Electric vehicles are transforming urban mobility by providing a cleaner alternative to conventional combustion engines. However, challenges related to route optimization and access to reliable charging infrastructure continue to limit their performance in many developing countries. This study addresses these issues through an enhanced electric vehicle path planning with time frame (EVPPTF) approach that focuses on minimizing travel time and energy use while meeting user deadlines and accounting for the spatial distribution of charging stations. Although Dijkstra’s algorithm and decision tree models are well-established methods, the main contribution of the paper lies in the development of a hybrid and time-aware framework that integrates these techniques in a coordinated manner to support real-time path planning and charging decisions for electric vehicles. The proposed method improves the classical Dijkstra search by embedding energy consumption constraints, traffic-aware weights, and charging station accessibility checks. In addition, the decision tree model is extended to predict optimal charging stops using features derived from real-time data, including traffic flow, station availability, and remaining battery levels. The study also presents a comparative performance evaluation using real traffic patterns from Indian cities, which demonstrates that the hybrid method outperforms traditional techniques, including decision trees, random forests, k-nearest neighbors, and support vector regression. Validation in cities such as Hyderabad and Bengaluru shows that the proposed system consistently reduces travel duration and energy use under realistic conditions. The findings contribute to smarter and more sustainable urban transportation by supporting autonomous driving applications, guiding the placement of charging stations, and offering a scalable approach that can be adopted in developing countries facing similar EV mobility challenges.
Raviprabhakaran et al. (Fri,) studied this question.