The Capacitated Location-Allocation Problem in the Presence of <i>k</i>Connections

We consider a capacitated location-allocation problem in the presence of k connections on the horizontal line barrier. The objective is to locate a set of new facilities among a set of existing facilities and to allocate an optimal number of existing facilities to each new facility in order to satisfy their demands such that the summation of the weighted rectilinear barrier distances from new facilities to existing facilities is minimized. The proposed problem is designed as a mixed-integer nonlinear programming model. To show the efficiency of the model, a numerical example is provided. It is worth noting that the global optimal solution is obtained.

Improved Adaptive Differential Evolution Algorithm for the Un-Capacitated Facility Location Problem

The differential evolution algorithm is an evolutionary algorithm for global optimization and the un-capacitated facility location problem (UFL) is one of the classic NP-Hard problems. In this paper, combined with the specific characteristics of the UFL problem, we introduce the activation function to the algorithm for solving UFL problem and name it improved adaptive differential evolution algorithm (IADEA). Next, to improve the efficiency of the algorithm and to alleviate the problem of being stuck in a local optimum, an adaptive operator was added. To test the improvement of our algorithm, we compare the IADEA with the basic differential evolution algorithm by solving typical instances of UFL problem respectively. Moreover, to compare with other heuristic algorithm, we use the hybrid ant colony algorithm to solve the same instances. The computational results show that IADEA improves the performance of the basic DE and it outperforms the hybrid ant colony algorithm.

A Memetic Algorithm With Competition for the Capacitated Green Vehicle Routing Problem

In this paper, a memetic algorithm with competition(MAC) is proposed to solve the capacitated green vehicle routing problem(CGVRP). Firstly, the permutation array called traveling salesman problem(TSP) route is used to encode the solution, and an effective decoding method to construct the CGVRP route is presented accordingly. Secondly, the k-nearest neighbor(k NN) based initialization is presented to take use of the location information of the customers. Thirdly, according to the characteristics of the CGVRP, the search operators in the variable neighborhood search(VNS) framework and the simulated annealing(SA) strategy are executed on the TSP route for all solutions. Moreover, the customer adjustment operator and the alternative fuel station(AFS) adjustment operator on the CGVRP route are executed for the elite solutions after competition. In addition, the crossover operator is employed to share information among different solutions. The effect of parameter setting is investigated using the Taguchi method of design-ofexperiment to suggest suitable values. Via numerical tests, it demonstrates the effectiveness of both the competitive search and the decoding method. Moreover, extensive comparative results show that the proposed algorithm is more effective and efficient than the existing methods in solving the CGVRP.

Hybrid discrete particle swarm optimization algorithm for capacitated vehicle routing problem

Capacitated vehicle routing problem (CVRP) is an NP-hard problem. For large-scale problems, it is quite difficult to achieve an optimal solution with traditional optimization methods due to the high computational complexity. A new hybrid ap- proximation algorithm is developed in this work to solve the problem. In the hybrid algorithm, discrete particle swarm optimiza- tion (DPSO) combines global search and local search to search for the optimal results and simulated annealing (SA) uses certain probability to avoid being trapped in a local optimum. The computational study showed that the proposed algorithm is a feasible and effective approach for capacitated vehicle routing problem, especially for large scale problems.

An Effective Hybrid Optimization Algorithm for Capacitated Vehicle Routing Problem

Capacitated vehicle routing problem (CVRP) is an important combinatorial optimization problem. However, it is quite difficult to achieve an optimal solution with the traditional optimization methods owing to the high computational complexity. A hybrid algorithm was developed to solve the problem, in which an artificial immune clonal algorithm (AICA) makes use of the global search ability to search the optimal results and simulated annealing (SA) algorithm employs certain probability to avoid becoming trapped in a local optimum. The results obtained from the computational study show that the proposed algorithm is a feasible and effective method for capacitated vehicle routing problem.

Computationally Efficient Problem Reformulations for Capacitated Lot Sizing Problem

In this article, we propose novel reformulations for capacitated lot sizing problem. These reformulations are the result of reducing the number of variables (by eliminating the backorder variable) or increasing the number of constraints (time capacity constraints) in the standard problem formulation. These reformulations are expected to reduce the computational time complexity of the problem. Their computational efficiency is evaluated later in this article through numerical analysis on randomly generated problems.

Vertical Decomposition Approach to Solve Single Stage Capacitated Warehouse Location Problem (SSCWLP)

Single Stage Capacitated Warehouse Location Problem (SSCWLP) has been attempted by few researchers in the past. These are Geoffrion and Graves [1], Sharma [2], Sharma [3] and Sharma and Berry [4]. In this paper we give a “vertical decomposition” approach to solve SSCWLP that uses Lagrangian relaxation. This way SSCWLP is broken into two versions of capacitated plant location problem (the CPLP_L and CPLP_R) by relaxing the flow balance constraints. For CPLP_R, we use well known Lagrangian relaxations given in literature (Christofides and Beasley [5] and Nauss [6]);and adopt them suitably for solving CPLP_L. We show theoretically in this paper that SSCWLP can be more efficiently solved by techniques of vertical decomposition developed in this paper than the method available in literature (Sharma and Berry [4]). Encouraging computational study is reported in this paper.

Combining Geographic Information Systems for Transportation and Mixed Integer Linear Programming in Facility Location-Allocation Problems

In this study, we aimed to assess the solution quality for location-allocation problems from facilities generated by the software TransCAD&reg;?, a Geographic Information System for Transportation (GIS-T). Such facilities were obtained after using two routines together: Facility Location and Transportation Problem, when compared with optimal solutions from exact mathematical models, based on Mixed Integer Linear Programming (MILP), developed externally for the GIS. The models were applied to three simulations: the first one proposes opening factories and customer allocation in the state of Sao Paulo, Brazil;the second involves a wholesaler and a study of location and allocation of distribution centres for retail customers;and the third one involves the location of day-care centers and allocation of demand (0 - 3 years old children). The results showed that when considering facility capacity, the MILP optimising model presents results up to 37% better than the GIS and proposes different locations to open new facilities.

Efficient Network Selection Using Multi-Depot Routing Problem for Smart Cities

Smart cities make use of a variety of smart technology to improve societies in better ways.Such intelligent technologies,on the other hand,pose sig-nificant concerns in terms of power usage and emission of carbons.The suggested study is focused on technological networks for big data-driven systems.With the support of software-defined technologies,a transportation-aided multicast routing system is suggested.By using public transportation as another communication platform in a smart city,network communication is enhanced.The primary objec-tive is to use as little energy as possible while delivering as much data as possible.The Attribute Decision Making with Capacitated Vehicle(CV)Routing Problem(RP)and Half Open Multi-Depot Heterogeneous Vehicle Routing Problem is used in the proposed research.For the optimum network selection,a Multi-Attribute Decision Making(MADM)method is utilized.For the sake of reducing energy usage,the Capacitated Vehicle Routing Problem(CVRP)is employed.To reduce the transportation cost and risk,Half Open Multi-Depot Heterogeneous Vehicle Routing Problem is used.Moreover,a mixed-integer programming approach is used to deal with the problem.To produce Pareto optimal solutions,an intelligent algorithm based on the epsilon constraint approach and genetic algorithm is cre-ated.A scenario of Auckland Transport is being used to validate the concept of offloading the information onto the buses for energy-efficient and delay-tolerant data transfer.Therefore the experiments have demonstrated that the buses may be used effectively to carry out the data by customer requests while using 30%of less energy than the other systems.

基于离散哈里斯鹰算法求解车辆路径问题

针对带容量约束车辆路径问题,提出一种离散哈里斯鹰算法。在哈里斯鹰算法的基础上,根据车辆路径的编解码特点,重新定义算法在全局搜索和局部开发阶段的更新策略;在全局搜索阶段利用随机插入和反转策略更新哈里斯鹰个体的位置,提高算法的全局开发能力;在局部开发阶段利用转移算子和移除算子设计哈里斯鹰个体的更新机制,提高算法的局部精细化搜索能力;通过改进逃逸能量平衡全局搜索和局部开发能力。实验结果表明,重定义的更新策略均能有效提升算法效率,将该算法和其它启发式算法的结果相比较,所提算法在求解精度和稳定性方面更具优势。

测量原理-数据-领域知识融合ECT重建方法

低质量的图像制约了电容层析成像在多相流参数测量中的应用。针对该问题,引入了由深度卷积神经网络预测的数据驱动先验,提出了融合测量原理、数据驱动先验和稀疏先验的成像模型;建立了新的算法实现成像模型的高效求解。评估结果证实,与其他的成像算法相比,新算法在细节重建、伪影去除和鲁棒性等方面具有显著优势。

Implementing Lagrangean Decomposition Technique to Acquire an Adequate Lower Boundon the Facility Location Problem Solution

In this work, the Lagrangean Relaxation method has been discussed to solve different sizes of capacitated facility location problem (CFLP). A good lower bound has been achieved on the solution of the CFLP considered in this paper. This lower bound has been improved by using the Volume algorithm. The methods of setting two important parameters in heuristic have been given. The approaches used to gain the lower bound have been explained. The results of this work have been compared with the known results given by Beasley.

自适应混合蚁群算法求解带容量约束车辆路径问题

针对带容量约束车辆路径问题(capacitated vehicle routing problem,CVRP),提出了一种自适应混合蚁群算法.由蚁群算法生成子回路,为增强跳出局部最优能力,在蚁群算法的状态转移规则和信息素更新规则中引入了自适应机制.基于子回路组合,由遗传算法构造近似解,根据问题编码特性设计了适应度函数和遗传算子,提高了构造效率,并采用Clark和Wright节约算法将近似解修复成可行解.采用扫描法和2-opt局部优化方法提高可行解的质量.标准算例的实验结果表明,该算法在求解CVRP问题上具有良好的寻优精度和寻优效率.灵敏度分析结果表明蚂蚁数量对算法性能具有显著影响.

三阶段优化算法求解带三维装载约束的MDVRP

对带三维装载约束的多车场车辆路径问题,以最小化车辆行驶总里程为优化目标,建立问题模型,并提出一种三阶段优化算法进行求解。第一阶段设计带循环平衡的K-medoids聚类算法,将原问题分解成多个带三维装载约束限制的车辆路径子问题。第二阶段提出一种双层结构的超启发式蚁群算法用于求解各子问题,以确定各车辆的配送路径。在该算法中,低层设计9种启发式操作,并将其所构成的排列作为高层个体;同时,高层采用蚁群算法更新高层个体,以引导算法搜索方向。第三阶段以第二阶段所得阶段解作为初始解,设计组合启发式装箱算法对带容积约束的装箱过程进行优化,进而将第二、三阶段确定的解合并为原问题的解。最后,仿真实验和算法比较验证了所提算法的有效性。

一种求解CVRP的动态图转换模型

带容量的车辆路径问题是组合最优化问题中的经典问题,多年以来一直被反复研究。最近,Transformer已经成为解决车辆路径问题的主流深度学习架构。然而,由于一个实例在模型不同构造步骤中会发生改变,相应的节点特征也需要更新,传统位置编码方法不适用于提取动态优化问题的位置信息。因此,现有方法在提高学习效率方面效果较差。以最小化路径长度为目标,提出一种动态图转换模型(DGTM)和动态位置编码(DPE)方法,并使用一种双重损失REINFORCE算法训练DGTM模型。此外,强化学习、图神经网络和Transformer架构相结合,提高了模型的训练效率,增强了神经网络对带约束路径问题信息的表征能力。实验结果表明,DGTM模型在此问题上的优化效果超越了目前基于深度强化学习的方法和部分传统算法,整体性能优于专业求解器的,且具有较好的泛化性能,为求解图上组合最优化问题提供了一种有效方法。

求解带容量约束车辆路径问题的多模态差分进化算法

针对带容量约束车辆路径问题(CVRP)中交通拥堵、资源供给、客户需求等不确定性因素的影响容易导致单一最优解不可行或非最优的问题,提出一种多模态差分进化(MDE)算法,以同时求解得到目标值相近的多个备选车辆路径方案。首先结合CVRP的特点,构建高效的解个体编解码策略,并基于修复机制提升解个体的质量;然后在差分进化(DE)算法框架下,基于多模态优化视角引入动态半径小生境生成方法,并采用杰卡德系数来度量解个体之间相似性,进而实现对于解个体之间距离的计算;最后,改进邻域搜索策略,采用精英存档和更新策略来得到多模态最优解集。基于典型数据集的仿真实验与分析结果表明,所提MDE算法寻优得到的平均最优解个数达到1.7434个,平均最优解与已知最优解的平均偏差为0.03%,而差分进化(DE)算法二者分别为0.8486和0.63%。可见,所提算法在求解CVRP上表现出较高的有效性和稳定性,能同时得到CVRP的多个近似最优解。

数字经销平台统采共配双层拍卖机制设计

针对当前都市圈经销商因“孤立式发展、分散化建网”而导致无法满足碎片化订单、多渠道履约及高频高效配送要求等痛点,提出了一种数字经销平台统采共配双层拍卖机制。在上层机制中,考虑一家数字经销平台(卖者)与多家经销商(买者),以社会福利最大化为目标,构建了单边组合Vickery-Clarke-Groves(O-VCG)拍卖机制,实现了多物品多单元环境下的供需匹配。在下层机制中,考虑一家经销商(卖者)与多家承运商(买者),基于O-VCG拍卖机制的思想,实现了从城市集拼仓到门店、从门店到客户的两级城配运输服务采购。特别地,下层机制采用多轮O-VCG竞拍以满足多家经销商的运输需求。所提出的O-VCG拍卖机制可以实现激励相容、个体理性和配置效率。经销商构建基于需求预测及控制合理库存的上层拍卖投标策略。构建两级基于车容的城配车辆路径问题(Two-Echelon Capacity-Based Vehicle Routing Problem,2E-CVRP)近似优化算法,用于求解下层拍卖机制中基于库存限制的竞价生成问题(Bid Generation Problem,BGP)。针对双层拍卖中的胜者确定问题(Winner Determination Problem,WDP),提出有效的WDP算法。最后,基于全球最大的医药流通集团的真实数据进行数值仿真实验,结果表明:数字经销平台统采共配的双层拍卖机制可以高效分配货权及运单,合理确定批发价及城配运价,提高社会总效益,降低两级城配运输成本。

基于改进遗传算法求解容量约束车辆路径问题

为克服传统遗传算法在求解容量约束路径问题时易收敛和搜索能力不足的缺点,提出了动态调参的方式对算法进行改进。首先采用局部搜索算法生成初始解,提高初始解的质量,并动态调整选择、交叉、变异操作的参数,既保留了种群多样性,又避免了优秀个体被破坏,最后通过变邻域搜索算法提高算法搜索能力。实验表明,所有算例实例求得的最优解误差不超1.0%,并与其他经典的启发式算法进行了比较。

改进混合萤火虫算法求解CVRP

提出一种改进混合萤火虫算法(KM-HFA)来解决带容量约束的车辆路径问题。该算法利用K-Means聚类方法将客户集先进行分类,再构建初始解,以较好的初始解开始萤火虫算法的寻优过程,减少了算法的计算量。在萤火虫算法中引入部分匹配交叉算子,2H-opt交换算子,局部搜索算子和变异算子,这些方法加快了算法的收敛速度,提高了萤火虫算法跳出局部最优的能力。选取小规模及中规模数据集进行仿真实验,共94组标准算例。对于79组实例,KM-HFA得到的解优于对照的混合萤火虫算法和CC-CVRP所得的求解方案,KM-HFA所求方案的车辆行驶总距离更小。KM-HFA计算了5组小规模实例,即A-n33-k6,A-n37-k6,P-n16-k8,P-n19-k2和P-n20-k2,在不增加车辆配送路径数目的情况下,得到比经典解更好的配送方案。对于实例P-n22-k8和P-n23-k8,文中算法在比经典解路径数增加了一条的前提下,找到了车辆行驶总距离更小的解。仿真实验结果表明KM-HFA具有较好的稳定性和有效性。

A hybrid particle swarm optimization algorithm for the capacitated location routing problem

Purpose–The purpose of this paper is to solve the capacitated location routing problem(CLRP),which is an NP-hard problem that involves making strategic decisions as well as tactical and operational decisions,using a hybrid particle swarm optimization(PSO)algorithm.Design/methodology/approach–PSO,which is a population-based metaheuristic,is combined with a variable neighborhood strategy variable neighborhood search to solve the CLRP.Findings–The algorithm is tested on a set of instances available in the literature and gave good quality solutions,results are compared to those obtained by other metaheuristic,evolutionary and PSO algorithms.Originality/value–Local search is a time consuming phase in hybrid PSO algorithms,a set of neighborhood structures suitable for the solution representation used in the PSO algorithm is proposed in the VNS phase,moves are applied directly to particles,a clear decoding method is adopted to evaluate a particle(solution)and there is no need to re-encode solutions in the form of particles after applying local search.