Cloud-Edge Collaboration And Crowdsourcing Based Spare Parts Delivery Optimization

In this thesis,the delivery of spare parts involved in manufacturing and after-sales service of enterprises is taken as the starting point of the study.From the perspective of saving delivery time or cost,the optimization methods of spare parts delivery are studied in depth.The main contributions of this thesis are as follows:Aiming at the problem that the delivery process of spare parts is vulnerable to changes in road conditions,a spare parts delivery optimization method based on cloud-edge collaboration is proposed.The method firstly uses genetic algorithm to solve the initial delivery scheme in the cloud according to the delivery requirements and existing delivery resources.Then,in the delivery process,the edge device senses the road traffic condition in the delivery area in real time,and judges the impact of the road condition change on the completion of the delivery task.The improved A* algorithm is used to adjust and optimize the sub-path of the initial delivery scheme in real time.Experiments with the delivery demand data of an enterprise show that this method can deal with the impact of road condition changes and effectively optimize the delivery time of spare parts.Aiming at the spare parts delivery demand with low real-time requirements,a spare parts delivery optimization method based on Crowdsourcing is proposed.In this method,private cars with relatively fixed commuting routes are regarded as the vehicles that can meet the delivery requirements of spare parts,and the optimization problem of spare parts delivery routes is transformed into the matching problem between private cars’ routes and spare parts delivery tasks.On this basis,the delivery cost of spare parts can be optimized by selecting the vehicle that meets the constraints of the delivery task and has the lowest cost.The simulation results show the effectiveness of the proposed method.