Memetic Algorithms for Parallel Code Optimization

Discovering the optimum number of processors and the distribution of data on distributed memory parallel computers for a given algorithm is a demanding task. A memetic algorithm (MA) is proposed here to find the best number of processors and the best data distribution method to be used for each stage of a parallel program. Steady state memetic algorithm is compared with transgenerational memetic algorithm using different crossover operators and hill-climbing methods. A self-adaptive MA is also implemented, based on a multimeme strategy. All the experiments are carried out on computationally intensive, communication intensive, and mixed problem instances. The MA performs successfully for the illustrative problem instances.     

A memetic algorithm-based heuristic for a scheduling problem in printed circuit board assembly

This research develops a memetic algorithm to solve Printed Circuit Board (PCB) scheduling with sequence-dependent setup times on a single machine with constrained feeder capacity. The objective of the scheduling problem is to minimize the total weighted tardiness. A memetic algorithm-based heuristics is developed by integrating a genetic algorithm, Minimum Slack Time (MST) scheduling rule, “Keep Tool Needed Soonest” (KTNS) policy, and a local search procedure. Application of the MA results in two outcome plans: a scheduling plan and a feeder setup plan.Numerical experiments show that compared to a number of commonly used dispatching rules, the memetic algorithm provides better solutions in term of minimum total weighted tardiness. Even the computation is the highest, it still practical. Calibration of MA parameter values is also explored in this study.     

A memetic algorithm for the re-entrant permutation flowshop scheduling problem to minimize the makespan

A common assumption in the classical permutation flowshop scheduling model is that each job is processed on each machine at most once. However, this assumption does not hold for a re-entrant flowshop in which a job may be operated by one or more machines many times. Given that the re-entrant permutation flowshop scheduling problem to minimize the makespan is very complex, we adopt the CPLEX solver and develop a memetic algorithm (MA) to tackle the problem. We conduct computational experiments to test the effectiveness of the proposed algorithm and compare it with two existing heuristics. The results show that CPLEX can solve mid-size problem instances in a reasonable computing time, and the proposed MA is effective in treating the problem and outperforms the two existing heuristics.     

Flow shop scheduling with blocking using modified harmony search algorithm with neighboring heuristics methods

The flow shop scheduling with blocking is considered an important scheduling problem which has many real-world applications. This paper proposes a new algorithm which applies heuristic techniques in harmony search algorithm (HSA) to minimize the total flow time. The proposed method is called modified harmony search algorithm with neighboring heuristics methods (MHSNH). To improve the initial harmony memory, we apply two heuristic techniques: nearest neighbor (NN) and constructive modified NEH (MNEH). A modified version of harmony search algorithm evolves to explore and generates a new solution. The newly generated solution is then enhanced by using neighboring heuristics. Lastly, another neighboring heuristic is applied to improve the obtained solution. The proposed algorithm is evaluated using 12 real-world problem instances each with 10 samples. The experimental evaluation is accomplished using two factors: CPU computational time and the number of iterations. For the first factor, comparative evaluation against six well-established methods shows that the proposed method achieves almost the best overall results in six problem instances out of the twelve and yields fruitful results for others. For the second factor, comparative evaluation against twelve well-regarded methods shows that the proposed method achieves the best overall results in three problem instances and obtains very good results in other instances. In a nutshell, the proposed MHSNH is an effective strategy for solving the job shop scheduling problem.     

Multiscale production routing in multicommodity supply chains with complex production facilities

In this work, we introduce the multiscale production routing problem (MPRP), which considers the coordination of production, inventory, distribution, and routing decisions in multicommodity supply chains with complex continuous production facilities. We propose an MILP model involving two different time grids. While a detailed mode-based production scheduling model captures all critical operational constraints on the fine time grid, vehicle routing is considered in each time period of the coarse time grid. In order to solve large instances of the MPRP, we propose an iterative MILP-based heuristic approach that solves the MILP model with a restricted set of candidate routes at each iteration and dynamically updates the set of candidate routes for the next iteration. The results of an extensive computational study show that the proposed algorithm finds high-quality solutions in reasonable computation times, and in large instances, it significantly outperforms a standard two-phase heuristic approach and a solution strategy involving a one-time heuristic pre-generation of candidate routes. Similar results are achieved in an industrial case study, which considers a real-world industrial gas supply chain.     

A memetic algorithm for the multi-compartment vehicle routing problem with stochastic demands

The multi-compartment vehicle routing problem (MC-VRP) consists of designing transportation routes to satisfy the demands of a set of customers for several products that, because of incompatibility constraints, must be loaded in independent vehicle compartments. Despite its wide practical applicability the MC-VRP has not received much attention in the literature, and the few existing methods assume perfect knowledge of the customer demands, regardless of their stochastic nature. This paper extends the MC-VRP by introducing uncertainty on what it is known as the MC-VRP with stochastic demands (MC-VRPSD). The MC-VRPSD is modeled as a stochastic program with recourse and solved by means of a memetic algorithm. The proposed memetic algorithm couples genetic operators and local search procedures proven to be effective on deterministic routing problems with a novel individual evaluation and reparation strategy that accounts for the stochastic nature of the problem. The algorithm was tested on instances of up to 484 customers, and its results were compared to those obtained by a savings-based heuristic and a memetic algorithm (MA/SCS) for the MC-VRP that uses a spare capacity strategy to handle demand fluctuations. In addition to effectively solve the MC-VRPSD, the proposed MA/SCS also improved 14 best known solutions in a 40-problem testbed for the MC-VRP.     

A transgenetic algorithm applied to the Traveling Car Renter Problem

The Traveling Car Renter is a new problem and constitutes a generalization of the Traveling Salesman. Several applications arise from it, mainly in the scheduling optimization of rental cars and in other problems concerning transport systems. In this paper, an integer quadratic programming model is presented for the Traveling Car Renter. It is linearized and implemented on a solver providing optimal solutions to a set of eighteen small instances. Large instances are tackled with a transgenetic algorithm proposed here. A computational experiment is reported on sixty instances and the proposed algorithm is compared to a memetic algorithm presented previously. The computational experiment aimed at focusing on the differences of performance between the two heuristic algorithms due to the search strategy used by each of them. Therefore, the implementation of both methods shared several elements. The results show that the transgenetic algorithm presents the best performance, indicating that its cooperative evolutionary process was more effective on the investigated problem than the competitive scheme of the memetic algorithm.     

An efficient memetic algorithm for the uncapacitated single allocation hub location problem

In this paper, we present a memetic algorithm (MA) for solving the uncapacitated single allocation hub location problem (USAHLP). Two efficient local search heuristics are designed and implemented in the frame of an evolutionary algorithm in order to improve both the location and allocation part of the problem. Computational experiments, conducted on standard CAB/AP hub data sets (Beasley in J Global Optim 8:429–433, 1996) and modified AP data set with reduced fixed costs (Silva and Cunha in Computer Oper Res 36:3152–3165, 2009), show that the MA approach is superior over existing heuristic approaches for the USAHLP. For several large-scale AP instances up to 200 nodes, the MA improved the best-known solutions from the literature until now. Numerical results on instances with 300 and 400 nodes introduced in Silva and Cunha (Computer Oper Res 36:3152–3165, 2009) show significant improvements in the sense of both solution quality and CPU time. The robustness of the MA was additionally tested on a challenging set of newly generated large-scale instances with 520–900 nodes. To the best of our knowledge, these are the largest USAHLP problem dimensions solved in the literature until now. In addition, in this paper, we report for the first time optimal solutions for 30 AP and modified AP instances.     

A hybrid metaheuristic case-based reasoning system for nurse rostering

In this paper we present a novel Case-Based Reasoning (CBR) system called CABAROST (CAsed-BAsed ROSTering) which was developed for personnel scheduling problems. CBR is used to capture and store examples of personnel manager behaviour which are then used to solve future problems. Previous examples of constraint violations in schedules and the repairs that were used to solve the violations are stored as cases. The sequence in which violations are repaired can have a great impact on schedule quality. A novel memetic algorithm is proposed which evolves good quality sequences of repairs generated by CABAROST. The algorithm was tested on instances of the real-world nurse rostering problem at the Queens Medical Centre NHS Trust in Nottingham.     

启发式任务调度中的处理器选择策略

任务调度是并行分布计算中最为基本、最为关键,也最具有挑战性的问题之一,是影响并行分布计算执行效率的一个关键因素.现有的基于任务静态优先级的启发式任务调度方法都是以“当前任务具有最早起始执行时刻”为目标来选择执行处理器.该文在详细分析讨论该种调度方法的基础上,指出了以该目标选择处理器存在的问题及缺点,并提出了以“当前任务的直接后继具有最早起始执行时刻”为目标选择处理器的方法,并给出了相应的约束条件.     

Parallel-identical-machine job-shop scheduling with different stage-dependent buffering requirements

The neglect of buffering requirements in a classical job shop scheduling system often results in inapplicability in many complex real-world applications. To overcome this inapplicability, a new and more generalised scheduling problem is proposed under different stage-dependent buffering requirements and parallel use of identical-function machine units at each processing stage in job shop environments. The problem is formulated as a mixed integer programming model that can be exactly solved by ILOG-CPEX for small-size instances. Moreover, a hybrid metaheuristic algorithm embedded with a state-of-the-art constructive algorithm is developed. The computational experiment shows that the proposed metaheuristic can efficiently solve large-size instances. The result analysis indicates that the proposed approach can provide better configuration of real-world scheduling systems. The proposed DBPMJSS methodology has a potential to analyse, model and solve many industrial systems with the requirements of buffering conditions, particularly for manufacturing, railway, healthcare and mining industries.     

Scheduling jobs with ready times and precedence constraints on parallel batch machines using metaheuristics

In this paper, we discuss a scheduling problem for parallel batch machines where the jobs have ready times. Problems of this type can be found in semiconductor wafer fabrication facilities (wafer fabs). In addition, we consider precedence constraints among the jobs. Such constraints arise, for example, in scheduling subproblems of the shifting bottleneck heuristic when complex job shop scheduling problems are tackled. We use the total weighted tardiness as the performance measure to be optimized. Hence, the problem is NP-hard and we have to rely on heuristic solution approaches. We consider a variable neighborhood search (VNS) scheme and a greedy randomized adaptive search procedure (GRASP) to compute efficient solutions. We assess the performance of the two metaheuristics based on a large set of randomly generated problem instances and based on instances from the literature. The obtained computational results demonstrate that VNS is a very fast heuristic that quickly leads to high-quality solutions, whereas the GRASP is slightly outperformed by the VNS approach. However, the GRASP approach has the advantage that it can be parallelized in a more natural manner compared to VNS.     

Memetic algorithms for the job shop scheduling problem with operators

The job-shop scheduling problem with operators (JSO) is an extension of the classic job-shop problem in which an operation must be assisted by one of a limited set of human operators, so it models many real life situations. In this paper we tackle the JSO by means of memetic algorithms with the objective of minimizing the makespan. We define and analyze a neighborhood structure which is then exploited in local search and tabu search algorithms. These algorithms are combined with a conventional genetic algorithm to improve a fraction of the chromosomes in each generation. We also consider two different schedule builders for chromosome decoding. All these elements are combined to obtain memetic algorithms which are evaluated over an extensive set of instances. The results of the experimental study show that they reach high quality solutions in very short time, comparing favorably with the state-of-the-art methods.     

An integrated search heuristic for large-scale flexible job shop scheduling problems

The flexible job shop scheduling problem (FJSP) is a generalization of the classical job shop scheduling problem (JSP), where each operation is allowed to be processed by any machine from a given set, rather than one specified machine. In this paper, two algorithm modules, namely hybrid harmony search (HHS) and large neighborhood search (LNS), are developed for the FJSP with makespan criterion. The HHS is an evolutionary-based algorithm with the memetic paradigm, while the LNS is typical of constraint-based approaches. To form a stronger search mechanism, an integrated search heuristic, denoted as HHS/LNS, is proposed for the FJSP based on the two algorithms, which starts with the HHS, and then the solution is further improved by the LNS. Computational simulations and comparisons demonstrate that the proposed HHS/LNS shows competitive performance with state-of-the-art algorithms on large-scale FJSP problems, and some new upper bounds among the unsolved benchmark instances have even been found.     

Improved bounds for hybrid flow shop scheduling with multiprocessor tasks

In this paper, we investigate the problem of minimizing makespan in a multistage hybrid flow-shop scheduling with multiprocessor tasks. To generate high-quality approximate solutions to this challenging NP-hard problem, we propose a discrepancy search heuristic that is based on the new concept of adjacent discrepancies. Moreover, we describe a new lower bound based on the concept of dual feasible functions. The proposed lower and upper bounds are assessed through computational experiments conducted on 300 benchmark instances with up to 100 jobs and 8 stages. For these instances, we provide evidence that the proposed bounds consistently outperform the best existing ones. In particular, the proposed heuristic successfully improved the best known solution of 75 benchmark instances.     

Multiobjective memetic algorithms for time and space assembly line balancing

This paper presents three proposals of multiobjective memetic algorithms to solve a more realistic extension of a classical industrial problem: time and space assembly line balancing. These three proposals are, respectively, based on evolutionary computation, ant colony optimisation, and greedy randomised search procedure. Different variants of these memetic algorithms have been developed and compared in order to determine the most suitable intensification–diversification trade-off for the memetic search process. Once a preliminary study on nine well-known problem instances is accomplished with a very good performance, the proposed memetic algorithms are applied considering real-world data from a Nissan plant in Barcelona (Spain). Outstanding approximations to the pseudo-optimal non-dominated solution set were achieved for this industrial case study.     

A particle swarm optimization and min–max-based workflow scheduling algorithm with QoS satisfaction for service-oriented grids

In service-orientated grids (SOG) environments, grid workflow schedulers play a critical role in providing quality-of-service (QoS) satisfaction for various end users (EUs) with diverse QoS objectives and optimization requirements. The EU requirements are not only many and conflicting, but also involve constraints of various degrees—loose, moderate or tight. However, most of the existing scheduling approaches violate EU constraints in tight situations and suffer inferior QoS optimization results. In this paper, a constraints-aware multi-QoS workflow scheduling strategy is proposed based on particle swarm optimization (PSO) and a proposed look-ahead heuristic (LAPSO) to improve performance in such situations. The algorithm selects the best scheduling solutions based on the proposed constraint-handling strategy. It hybridises PSO with a novel look-ahead mechanism based on a min–max heuristic, which deterministically improves the quality of the best solutions. Extensive simulation experiments have been carried out to evaluate the performance of the proposed approach. The simulation results show that the LAPSO algorithm guarantees satisfaction (0% violation) of the EU constraints even in tight situations. It also outperforms the comparison algorithm, with about 30% increase, in terms of cumulative QoS satisfaction of optimization requirements. In addition, the new scheme significantly reduces the CPU time by about 75% compared to the benchmark algorithm.     

Order acceptance and scheduling to maximize total net revenue in permutation flowshops with weighted tardiness

The order acceptance and scheduling (OAS) problem is important in make-to-order production systems in which production capacity is limited and order delivery requirements are applied. This study proposes a multi-initiator simulated annealing (MSA) algorithm to maximize the total net revenue for the permutation flowshop scheduling problem with order acceptance and weighted tardiness. To evaluate the performance of the proposed MSA algorithm, computational experiments are performed and compared for a benchmark problem set of test instances with up to 500 orders. Experimental results reveal that the proposed heuristic outperforms the state-of-the-art algorithm and obtains the best solutions in 140 out of 160 benchmark instances.     

Combining the principles of variable neighborhood decomposition search and the fix&optimize heuristic to solve multi-level lot-sizing and scheduling problems

In this paper a new heuristic is proposed to solve general multi-level lot-sizing and scheduling problems. The idea is to cross-fertilize the principles of the meta-heuristic Variable Neighborhood Decomposition Search (VNDS) with those of the MIP-based Fix&Optimize heuristic. This combination will make it possible to solve the kind of problems that typically arise in the consumer goods industry due to sequence-dependent setups and shifting bottlenecks. In order to demonstrate the strength of this procedure, a GLSP variant for multiple production stages is chosen as a representative. With the help of artificial and real-world instances, the quality of the solution as well as the computational performance of the new procedure is tested and compared to a standard MIP-solver.     

A genetic algorithm approach to the multiple machine tool selection problem

A number of earlier researches have emphasized the on-the-job scheduling problems that occur with a single flexible machine. Two solutions to the problem have generally been considered; namely minimization of tool switches and minimization of tool switching instances. Methods used to solve the problems have included KTNS heuristic, dual-based relaxation heuristic, and non-LP-based branch-and-bound methods. However, scant literature has considered the case of job scheduling on multiple parallel machines which invokes another problem involving machine assignment. This paper addresses the problem of job scheduling and machine assignment on a flexible machining workstation (FMW) equipped with multiple parallel machines in a tool-sharing environment. Under these circumstances, the authors have attempted to model the problem with the objective of simultaneously minimizing both the number of tool switches and the number of tool switching instances. Furthermore, a set of realistic constraints has been included in the investigation. A novel genetic algorithm (GA) heuristic has been developed to solve the problem, and performance results show that GA is an appropriate solution.