Predictive machine learning for optimal energy management in sustainable transportation systems

Abstract

This study explores the use of predictive machine learning techniques to enhance energy management in sustainable transportation systems, with a specific emphasis on electric vehicles (EVs). The analysis of EV specifications has shown a wide variety of battery capacities, ranging from 55 kWh to 75 kWh. These capacities have a direct impact on the energy storage capacity and the possible driving range of the vehicles. The range of vehicle weights, ranging from 1400 kg to 1700 kg, emphasized the possible effects on energy consumption rates and overall efficiency. The performance capabilities were shown with maximum speeds ranging from 160 km/h to 200 km/h. The energy consumption rates ranged from 0.18 kWh/km to 0.25 kWh/km, suggesting different levels of efficiency. An analysis of energy management data revealed that the lengths traveled varied from 180 km to 220 km, while the average speeds ranged from 50 km/h to 60 km/h. These variations directly affected the rates at which energy was used. The vehicles exhibited higher efficiency metrics by attaining energy consumption rates of 4.0 km/kWh to 5.6 km/kWh. The analysis of ambient variables indicated temperature fluctuations ranging from 20°C to 30°C, as well as a variety of terrain types that impact driving conditions and energy requirements. Predictive machine learning models demonstrated high accuracies, with Mean Absolute Error (MAE) values ranging from 0.13 to 0.18 kWh/km, Root Mean Squared Error (RMSE) values ranging from 0.18 to 0.22 kWh/km, and R-squared (R^2) scores ranging from 0.80 to 0.88. These results emphasize the need of using predictive machine learning to estimate energy consumption, optimize energy management systems, and address sustainable transportation concerns in order to improve the efficiency and sustainability of electric vehicles.