Optimizing Electric Vehicle Ride-Hailing Fleets through Artificial Intelligence

Research conducted by the Beijing Institute of Technology has resulted in a novel combination of deep learning algorithms with large-scale real-world charging data, providing practical solutions for promoting electric vehicle adoption and achieving low-carbon transportation. The study aimed to analyze current charging behaviors and evaluate the impact of key variables on costs and emissions, addressing a critical research gap in optimizing EV ride-hailing fleets. The integration of AI in operations could help achieve dual objectives of reducing charging costs and lowering carbon emissions.

Key Takeaways:

• The research focuses on developing a Neural Network (NN) trained with the Adaptive Moment Estimation (Adam) algorithm to optimize EV ride-hailing charging behavior, addressing a significant gap in empirical studies.
• The study analyzes 2.14 million charging events to evaluate the impact of key variables on costs and emissions, providing data-driven insights for potential improvements.
• The novel combination of deep learning algorithms with large-scale real-world charging data proposes a new method for optimizing EV ride-hailing charging behavior.
• The integration of AI in operations could substantially help achieve the dual objectives of reducing charging costs and lowering carbon emissions.
• The study provides practical solutions for promoting electric vehicle adoption and achieving low-carbon transportation.
• The research was made possible with financial support from the National Natural Science Foundation of China and the Ministry of Science and Technology of the People's Republic of China.
• Authors of the study include Kaizhe Chen, Jin Liu, Wenjing Lyu, Tianyuan Wang, and Jinxi Wen from the Beijing Institute of Technology.

Statistics:

• 2.14 million charging events were analyzed in the study to evaluate the impact of key variables on costs and emissions.
• The study proposes a new method for optimizing EV ride-hailing charging behavior using a deep neural network approach.
• The integration of AI in operations could help reduce charging costs by X% and lower carbon emissions by Y% in ride-hailing fleets.
• The research addresses a significant gap in empirical studies focusing on optimizing the charging behavior of operational EV fleets.

Sources:

• A deep neural network approach for optimizing charging behavior for electric vehicle ride-hailing fleet. Scientific Reports, 2025;15(1):21451.
• National Natural Science Foundation of China
• Ministry of Science and Technology of the People's Republic of China
• Beijing Institute of Technology