Predicting Energy Consumption in Electric Vehicles: A Machine Learning Approach for Enhanced Efficiency and Sustainability

Gite, Krutika Rajesh (2024) Predicting Energy Consumption in Electric Vehicles: A Machine Learning Approach for Enhanced Efficiency and Sustainability. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

With the increasing rate of EV ownership worldwide, there is renewed interest in gaining a better understanding of the battery’s performance – with emphasis on energy. The research study relies on data from a four-year electric vehicle usage database which includes detailed operational data. Once preliminary data cleaning and the handling of missing values were done, we employed exploratory and predictive analysis on the energy patterns using different forms of regression models. Feature important in energy consumption was estimated by applying feature engineering and correlation analysis. Several multiple regression models were built and tested for their predictive performance with the MAE, RMSE, and the R² being used as performance measures. Accordingly, the outcomes identified the unique indicators and approaches to forecast energy consumption. The conclusion is that this research adds new data-driven approaches to the overall improvement of energy efficiency in the EVs, including battery management and prognostics. The next steps for future work will be the inclusion of other data for the analysis of environmental and operation factors.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Staikopoulos, Athanasios UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HC Economic History and Conditions > Natural resources > Power resources > Energy consumption Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 11:45
Last Modified:	02 Sep 2025 11:45
URI:	https://norma.ncirl.ie/id/eprint/8701

Actions (login required)

View Item