Vehicle routing problem with time windows and carbon emissions: a case study in logistics distribution

Area of Science:

• Environmental Science
• Operations Research
• Transportation Engineering

Background:

• The logistics and transportation sector is a significant contributor to energy consumption and carbon emissions.
• Vehicle transportation's carbon footprint is influenced by routing, road conditions, speed, and speed variations.
• Sustainable development in logistics necessitates the adoption of green logistics practices.

Purpose of the Study:

• To address the low-carbon vehicle routing problem (LCVRP) considering high-granularity, time-dependent speeds, speed fluctuations, road conditions, and time windows.
• To accurately model and evaluate the impact of traffic dynamics on carbon emissions.
• To develop an effective algorithm for optimizing vehicle routes to minimize carbon emissions.

Main Methods:

• A graph convolutional network (GCN) was employed to predict high-granularity, time-dependent traffic speeds.
• A hybrid genetic algorithm integrated with adaptive variable neighborhood search was developed to solve the LCVRP.
• The proposed methodology was validated using real-world logistics and traffic data from Jingzhou, China.

Main Results:

• The GCN effectively predicted time-dependent traffic speeds with high granularity.
• The hybrid genetic algorithm successfully generated low-carbon vehicle routes.
• The case study demonstrated the practical effectiveness of the proposed method in reducing carbon emissions.

Conclusions:

• The developed approach provides a robust solution for the complex low-carbon vehicle routing problem.
• Integrating traffic prediction with advanced routing algorithms is crucial for achieving green logistics.
• This research offers a viable strategy for reducing the environmental impact of the logistics industry.