E-Mobility Advisor for Connected and Autonomous Vehicles Environments
Ahmad M. Khasawneh, Prashant Singh, Geetika Aggarwal, Rajkumar Singh Rathore and Omprakash Kaiwartya
The development and research carried out in this paper, delves into the area of electric mobility (E-Mobility) conversion and the scepticism, doubts on utilising electric vehicles for large scale transportation and personal use. Based on the problem domain outlined by the scrutiny of the existing literature, a prototype E-Mobility Advisor has been developed, and it is demonstrated through data analysis, machine learning and route planning how a user can observe how an electric vehicle is much cheaper to run than a traditional fuel-based vehicle by collating user driving data and quantifying this data. It demonstrates how much an alternative electric vehicle can cost for the same journey completed by the user’s fuel vehicle, also demonstrating which locations they have visited obtaining this driving data. Additionally, machine learning is utilised to analyse the current data set trend and make predictions for a week’s time in how many miles a user will complete, and the costs associated to this. The executions of this software proved to be successful with the analysis completed within the results section, where user feedback was collated on the system as a whole, as well as justifying the costs and predictions formed through the automatic data analysis through calculations. A thorough analysis has been completed outlining the successful elements of the developed prototypes operation, as well as outlining where the project could be extended and how it would operate and be used within an industry environment.
Keywords: E-Mobility, Electric Vehicles, Vehicular Traffic Environment, Green Transport
Full Text (IP)