Study On Intelligent Vehicle Routing Planning For Emergency Scheduling

The vehicle routing problem in emergency situation is a kind of combinatorial optimization problem that the vehicle meets the constraints of customer priority,realtime planning,vehicles’ capacity under the condition of limited resources,accesses the customer with reasonable path to maximize the distribution revenue.The research on this problem can effectively integrate the existing resources,reduce the loss of personnel and property,and has the significance of theoretical guidance for the real emergency situation.In this paper,we study the vehicle routing problem with task priority and limited resources and the real-time vehicle routing problem with uncertain demand in emergency scenarios.In the first problem,the pointer neural network proposed in this paper,and genetic algorithm and differential evolution algorithm are used to verify the effectiveness of the algorithm.The parameter sensitivity of each algorithm is assessed using different datasets.Then,comparison experiments with the three algorithms employing optimal parameter configurations are performed for the validation sets,which are generated at different instance scales.In the second problem,based on the first problem,we continue to consider the situation of uncertain demand,train the pointer neural network with variable length tasks and variable capacity vehicles,and generate a variety of scale validation sets.Under this dataset,we compare it with genetic algorithm,and verify the response speed and the solution result performance of pointer neural network algorithm to the random demand.In the two kinds of vehicle routing problems in the emergency scenario,the solution time of the pointer neural network proposed in this paper is far less than that of genetic algorithm and differential evolution algorithm,and the response speed is faster when there is a random demand,and there is a better solution result in the case of medium and large scale.Therefore,this method can provide decision-makers with efficient decision-making scheme in a very short time,which is of great significance to vehicle planning in emergency situations,and provides a new solution to the variant problem of vehicle routing problem.