Reformulation and a Lagrangian heuristic for lot sizing problem on parallel machines

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Hybrid methods for lot sizing on parallel machines

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Compiling serial languages for parallel machines /

Thesis (M. S.)--University of Illinois at Urbana-Champaign.

Control structures for parallel machines /

"UILU-ENG 79 1724"

Afetação de recursos em sistemas de produção

O problema do escalonamento, por ser um dos factores fundamentais na tomada de decisão para uma boa gestão das operações, tem sido alvo de um amplo estudo, tanto na sua componente teórica como na sua componente prática. A importância de um escalonamento correto das operações é preponderante, quando as pequenas diferenças, em termos de tempos de produção, podem ter um grande impacto na competitividade da organização. Em muitas unidades produtivas, existem máquinas capazes de realizar as mesmas operações com diferentes desempenhos. Isto pode dever-se à necessidade de flexibilizar os recursos ou mesmo a uma atualização da capacidade produtiva. Embora os problemas de máquinas diferentes em paralelo tenham sido alvo de um vasto estudo, muitos deles não são passíveis de ser resolvidos através de métodos exatos. O problema de minimização do makespan (Rm||Cmax), é NP-hard, sendo habitualmente abordado através de heurísticas. Entre as heurísticas utilizadas em problemas de minimização do makespan em máquinas diferentes em paralelo, é possível identificar duas filosofias de afectação: a que utiliza os tempos de processamento para alocar as tarefas e a que utiliza as datas de conclusão. Nesta dissertação, pretende-se dar uma contribuição para a resolução do problema de afectação de recursos em sistemas de produção. Para tal, foram propostas as heurísticas OMTC 3 e Suffrage One. A contribuição consiste na proposta de versões híbridas e modificadas das heurística MCT e Suffrage, uma vez identificadas várias características que podem limitar o seu desempenho, como o facto da heurística MCT alocar as tarefas numa ordem aleatória ou a heurística Suffrage alocar mais que uma tarefa por iteração. Finalmente, procedeu-se à realização de testes computacionais, para avaliar o desempenho das heurísticas propostas. Os testes realizados permitiram concluir que a heurística OMTC 3 apresentou um melhor desempenho que a heurística MCT.

Modelos Matemáticos e Métodos de Solução para Problemas de Dimensionamento de Lotes

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Concurrent Aggregates (CA): An Object-Oriented Language for Fine-Grained Message-Passing Machines

Fine-grained parallel machines have the potential for very high speed computation. To program massively-concurrent MIMD machines, programmers need tools for managing complexity. These tools should not restrict program concurrency. Concurrent Aggregates (CA) provides multiple-access data abstraction tools, Aggregates, which can be used to implement abstractions with virtually unlimited potential for concurrency. Such tools allow programmers to modularize programs without reducing concurrency. I describe the design, motivation, implementation and evaluation of Concurrent Aggregates. CA has been used to construct a number of application programs. Multi-access data abstractions are found to be useful in constructing highly concurrent programs.

Using P-GENESIS for Parallel Simulation of GENESIS Models

P-GENESIS is an extension to the GENESIS neural simulator that allows users to take advantage of parallel machines to speed up the simulation of their network models or concurrently simulate multiple models. P-GENESIS adds several commands to the GENESIS script language that let a script running on one processor execute remote procedure calls on other processors, and that let a script synchronize its execution with the scripts running on other processors. We present here some brief comments on the mechanisms underlying parallel script execution. We also offer advice on parallelizing parameter searches, partitioning network models, and selecting suitable parallel hardware on which to run P-GENESIS.

Easy PRAM-based High-performance Parallel Programming with ICE

A poster of this paper will be presented at the 25th International Conference on Parallel Architecture and Compilation Technology (PACT ’16), September 11-15, 2016, Haifa, Israel.

Skewness, splitting number and vertex deletion of some toroidal meshes

The skewness sk(G) of a graph G = (V, E) is the smallest integer sk(G) >= 0 such that a planar graph can be obtained from G by the removal of sk(C) edges. The splitting number sp(G) of C is the smallest integer sp(G) >= 0 such that a planar graph can be obtained from G by sp(G) vertex splitting operations. The vertex deletion vd(G) of G is the smallest integer vd(G) >= 0 such that a planar graph can be obtained from G by the removal of vd(G) vertices. Regular toroidal meshes are popular topologies for the connection networks of SIMD parallel machines. The best known of these meshes is the rectangular toroidal mesh C(m) x C(n) for which is known the skewness, the splitting number and the vertex deletion. In this work we consider two related families: a triangulation Tc(m) x c(n) of C(m) x C(n) in the torus, and an hexagonal mesh Hc(m) x c(n), the dual of Tc(m) x c(n) in the torus. It is established that sp(Tc(m) x c(n)) = vd(Tc(m) x c(n) = sk(Hc(m) x c(n)) = sp(Hc(m) x c(n)) = vd(Hc(m) x c(n)) = min{m, n} and that sk(Tc(m) x c(n)) = 2 min {m, n}.

Estudo e análise do sequenciamento de tarefas de produção: job shop scheduling

Esta dissertação apresenta um estudo sobre os problemas de sequenciamento de tarefas de produção do tipo job shop scheduling. Os problemas de sequenciamento de tarefas de produção pretendem encontrar a melhor sequência para o processamento de uma lista de tarefas, o instante de início e término de cada tarefa e a afetação de máquinas para as tarefas. Entre estes, encontram-se os problemas com máquinas paralelas, os problemas job shop e flow shop. As medidas de desempenho mais comuns são o makespan (instante de término da execução de todas as tarefas), o tempo de fluxo total, a soma dos atrasos (tardiness), o atraso máximo, o número de tarefas que são completadas após a data limite, entre outros. Num problema do tipo job shop, as tarefas (jobs) consistem num conjunto de operações que têm de ser executadas numa máquina pré-determinada, obedecendo a um determinado sequenciamento com tempos pré-definidos. Estes ambientes permitem diferentes cenários de sequenciamento das tarefas. Normalmente, não são permitidas interrupções no processamento das tarefas (preemption) e pode ainda ser necessário considerar tempos de preparação dependentes da sequência (sequence dependent setup times) ou atribuir pesos (prioridades) diferentes em função da importância da tarefa ou do cliente. Pretende-se o estudo dos modelos matemáticos existentes para várias variantes dos problemas de sequenciamento de tarefas do tipo job shop e a comparação dos resultados das diversas medidas de desempenho da produção. Este trabalho contribui para demonstrar a importância que um bom sequenciamento da produção pode ter na sua eficiência e consequente impacto financeiro.

Infraestructura de comunicaciones para algoritmos colaborativos

Este proyecto intenta crear un sistema cliente/servidor de comunicaciones para distintas máquinas paralelas en C++ utilizando WCF como tecnología en el servidor.

Development of a simulation tool for torsional vibration of branched power transmission system

In this master's thesis a mechanical model that is driven with variable speed synchronous machine was developed. The developed mechanical model simulates the mechanics of power transmission and its torsional vibrations. The mechanical model was developed for the need of the branched mechanics of a rolling mill and the propulsion system of a tanker. First, the scope of the thesis was to clarify the concepts connected to the mechanical model. The clarified concepts are the variable speed drive, the mechanics of power transmission and the vibrationsin the power transmission. Next, the mechanical model with straight shaft line and twelve moments of inertia that existed in the beginning was developed to be branched considering the case of parallel machines and the case of parallel rolls. Additionally, the model was expanded for the need of moreaccurate simulation to up to thirty moments of inertia. The model was also enhanced to enable three phase short circuit situation of the simulated machine. After that the mechanical model was validated by comparing the results of the developed simulation tool to results of other simulation tools. The compared results are the natural frequencies and mode shapes of torsional vibration, the response of the load torque step and the stress in the mechanical system occurred by the permutation of the magnetic field that is arisen from the three phase short circuit situation. The comparisons were accomplished well and the mechanical model was validated for the compared cases. Further development to be made is to develop the load torque to be time-dependent and to install two frequency converters and two FEM modeled machines to be simulated parallel.

Efficient Algorithms for Coastal Geographic Problems

The increasing performance of computers has made it possible to solve algorithmically problems for which manual and possibly inaccurate methods have been previously used. Nevertheless, one must still pay attention to the performance of an algorithm if huge datasets are used or if the problem iscomputationally difficult. Two geographic problems are studied in the articles included in this thesis. In the first problem the goal is to determine distances from points, called study points, to shorelines in predefined directions. Together with other in-formation, mainly related to wind, these distances can be used to estimate wave exposure at different areas. In the second problem the input consists of a set of sites where water quality observations have been made and of the results of the measurements at the different sites. The goal is to select a subset of the observational sites in such a manner that water quality is still measured in a sufficient accuracy when monitoring at the other sites is stopped to reduce economic cost. Most of the thesis concentrates on the first problem, known as the fetch length problem. The main challenge is that the two-dimensional map is represented as a set of polygons with millions of vertices in total and the distances may also be computed for millions of study points in several directions. Efficient algorithms are developed for the problem, one of them approximate and the others exact except for rounding errors. The solutions also differ in that three of them are targeted for serial operation or for a small number of CPU cores whereas one, together with its further developments, is suitable also for parallel machines such as GPUs.

GRASP heuristic with path-relinking for the multi-plant capacitated lot sizing problem

This paper addresses the independent multi-plant, multi-period, and multi-item capacitated lot sizing problem where transfers between the plants are allowed. This is an NP-hard combinatorial optimization problem and few solution methods have been proposed to solve it. We develop a GRASP (Greedy Randomized Adaptive Search Procedure) heuristic as well as a path-relinking intensification procedure to find cost-effective solutions for this problem. In addition, the proposed heuristics is used to solve some instances of the capacitated lot sizing problem with parallel machines. The results of the computational tests show that the proposed heuristics outperform other heuristics previously described in the literature. The results are confirmed by statistical tests. (C) 2009 Elsevier B.V. All rights reserved.