Abstract :

The Rapid Adoption Of Electric Vehicles (EVs) Has Significantly Increased The Demand For Efficient Energy Management And Intelligent Charging Infrastructure. Predicting Energy Consumption Accurately Is A Critical Component For Optimizing Charging Schedules, Reducing Grid Load, And Improving User Experience. This Research Presents A Machine Learning-based Approach For Predicting Electric Vehicle Energy Consumption Using Realworld Charging Station Data. The System Utilizes Historical Datasets Containing Various Attributes Such As Charging Duration, Energy Consumed, Location Details, Vehicle Specifications, And Charging Patterns.The Proposed Model Integrates Multiple Machine Learning Algorithms, Including K-Nearest Neighbors (KNN), Decision Tree, And Support Vector Machine (SVM), Combined Using A Voting Classifier For Improved Prediction Accuracy. The Dataset Is Preprocessed Using Feature Extraction Techniques Such As Count Vectorization, Enabling Effective Handling Of Textual Identifiers Like Session IDs. The Classification Problem Is Defined As Predicting Energy Demand Levels Categorized Into “High” And “Low” Based On Consumption Patterns.The System Is Developed Using The Django Framework, Which Provides A Robust Web-based Interface For Users To Input Charging Data And Retrieve Predictions. Additionally, Administrative Modules Are Implemented For Monitoring User Activity, Visualizing Trends, And Analyzing Prediction Accuracy Through Graphical Representations. The System Also Supports Dataset Export Functionality, Enabling Further Offline Analysis.Experimental Results Demonstrate That The Ensemble-based Voting Classifier Outperforms Individual Models In Terms Of Accuracy And Robustness. The System Effectively Captures Patterns In Charging Behavior And Provides Reliable Predictions For Energy Demand Classification. This Contributes To Improved Decision-making For Both Users And Service Providers.Overall, The Proposed System Offers A Scalable And Efficient Solution For EV Energy Consumption Prediction, Supporting The Development Of Smart Transportation Systems And Sustainable Energy Utilization. Future Enhancements May Include Integration With Deep Learning Models And Real-time IoT Data Streams For Dynamic Prediction.

Published:

07-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1468-1476

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite