The growing adoption of electric vehicles (EVs) presents a significant challenge in accurately predicting their energy consumption. As countries move towards more sustainable transportation, forecasting energy demand is crucial for infrastructure development, grid management, and battery optimisation. This project, "A Comprehensive Systematic Review of Techniques for Predicting Electric Vehicle Energy Demand," evaluates machine learning algorithms used for energy consumption forecasting in electric vehicles.The review focuses on algorithms such as Random Forest, Logistic Regression, Decision Trees, and K-Nearest Neighbors. These models were assessed for their ability to predict energy consumption based on various factors, including driving behavior, weather, terrain, and vehicle specifications. Each algorithm’s strengths and limitations were considered, with Random Forest proving particularly effective for handling complex, non-linear data, while Logistic Regression and KNN offered computational efficiency and simplicity. Through an in-depth analysis of existing research, the study also identifies key challenges in energy demand forecasting, such as data noise, missing values, and the need for real-time data integration. The review suggests that future improvements could be made through the incorporation of deep learning techniques like LSTM networks, which are well-suited for time- series data, and the integration of real-time data from vehicle sensors and charging stations.By synthesising current research, this project aims to enhance the accuracy and robustness of energy demand predictions, helping to optimise EV battery usage, infrastructure planning, and energy grid management. It offers valuable insights for researchers and stakeholders in the electric vehicle and energy sectors,paving the way for more efficient, sustainable transportation systems. Keywords: Random Forest, Logistic Regression, Decision Trees, and K-Nearest Neighbores
N et al. (Sun,) studied this question.