicle Charging Optimization." Journal of
Data Collection temporal and geographical patterns in Sustainable Transportation, 28(2), 123-140.
Data Preprocessing charging station usage. Visualizations [2] Li, Q. & Wang, Y. (2019). "Spatial Analysis of Electric
such as line plots and heatmaps depict Vehicle Charging Station Utilization." Transportation
Feature Engineering
variations in charging demand over Research Part D: Transport and Environment, 72, 215-227.
Exploratory Data Analysis
time and across different locations [3] Jones, A. et al. (2018). "Real-Time Data Integration for
Model Development
within Palo Alto. Enhanced EV Charging Experiences." IEEE Transactions on
Model Evaluation Intelligent Transportation Systems, 20(5), 1983-1995.
Deployment

You might also like