• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.167-178
• /
• 2019

In this paper, we study the multi-objectives vehicle and drone routing problem with time windows, MOVDRPTW for short, which is defined in an urban delivery network. We consider the dual modal delivery system consisting of drones and vehicles. Drones are used as a complement to the vehicle and operate in a point to point manner between the depot and the customer. Customers make various requests. They prefer to receive delivery services within the predetermined time range and some customers require fast delivery. The purpose of this paper is to investigate the effectiveness of the delivery strategy of using drones and vehicles together with a multi-objective measures. As experiment datasets, we use the instances generated based on actual courier delivery data. We propose a hybrid multi-objective evolutionary algorithm for solving MOVDRPTW. Our results confirm that the vehicle-drone mixed strategy has 30% cost advantage over vehicle only strategy.

• IE interfaces
• /
• v.11 no.1
• /
• pp.67-74
• /
• 1998

This study is to develop a vehicle scheduling system for the efficient delivery of goods to places of business. For gathering data and testing the system developed, we have chosen a company which is located in Taegu city and has more than 700 delivery points over Taegu city and Kyungbuk province. We consider multiple vehicle types, travel time restrictions on vehicles, vehicle acceptance restrictions at delivery points, and other operational restrictions. We divide the whole delivery points into 44 regions and generate a region-based shortest path tree. Based on the shortest path tree, we perform vehicle assignment sequentially for each vehicle used. Then vehicle routings are determined. We have implemented the whole procedure on computer system. The system developed is flexible enough to be applicable to other companies by just changing the standard data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.138-145
• /
• 2013

A sweep-based heuristic using common area is developed for multi-vehicle VRPs under time various and unsymmetric forward and backward vehicle moving speed. One depot and 2 delivery vehicle are assumed in this research to make the problem solving strategy simple. A common area is held to make adjustment of possible unbalance of between two vehicle delivery completion times. The 4 time zone heuristic is used to solve for efficient delivery route for each vehicle. The current size of common area needs to be studied for better results, but the suggested problem solving procedures can be expanded for any number of vehicles.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.2
• /
• pp.193-204
• /
• 2013

The growing logistics strategy of a company is to optimize their vehicle route scheduling in their supply chain system. It is very important to analyze for continuous pickups and delivery vehicle scheduling. This paper is a computational study to investigate the effectiveness of continuous pickups and delivery vehicle routing problems. These scheduling problems have 3 subproblems; Inbound Vehicle Routing Problem with Makespan and Pickup, Line-haul Network Problem, and Outbound Vehicle Routing Problem with Delivery. In this paper, we propose 5 heuristic Algorithms; Selecting Routing Node, Routing Scheduling, Determining Vehicle Type with Number and Quantity, and Modification Selecting Routing Node. We apply these Algorithms to S vehicle company. The results of computational experiments demonstrate that proposed methods perform well and have better solutions than other methods considering the basic time and due-date.

• Journal of the Korea Safety Management & Science
• /
• v.19 no.3
• /
• pp.129-135
• /
• 2017

The respective delivering vehicle loaded with the own cargo moves into the respective delivery area. At the base, the delivery points D1 and D2, for example, have the same starting point but the destination is different. The average delivering time of the delivery vehicle is mostly more than 8 hours a day. Therefore, the efficiency of delivery is generally low. In this study, the deliveries will be forwarded from a base station to a delivery point where cross docking will be applied to a single vehicle, and will be distributed from the cross docking point through cross docking. If the distribution is implemented, one vehicle will not have to be operated from the base to the cross docking point. In that case, logistics cost will be reasonably saved by the reduction of transportation cost and labor time. If one vehicle only runs from the base to the cross docking point, each vehicle will be operated in two shifts, and the vehicle operation can be efficiently implemented. This research model is based on the assumption that the 3 types of ratios between the traffic volume of the vehicles starting at the base and the vehicles waiting at the cross docking point are set to the first ratio of 30% to 70%, the second ratio of 50% to 50% and the final ratio of 70% to 30%. As a result of the study, The delivery time in the cross docking point is much higher than that in present on the condition that the cargo volume in the D2 area is more than 50%. Likewise, the delivery time is slightly higher on the condition that the cargo volume is less than 50%. Time is reduced in terms of 50% model like AS-IS model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.38 no.3
• /
• pp.1-7
• /
• 2015

This research is to develop a possible process to apply k-means clustering to an efficient vehicle routing process under time varying vehicle moving speeds. Time varying vehicle moving speeds are easy to find in metropolitan area. There is a big difference between the moving time requirements of two specific delivery points. Less delivery times are necessary if a delivery vehicle moves after or before rush hours. Various vehicle moving speeds make the efficient vehicle route search process extremely difficult to find even for near optimum routes due to the changes of required time between delivery points. Delivery area division is designed to simplify this complicated VRPs due to time various vehicle speeds. Certain divided area can be grouped into few adjacent divisions to assume that no vehicle speed change in each division. The vehicle speeds moving between two delivery points within this adjacent division can be assumed to be same. This indicates that it is possible to search optimum routes based upon the distance between two points as regular traveling salesman problems. This makes the complicated search process simple to attack since few local optimum routes can be found and then connects them to make a complete route. A possible method to divide area using k-means clustering is suggested and detailed examples are given with explanations in this paper. It is clear that the results obtained using the suggested process are more reasonable than other methods. The suggested area division process can be used to generate better area division promising improved vehicle route generations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.1
• /
• pp.133-140
• /
• 2014

An efficient heuristic for two-vehicle-one-depot problems is developed in this research. Vehicle moving speeds are various along hour based time intervals due to traffic jams of rush hours. Two different heuristics are examined. One is that the delivery area assignment is made using Sweep algorithm for two vehicles by splitting the whole area in half to equally divide all delivery points. The other is using common area by leaving unassigned area between the assigned for two vehicles. The common area is reassigned by two stages to balance the completion time of two vehicle's delivery. The heuristic with common area performed better than the other due to various vehicle moving speeds and traffic jams.

• Journal of Korean Institute of Industrial Engineers
• /
• v.30 no.4
• /
• pp.346-354
• /
• 2004

Most industrial logistic systems have focused on carrying products from manufacturers or distribution centers to customers. In recent years, they are faced with the problem of integrating reverse flows into their transportation systems. In this paper, we address the vehicle routing problems with mixed delivery and pick-up(VRPMDP). Mixed operation of delivery and pick-up during a vehicle tour requires rearrangement of the goods on board. The VRPMDP considers the reshuffling time of goods at customers, hard time windows, and split operation of delivery and pick-up. We construct a mixed integer mathematical model and propose a new genetic algorithm named GAMP for VRPMDP. Computational experiments on various types of test problems are performed to evaluate GAMP against the modified Dethloff's algorithm. The results show that GAMP reduces the total vehicle operation time by 5.9% on average, but takes about six times longer computation time.

• Journal of Aerospace System Engineering
• /
• v.14 no.6
• /
• pp.1-9
• /
• 2020

Global e-commerce and delivery companies are actively pursuing last-mile delivery service using drones, and various delivery schedule planning studies have been conducted. In this study, separate individual route networks were constructed to reflect drone route constraints such as prohibited airspace and truck route constraints such as rivers, which previous studies did not incorporate. The A* algorithm was used to calculate the shortest path distance matrix between the starting point and destinations. In addition, we proposed an optimal delivery schedule plan using genetic algorithms and applied it to compare the efficiency with that of vehicle-only delivery.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.143-153
• /
• 2021

In this paper, we propose "flexible routing with flex" to provide fast delivery by using the flexible routing for the delivery vehicle and crowd-shipper named flex. To this end, we have introduced an algorithm that can build the delivery plan for delivery vehicles and flexes. The introduced algorithm uses the 2-opt algorithm to construct routes with low complexity and acceptable quality, and the revised saving algorithm to assign customer orders to the flex. The algorithm allows the vehicle and the flex to function complement each other without separating the delivery vehicle from the flex. The experiments consider the 3 different instances named Random, Mixed, Cluster, and show that "the flexible routing with flex" has a better result than "vehicle only". The sensitivity analysis of the flex cost and time penalty shows "the flexible routing with flex" can provide better service not only to the customers who are serviced by flex but also to the customers who are serviced by the delivery vehicle.