Difference between revisions of "Project with chargefinder.com"

From ISLAB/CAISR
 
Line 1: Line 1:
 
{{StudentProjectTemplate
 
{{StudentProjectTemplate
 
|Summary=Use data to create a machine learning model that can predict estimated availability of a specific charger based on day, time and maybe other external factors (holiday, weather)
 
|Summary=Use data to create a machine learning model that can predict estimated availability of a specific charger based on day, time and maybe other external factors (holiday, weather)
|TimeFrame=Fall 2023
+
|TimeFrame=Fall 2024
 
|References=http://chargefinder.com/
 
|References=http://chargefinder.com/
 
|Supervisor=TBD, please contact Sławomir Nowaczyk if interested
 
|Supervisor=TBD, please contact Sławomir Nowaczyk if interested

Latest revision as of 21:09, 24 August 2024

Title Project with chargefinder.com
Summary Use data to create a machine learning model that can predict estimated availability of a specific charger based on day, time and maybe other external factors (holiday, weather)
Keywords
TimeFrame Fall 2024
References http://chargefinder.com/
Prerequisites
Author
Supervisor TBD, please contact Sławomir Nowaczyk if interested
Level Master
Status Open


I’m currently helping out with another project chargefinder.com <http://chargefinder.com/> - a Swedish-made non-profit website and mobile app to lookup EV chargers and availability. Currently the #1 website in this industry in Sweden and Norway with over 100.000 unique visitors per month.

We have realtime availability status for most of the electric vehicle chargers in Sweden and have also collected historical metrics for the last 12 months in a structured format.

My vision is to use this data to create a machine learning model that can predict estimated availability of a specific charger based on day, time and maybe other external factors (holiday, weather etc).

If you think this could be an interesting project for the students this upcoming spring, please let me know and I will be happy to setup access to datasets and do a briefing about how everything works.