Fuel Consumption and Carbon Emission Reduction in Dvrp Using Ant Colony Optimization

Delivery vehicles significantly contribute to urban congestion and carbon emissions due to their elevated fuel consumption. Difficulties with routing delivery vehicles may be remedied through route optimization, which would substantially reduce fuel consumption and emissions. This paper aims to find acceptable optimization strategies for sustainable vehicle routing problems, specifically lowering fuel usage and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex> emissions. The employment of optimization model for route planning that effectively reduces carbon emissions and fuel consumption based on ant colony optimization. The datasets were acquired from several sources, including Google Maps, with a particular emphasis on the Kuala Lumpur Malaysia region. Experimental results indicated that ant colony optimization outperformed the genetic algorithm in solving a DVRP problem, with an optimal route of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 1. 5 2 ~ K M}$</tex> compared to the genetic algorithm's <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 4. 0 7}$</tex> KM. A genetic algorithm resulted in a 43 % decrease in fuel usage and a 37.5 percent reduction in carbon emissions. The ant colony optimization resulted in a 35 % reduction in fuel usage and 30 % in carbon emissions. AI optimization solutions can potentially be a promising new area of focus in pursuing sustainable logistics. This breakthrough technology helps organizations combine profitability and environmental responsibility for a more sustainable and efficient future. This study proves AI optimizer can change vehicle routing optimization and initiates the foundation for future improvements.