Data mining-based firefly algorithm for green vehicle routing problem with heterogeneous fleet and refueling constraint

Original Source Here


One of the major reasons for the importance of green vehicle routing is that current distribution systems are not sustainable in the long run. Because currently, only conventional economic costs are considered and environmental impacts of logistics strategies are not considered to be an important issue. Green vehicle routing emphasizes the use of clean fuels as an important factor in reducing the environmental pollution. However, due to the shortage of fuel stations providing these types of fuels, careful planning is needed considering the location and time of refueling of vehicles. In this regard, here, it is assumed that vehicles have limited fuel and should go to refueling stations and so fuel stations have also been added to the nodes of the classic vehicle routing problem. In this paper, a mathematical formulation is presented for a green heterogeneous vehicle routing problem and a firefly algorithm is developed to solve it in large-size instances. Two approaches have been used in applying the firefly algorithm. The first approach is the basic firefly algorithm and the second one is the firefly algorithm based on data mining in which the decision tree method reduces solution space and makes smarter fireflies movement. Finally, we have shown that using data mining has a significant effect on improving the performance of the firefly algorithm and by using a decision tree, the efficiency of the algorithm is significantly improved.


Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: