Research On Vehicle Distribution Optimization Under Cloud Logistics Service Model

With the combination of technologies and logistics such as the Internet of Things and cloud computing,the cloud logistics service model with the cloud logistics service platform as the core is the key to the current traditional enterprises to cope with the dynamic and changing market competition environment and enhance their own international competitiveness.Distribution is an extremely critical link in the logistics system.With more and more enterprises demanding customized,specialized and personalized logistics services,the efficiency of vehicle distribution under the cloud logistics service model directly affects the logistics costs of enterprises and has an important impact on the production and operation of enterprises.Therefore,it is particularly important to study the optimization of vehicle distribution under the cloud logistics service model.This paper is based on the 2017 Baohe District Government of Hefei City carrying out a scientific and technological achievements transformation project-"Cloud Logistics and Key Technology Research and Industrialization of Big Data Services".This project builds a cloud logistics service model platform.Focusing on the delivery order,the vehicle distribution optimization problem is researched on the multi-center single-model distribution optimization problem with time window and the multi-center multi-model distribution optimization problem considering the pickup demand.First,for the multi-center single-vehicle distribution optimization problem with time window constraints,considering the situation that the distribution vehicle returns to different distribution centers after completing the distribution service,the paper uses the k-means algorithm to cluster the distribution orders on the cloud logistics service platform.The paper establishes a vehicle distribution optimization model aiming at driving distance,time penalty cost,fixed cost and remaining loading capacity,and builds an improved genetic algorithm based on Bellman-Ford model solution.The paper uses Bellman-Ford algorithm to divide the optimal path of the genetic algorithm's chromosomes,and obtains a multi-objective function comprehensive optimal distribution plan when the vehicle capacity and other constraints are met.By analyzing the results of the examples,the feasibility and applicability of the model and the solution method are verified.Secondly,in view of the multi-center and multi-vehicle distribution optimization problem whenconsidering the demand for pickup with time window constraints,the paper establishes a vehicle distribution optimization model aiming at driving distance,time penalty cost,fixed cost and remaining loading capacity,and builds a hybrid algorithm combining genetic algorithm and simulated annealing algorithm to solve the model,combined with example data to simulate calculation of the solution algorithm.Through the result analysis and factor analysis,the applicability of the model and solution method is verified,and the influence of time window constraints and different objective functions on the optimization problem is analyzed.The research results of this paper are applied to the decision of vehicle distribution optimization under the cloud logistics service platform,which is of great significance to reduce the logistics cost under the cloud logistics service model and improve the utilization rate of vehicle loading capacity.At the same time,it can also contribute to the supply-side reform of the logistics industry,promote the deep integration of the logistics industry and the Internet,and improve the competitiveness of enterprises in the dynamic and changing global market.