An ensemble learning based multi-objective evolutionary algorithm for the dynamic vehicle routing problem with time windows

The Vehicle Routing Problem (VRP) is a typical combinatorial optimization problem and has been studied for many years. However, there are few researches on the Dynamic Vehicle Routing Problem with Time Window (DVRPTW), which is an extension of VRP and more challenging with changing environmental factors, such as stochastic customer requests. Once changes happen, the routes should be adjusted for the new environments. In this paper, we construct a multi-objective optimization model for the DVRPTW and propose a new algorithm named as EL-DMOEA, where an ensemble learning method is investigated to improve the performance of the algorithm. In EL-DMOEA, to enhance the population’s diversity and accelerate the convergence, three different strategies, i.e., population-based prediction strategy, immigrant strategy and random strategy, are employed in the training process of three kinds of basic models respectively. The experimental results on the test benchmarks reveal that the proposed algorithm is effective to make promising routing plans.