Search results

Drugs are strategic products with essential functions in human health. An optimum design of the pharmaceutical supply chain is critical to avoid economic damage and adverse effects on human health. The vehicle-routing problem, focused on finding the lowest-cost routes with available vehicles and constraints, such as time constraints and road length, is an important aspect of this. In this paper, the vehicle routing problem (VRP) for a pharmaceutical company in Turkey is discussed.

A mixed-integer programming (MIP) model based on the vehicle routing problem with time windows (VRPTW) is presented, aiming to minimize the total route cost with certain constraints. As the model provides an optimum solution for small problem sizes with the GUROBI® solver, for large problem sizes, metaheuristic methods that simulate annealing and adaptive large neighborhood search algorithms are proposed. A real dataset was used to analyze the effectiveness of the metaheuristic algorithms. The proposed simulated annealing (SA) and adaptive large neighborhood search (ALNS) were evaluated and compared against GUROBI® and each other through a set of real problem instances.

The model is solved optimally for a small-sized dataset with exact algorithms; for solving a larger dataset, however, metaheuristic algorithms require significantly lesser time. For the problem addressed in this study, while the metaheuristic algorithms obtained the optimum solution in less than one minute, the solution in the GUROBI® solver was limited to one hour and three hours, and no solution could be obtained in this time interval.

The VRPTW problem presented in this paper is a real-life problem. The vehicle fleet owned by the factory cannot be transported between certain suppliers, which complicates the solution of the problem.

This paper aims to address a distributed assembly permutation flow-shop scheduling problem (DAPFSP) considering budget constraints and factory eligibility. The first stage of the considered production system is composed of several non-identical factories with different technology levels and so the factories' performance is different in terms of processing time and cost. The second stage is an assembly stage wherein there are some parallel work stations to assemble the ready parts into the products. The objective function is to minimize the maximum completion time of products (makespan).

First, the problem is formulated as mixed-integer linear programing (MIP) model. In view of the nondeterministic polynomial (NP)-hard nature, three approximate algorithms are adopted based on variable neighborhood search (VNS) and the Johnsons' rule to solve the problem on the practical scales. The proposed algorithms are applied to solve some test instances in different sizes.

Comparison result to mathematical model validates the performance accuracy and efficiency of three proposed methods. In addition, the result demonstrated that the proposed two-level self-adaptive variable neighborhood search (TLSAVNS) algorithm outperforms the other two proposed methods. Moreover, the proposed model highlighted the effects of budget constraints and factory eligibility on the makespan. Supplementary analysis was presented by adjusting different amounts of the budget for controlling the makespan and total expected costs. The proposed solution approach can provide proper alternatives for managers to make a trade-off in different various situations.

The problem of distributed assembly permutation flow-shop scheduling is traditionally studied considering identical factories. However, processing factories as an important element in the supply chain use different technology levels in the real world. The current paper is the first study that investigates that problem under non-identical factories condition. In addition, the impact of different technology levels is investigated in terms of operational costs, quality levels and processing times.

This research explores mitigating carbon emissions and integrating sustainability in e-commerce logistics by optimizing the multi-depot pollution routing problem with time windows (MDPRPTW). A proposed model contrasts non-collaborative and collaborative decision-making for order assignment among logistics service providers (LSPs), incorporating low-carbon considerations.

The model is substantiated using improved adaptive large neighborhood search (IALNS), tabu search (TS) and oriented ant colony algorithm (OACA) within the context of e-commerce logistics. For model validation, a normal distribution is employed to generate random demand and inputs, derived from the location and requirements files of LSPs.

This research validates the efficacy of e-commerce logistics optimization and IALNS, TS and OACA algorithms, especially when demand follows a normal distribution. It establishes that cooperation among LSPs can substantially reduce carbon emissions and costs, emphasizing the importance of integrating sustainability in e-commerce logistics optimization.

This paper proposes a meta-heuristic algorithm to solve the NP-hard problem. Methodologies such as reinforcement learning can be investigated in future work.

This research can help logistics managers understand the status of sustainable and cost-effective logistics operations and provide a basis for optimal decision-making.

This paper describes the complexity of the MDPRPTW model, which addresses both carbon emissions and cost reduction. Detailed information about the algorithm, methodology and computational studies is investigated. The research problem encompasses various practical aspects related to routing optimization in e-commerce logistics, aiming for sustainable development.

This paper aims to address a pollution-routing problem with one general period of congestion (PRP-1GPC), where the start and finish times of this period can be set freely.

In this paper, three sets of decision variables are optimized, namely, travel speeds before and after congestion and departure times on given routes, aiming to minimize total cost including green-house gas emissions, fuel consumption and driver wages. A two-phase algorithm is introduced to solve this problem. First, an adaptive large neighborhood search heuristic is used where new removal and insertion operators are developed. Second, an analysis of optimal speed before congestion is presented, and a tailored speed-and-departure-time optimization algorithm considering congestion is proposed by obtaining the best node to be served first over the congested period.

The results show that the newly developed operator of congested service-time insertion with noise is generally used more than other insertion operators. Besides, compared to the baseline methods, the proposed algorithm equipped with the new operators provides better solutions in a short time both in PRP-1GPC instances and time-dependent pollution-routing problem instances.

This paper considers a more general situation of the pollution-routing problem that allows drivers to depart before the congestion. The PRP-1GPC is better solved by the proposed algorithm, which adds operators specifically designed from the new perspective of the traveling distance, traveling time and service time during the congestion period.

The volumes of international containerized trade substantially increased over the past years. In the meantime, marine container terminal (MCT) operators are facing congestion issues at their terminals because of the increasing number of large-size vessels, the lack of innovative technologies and advanced handling equipment and the inability of proper scheduling of the available resources. This study aims to propose a novel memetic algorithm with a deterministic parameter control to facilitate the berth scheduling at MCTs and minimize the total vessel service cost.

A local search heuristic, which is based on the first-come-first-served policy, is applied at the chromosomes and population initialization stage within the developed memetic algorithm (MA). The deterministic parameter control strategy is implemented for a custom mutation operator, which alters the mutation rate values based on the piecewise function throughout the evolution of the algorithm. Performance of the proposed MA is compared with that of the alternative solution algorithms widely used in the berth scheduling literature, including a MA that does not apply the deterministic parameter control strategy, typical evolutionary algorithm, simulated annealing and variable neighborhood search.

Results demonstrate that the developed MA with a deterministic parameter control can obtain superior berth schedules in terms of the total vessel service cost within a reasonable computational time. Furthermore, greater cost savings are observed for the cases with high demand and low berthing capacity at the terminal. A comprehensive analysis of the convergence patterns indicates that introduction of the custom mutation operator with a deterministic control for the mutation rate value would provide more efficient exploration and exploitation of the search space.

This study does not account for uncertainty in vessel arrivals. Furthermore, potential changes in the vessel handling times owing to terminal disruptions are not captured.

The developed solution algorithm can serve as an efficient planning tool for MCT operators and assist with efficient berth scheduling for both discrete and continuous berthing layout cases.

The majority of studies on berth scheduling rely on the stochastic search algorithms without considering the specific problem properties and applying the guided search heuristics. Unlike canonical evolutionary algorithms, the developed algorithm uses a local search heuristic for the chromosomes and population initialization and adjusts the mutation rate values based on a deterministic parameter control strategy for more efficient exploration and exploitation of the search space.

This paper aims to investigate a multi-objective electric vehicle’s (EV’s) synergetic scheduling problem in the automotive industry, where a synergetic delivery mechanism to coordinate multiple EVs is proposed to fulfill part feeding tasks.

A chaotic reference-guided multi-objective evolutionary algorithm based on self-adaptive local search (CRMSL) is constructed to deal with the problem. The proposed CRMSL benefits from the combination of reference vectors guided evolutionary algorithm (RVEA) and chaotic search. A novel directional rank sorting procedure and a self-adaptive energy-efficient local search strategy are then incorporated into the framework of the CRMSL to obtain satisfactory computational performance.

The involvement of the chaotic search and self-adaptive energy-efficient local search strategy contributes to obtaining a stronger global and local search capability. The computational results demonstrate that the CRMSL achieves better performance than the other two well-known benchmark algorithms in terms of four performance metrics, which is inspiring for future researches on energy-efficient co-scheduling topics in manufacturing industries.

This research fully considers the cooperation and coordination of handling devices to reduce energy consumption, and an improved multi-objective evolutionary algorithm is creatively applied to solve the proposed engineering problem.

Marine transportation has been faced with an increasing demand for containerized cargo during the past decade. Marine container terminals (MCTs), as the facilities for connecting seaborne and inland transportation, are expected to handle the increasing amount of containers, delivered by vessels. Berth scheduling plays an important role for the total throughput of MCTs as well as the overall effectiveness of the MCT operations. This study aims to propose a novel island-based metaheuristic algorithm to solve the berth scheduling problem and minimize the total cost of serving the arriving vessels at the MCT.

A universal island-based metaheuristic algorithm (UIMA) was proposed in this study, aiming to solve the spatially constrained berth scheduling problem. The UIMA population was divided into four sub-populations (i.e. islands). Unlike the canonical island-based algorithms that execute the same metaheuristic on each island, four different population-based metaheuristics are adopted within the developed algorithm to search the islands, including the following: evolutionary algorithm (EA), particle swarm optimization (PSO), estimation of distribution algorithm (EDA) and differential evolution (DE). The adopted population-based metaheuristic algorithms rely on different operators, which facilitate the search process for superior solutions on the UIMA islands.

The conducted numerical experiments demonstrated that the developed UIMA algorithm returned near-optimal solutions for the small-size problem instances. As for the large-size problem instances, UIMA was found to be superior to the EA, PSO, EDA and DE algorithms, which were executed in isolation, in terms of the obtained objective function values at termination. Furthermore, the developed UIMA algorithm outperformed various single-solution-based metaheuristic algorithms (including variable neighborhood search, tabu search and simulated annealing) in terms of the solution quality. The maximum UIMA computational time did not exceed 306 s.

Some of the previous berth scheduling studies modeled uncertain vessel arrival times and/or handling times, while this study assumed the vessel arrival and handling times to be deterministic.

The developed UIMA algorithm can be used by the MCT operators as an efficient decision support tool and assist with a cost-effective design of berth schedules within an acceptable computational time.

A novel island-based metaheuristic algorithm is designed to solve the spatially constrained berth scheduling problem. The proposed island-based algorithm adopts several types of metaheuristic algorithms to cover different areas of the search space. The considered metaheuristic algorithms rely on different operators. Such feature is expected to facilitate the search process for superior solutions.

In the modern era of e-grocery, attended home delivery (AHD) has been identified as a crucial part of the last-mile delivery problem. This paper aims to deal with a real-life last-mile-delivery problem in the context of the Indian public distribution system (PDS). The authors identified two different environments for the said AHD problem and proposed two different approaches to address the issue under these problem settings.

In this study, the authors first consider the problem in a static environment and propose an iterated local search (ILS) integrated with an adaptive large neighborhood search (ALNS) meta-heuristic algorithm to obtain a routing solution. Thereafter, they extend the study in a dynamic environment where new delivery requests occur dynamically and propose a heuristic algorithm to solve the problem. For the dynamic case, multiple scenarios for the occurrence of delivery requests are considered to determine decisions regarding the opportunity to include a new request into the current solution.

By computational experiments, the authors show that the proposed approach performs significantly well for large size problem instances. They demonstrate the differences and advantages of the dynamic problem setting through a set of different scenarios. Also, they present a comparative analysis to show the benefits of adopting the algorithm in dynamic routing scenarios.

Future research may extend the scope of this study by incorporating stochastic delivery failure probabilities and customer behavior affecting the delivery response. Also, the present study does not take inventory policies at the depot into consideration. It will be of interest to see how the system performs under the uncertainty of supply from the depot. Despite the limitations, the authors believe that this study provides food for thought and encouragements for practitioners.

This study shows the benefits of adopting an AHD problem in a dynamic setting in terms of customer service as compared to a traditional static environment. The authors clearly demonstrate the differences and advantages of the dynamic problem setting through a set of different scenario analysis.

This paper investigates a real-life AHD problem faced by the Department of Food, Supply and Consumer Affairs, India. The findings of this study will be of particular interest to the policy-makers to build a more robust PDS in India.

The study is unique and highly relevant for real-world applications and can help build a more robust AHD system. Also, the proposed solution approaches to aid the problem in both static and dynamic routing scenarios will be of particular interest to practitioners.

The purpose of this paper is to provide an effective solution method for the truck and trailer routing problem (TTRP) which is one of the important NP-hard combinatorial optimization problems owing to its multiple real-world applications. It is a generalization of the famous vehicle routing problem (VRP), involving a group of geographically scattered customers served by the vehicle fleet including trucks and trailers.

The meta-heuristic solution approach based on bat algorithm (BA) in which a local search procedure performed by five different neighborhood structures is developed. Moreover, a self-adaptive (SA) tuning strategy to preserve the swarm diversity is implemented. The effectiveness of the proposed SA-BA is investigated by an experiment conducted on 21 benchmark problems that are well known in the literature.

Computational results indicate that the proposed SA-BA algorithm is computationally efficient through comparison with other existing algorithms found from the literature according to solution quality. As for the actual computational time, the SA-BA algorithm outperforms others. However, the scaled computational time of the SA-BA algorithm underperforms the other algorithms.

In this work the authors show that the proposed SA-BA is effective as a method for the TTRP problem. To the authors’ knowledge, the BA has not been applied previously, as in this work, to solve the TTRP problem.

This paper aims to investigate the part feeding scheduling problem with electric vehicles (EVs) for automotive assembly lines. A point-to-point part feeding model has been formulated to minimize the number of EVs and the maximum handling time by specifying the EVs and sequence of all the delivery tasks.

First, a mathematical programming model of point-to-point part feeding scheduling problem (PTPPFSP) with EVs is presented. Because the PTPPFSP is NP-hard, an improved multi-objective cuckoo search (IMCS) algorithm is developed with novel search strategies, possessing the self-adaptive Levy flights, the Gaussian mutation and elite selection strategy to strengthen the algorithm’s optimization performance. In addition, two local search operators are designed for deep optimization. The effectiveness of the IMCS algorithm is verified by dealing with the PTPPFSP in different problem scales.

Numerical experiments are used to demonstrate how the IMCS algorithm serves as an efficient method to solve the PTPPFSP with EVs. The effectiveness and feasibility of the IMCS algorithm are validated by approximate Pareto fronts obtained from the instances of different problem scales. The computational results show that the IMCS algorithm can achieve better performance than the other high-performing algorithms in terms of solution quality, convergence and diversity.

This study is applicable without regard to the breakdown of EVs. The current research contributes to the scheduling of in-plant logistics for automotive assembly lines, and it could be modified to cope with similar part feeding scheduling problems characterized by just-in-time (JIT) delivery.

Both limited electricity capacity and no earliness and tardiness constraints are considered, and the scheduling problem is solved satisfactorily and innovatively for an efficient JIT part feeding with EVs applied to in-plant logistics.