872 resultados para Particle swarm optimization algorithm PSO
Resumo:
La survie des rseaux est un domaine d'tude technique trs intressant ainsi qu'une proccupation critique dans la conception des rseaux. Compte tenu du fait que de plus en plus de donnes sont transportes travers des rseaux de communication, une simple panne peut interrompre des millions d'utilisateurs et engendrer des millions de dollars de pertes de revenu. Les techniques de protection des rseaux consistent fournir une capacit supplmentaire dans un rseau et racheminer les flux automatiquement autour de la panne en utilisant cette disponibilit de capacit. Cette thse porte sur la conception de rseaux optiques intgrant des techniques de survie qui utilisent des schmas de protection bass sur les p-cycles. Plus prcisment, les p-cycles de protection par chemin sont exploits dans le contexte de pannes sur les liens. Notre tude se concentre sur la mise en place de structures de protection par p-cycles, et ce, en supposant que les chemins d'opration pour l'ensemble des requtes sont dfinis a priori. La majorit des travaux existants utilisent des heuristiques ou des mthodes de rsolution ayant de la difficult rsoudre des instances de grande taille. L'objectif de cette thse est double. D'une part, nous proposons des modles et des mthodes de rsolution capables d'aborder des problmes de plus grande taille que ceux dj prsents dans la littrature. D'autre part, grce aux nouveaux algorithmes, nous sommes en mesure de produire des solutions optimales ou quasi-optimales. Pour ce faire, nous nous appuyons sur la technique de gnration de colonnes, celle-ci tant adquate pour rsoudre des problmes de programmation linaire de grande taille. Dans ce projet, la gnration de colonnes est utilise comme une faon intelligente d'numrer implicitement des cycles prometteurs. Nous proposons d'abord des formulations pour le problme matre et le problme auxiliaire ainsi qu'un premier algorithme de gnration de colonnes pour la conception de rseaux proteges par des p-cycles de la protection par chemin. L'algorithme obtient de meilleures solutions, dans un temps raisonnable, que celles obtenues par les mthodes existantes. Par la suite, une formulation plus compacte est propose pour le problme auxiliaire. De plus, nous prsentons une nouvelle mthode de dcomposition hirarchique qui apporte une grande amlioration de l'efficacit globale de l'algorithme. En ce qui concerne les solutions en nombres entiers, nous proposons deux mthodes heurisiques qui arrivent trouver des bonnes solutions. Nous nous attardons aussi une comparaison systmatique entre les p-cycles et les schmas classiques de protection partage. Nous effectuons donc une comparaison prcise en utilisant des formulations unifies et bases sur la gnration de colonnes pour obtenir des rsultats de bonne qualit. Par la suite, nous valuons empiriquement les versions oriente et non-oriente des p-cycles pour la protection par lien ainsi que pour la protection par chemin, dans des scnarios de trafic asymtrique. Nous montrons quel est le cot de protection additionnel engendr lorsque des systmes bidirectionnels sont employs dans de tels scnarios. Finalement, nous tudions une formulation de gnration de colonnes pour la conception de rseaux avec des p-cycles en prsence d'exigences de disponibilit et nous obtenons des premires bornes infrieures pour ce problme.
Resumo:
Dans cette thse, nous prsentons une nouvelle mthode smoothed particle hydrodynamics (SPH) pour la rsolution des quations de Navier-Stokes incompressibles, mme en prsence des forces singulires. Les termes de sources singulires sont traits d'une manire similaire celle que l'on retrouve dans la mthode Immersed Boundary (IB) de Peskin (2002) ou de la mthode rgularise de Stokeslets (Cortez, 2001). Dans notre schma numrique, nous mettons en oeuvre une mthode de projection sans pression de second ordre inspire de Kim et Moin (1985). Ce schma vite compltement les difficults qui peuvent tre rencontres avec la prescription des conditions aux frontires de Neumann sur la pression. Nous prsentons deux variantes de cette approche: l'une, Lagrangienne, qui est communment utilise et l'autre, Eulerienne, car nous considrons simplement que les particules SPH sont des points de quadrature o les proprits du fluide sont calcules, donc, ces points peuvent tre laisss fixes dans le temps. Notre mthode SPH est d'abord teste la rsolution du problme de Poiseuille bidimensionnel entre deux plaques infinies et nous effectuons une analyse dtaille de l'erreur des calculs. Pour ce problme, les rsultats sont similaires autant lorsque les particules SPH sont libres de se dplacer que lorsqu'elles sont fixes. Nous traitons, par ailleurs, du problme de la dynamique d'une membrane immerge dans un fluide visqueux et incompressible avec notre mthode SPH. La membrane est reprsente par une spline cubique le long de laquelle la tension prsente dans la membrane est calcule et transmise au fluide environnant. Les quations de Navier-Stokes, avec une force singulire issue de la membrane sont ensuite rsolues pour dterminer la vitesse du fluide dans lequel est immerge la membrane. La vitesse du fluide, ainsi obtenue, est interpole sur l'interface, afin de dterminer son dplacement. Nous discutons des avantages maintenir les particules SPH fixes au lieu de les laisser libres de se dplacer. Nous appliquons ensuite notre mthode SPH la simulation des coulements confins des solutions de polymres non dilus avec une interaction hydrodynamique et des forces d'exclusion de volume. Le point de dpart de l'algorithme est le systme coupl des quations de Langevin pour les polymres et le solvant (CLEPS) (voir par exemple Oono et Freed (1981) et ttinger et Rabin (1989)) dcrivant, dans le cas prsent, les dynamiques microscopiques d'une solution de polymre en coulement avec une reprsentation bille-ressort des macromolcules. Des tests numriques de certains coulements dans des canaux bidimensionnels rvlent que l'utilisation de la mthode de projection d'ordre deux couple des points de quadrature SPH fixes conduit un ordre de convergence de la vitesse qui est de deux et une convergence d'ordre sensiblement gale deux pour la pression, pourvu que la solution soit suffisamment lisse. Dans le cas des calculs grandes chelles pour les altres et pour les chanes de bille-ressort, un choix appropri du nombre de particules SPH en fonction du nombre des billes N permet, en l'absence des forces d'exclusion de volume, de montrer que le cot de notre algorithme est d'ordre O(N). Enfin, nous amorons des calculs tridimensionnels avec notre modle SPH. Dans cette optique, nous rsolvons le problme de l'coulement de Poiseuille tridimensionnel entre deux plaques parallles infinies et le problme de l'coulement de Poiseuille dans une conduite rectangulaire infiniment longue. De plus, nous simulons en dimension trois des coulements confins entre deux plaques infinies des solutions de polymres non dilues avec une interaction hydrodynamique et des forces d'exclusion de volume.
Resumo:
Lapprentissage supervis de rseaux hirarchiques grande chelle connat prsentement un succs fulgurant. Malgr cette effervescence, lapprentissage non-supervis reprsente toujours, selon plusieurs chercheurs, un lment cl de lIntelligence Artificielle, o les agents doivent apprendre partir dun nombre potentiellement limit de donnes. Cette thse sinscrit dans cette pense et aborde divers sujets de recherche lis au problme destimation de densit par lentremise des machines de Boltzmann (BM), modles graphiques probabilistes au coeur de lapprentissage profond. Nos contributions touchent les domaines de lchantillonnage, lestimation de fonctions de partition, loptimisation ainsi que lapprentissage de reprsentations invariantes. Cette thse dbute par lexposition dun nouvel algorithme d'chantillonnage adaptatif, qui ajuste (de fa con automatique) la temprature des chanes de Markov sous simulation, afin de maintenir une vitesse de convergence leve tout au long de lapprentissage. Lorsquutilis dans le contexte de lapprentissage par maximum de vraisemblance stochastique (SML), notre algorithme engendre une robustesse accrue face la slection du taux dapprentissage, ainsi quune meilleure vitesse de convergence. Nos rsultats sont prsent es dans le domaine des BMs, mais la mthode est gnrale et applicable lapprentissage de tout modle probabiliste exploitant lchantillonnage par chanes de Markov. Tandis que le gradient du maximum de vraisemblance peut-tre approxim par chantillonnage, lvaluation de la log-vraisemblance ncessite un estim de la fonction de partition. Contrairement aux approches traditionnelles qui considrent un modle donn comme une bote noire, nous proposons plutt dexploiter la dynamique de lapprentissage en estimant les changements successifs de log-partition encourus chaque mise jour des paramtres. Le problme destimation est reformul comme un problme dinfrence similaire au filtre de Kalman, mais sur un graphe bi-dimensionnel, o les dimensions correspondent aux axes du temps et au paramtre de temprature. Sur le thme de loptimisation, nous prsentons galement un algorithme permettant dappliquer, de manire efficace, le gradient naturel des machines de Boltzmann comportant des milliers dunits. Jusqu prsent, son adoption tait limite par son haut cot computationel ainsi que sa demande en mmoire. Notre algorithme, Metric-Free Natural Gradient (MFNG), permet dviter le calcul explicite de la matrice dinformation de Fisher (et son inverse) en exploitant un solveur linaire combin un produit matrice-vecteur efficace. Lalgorithme est prometteur: en terme du nombre dvaluations de fonctions, MFNG converge plus rapidement que SML. Son implmentation demeure malheureusement inefficace en temps de calcul. Ces travaux explorent galement les mcanismes sous-jacents lapprentissage de reprsentations invariantes. cette fin, nous utilisons la famille de machines de Boltzmann restreintes spike & slab (ssRBM), que nous modifions afin de pouvoir modliser des distributions binaires et parcimonieuses. Les variables latentes binaires de la ssRBM peuvent tre rendues invariantes un sous-espace vectoriel, en associant chacune delles, un vecteur de variables latentes continues (dnommes slabs). Ceci se traduit par une invariance accrue au niveau de la reprsentation et un meilleur taux de classification lorsque peu de donnes tiquetes sont disponibles. Nous terminons cette thse sur un sujet ambitieux: lapprentissage de reprsentations pouvant sparer les facteurs de variations prsents dans le signal dentre. Nous proposons une solution base de ssRBM bilinaire (avec deux groupes de facteurs latents) et formulons le problme comme lun de pooling dans des sous-espaces vectoriels complmentaires.
Resumo:
Embedded systems are usually designed for a single or a specified set of tasks. This specificity means the system design as well as its hardware/software development can be highly optimized. Embedded software must meet the requirements such as high reliability operation on resource-constrained platforms, real time constraints and rapid development. This necessitates the adoption of static machine codes analysis tools running on a host machine for the validation and optimization of embedded system codes, which can help meet all of these goals. This could significantly augment the software quality and is still a challenging field.Embedded systems are usually designed for a single or a specified set of tasks. This specificity means the system design as well as its hardware/software development can be highly optimized. Embedded software must meet the requirements such as high reliability operation on resource-constrained platforms, real time constraints and rapid development. This necessitates the adoption of static machine codes analysis tools running on a host machine for the validation and optimization of embedded system codes, which can help meet all of these goals. This could significantly augment the software quality and is still a challenging field.Embedded systems are usually designed for a single or a specified set of tasks. This specificity means the system design as well as its hardware/software development can be highly optimized. Embedded software must meet the requirements such as high reliability operation on resource-constrained platforms, real time constraints and rapid development. This necessitates the adoption of static machine codes analysis tools running on a host machine for the validation and optimization of embedded system codes, which can help meet all of these goals. This could significantly augment the software quality and is still a challenging field.Embedded systems are usually designed for a single or a specified set of tasks. This specificity means the system design as well as its hardware/software development can be highly optimized. Embedded software must meet the requirements such as high reliability operation on resource-constrained platforms, real time constraints and rapid development. This necessitates the adoption of static machine codes analysis tools running on a host machine for the validation and optimization of embedded system codes, which can help meet all of these goals. This could significantly augment the software quality and is still a challenging field.This dissertation contributes to an architecture oriented code validation, error localization and optimization technique assisting the embedded system designer in software debugging, to make it more effective at early detection of software bugs that are otherwise hard to detect, using the static analysis of machine codes. The focus of this work is to develop methods that automatically localize faults as well as optimize the code and thus improve the debugging process as well as quality of the code.Validation is done with the help of rules of inferences formulated for the target processor. The rules govern the occurrence of illegitimate/out of place instructions and code sequences for executing the computational and integrated peripheral functions. The stipulated rules are encoded in propositional logic formulae and their compliance is tested individually in all possible execution paths of the application programs. An incorrect sequence of machine code pattern is identified using slicing techniques on the control flow graph generated from the machine code.An algorithm to assist the compiler to eliminate the redundant bank switching codes and decide on optimum data allocation to banked memory resulting in minimum number of bank switching codes in embedded system software is proposed. A relation matrix and a state transition diagram formed for the active memory bank state transition corresponding to each bank selection instruction is used for the detection of redundant codes. Instances of code redundancy based on the stipulated rules for the target processor are identified.This validation and optimization tool can be integrated to the system development environment. It is a novel approach independent of compiler/assembler, applicable to a wide range of processors once appropriate rules are formulated. Program states are identified mainly with machine code pattern, which drastically reduces the state space creation contributing to an improved state-of-the-art model checking. Though the technique described is general, the implementation is architecture oriented, and hence the feasibility study is conducted on PIC16F87X microcontrollers. The proposed tool will be very useful in steering novices towards correct use of difficult microcontroller features in developing embedded systems.
Resumo:
This thesis Entitled Studies on transport and magnetic properties of nano particle doped mgb2 superconductor for technological applications.The thesis ahead focuses on the establishment of enhanced superconducting properties in bulk MgB2 via nano particle doping and its conversion into mono/multifilamentary wires. Further, an attempt has also been made to develop prototypes of MgB2 coil and conduction cooled current lead for technological applications. The thesis is configured into 6 chapters. The opening chapter gives an idea on the phenomenon of superconductivity, the various types of superconductors and its applications in different fields. The second chapter is an introduction on MgB2 superconductor and its relevance which includes crystal and electronic structure, superconducting mechanism, basic superconducting properties along with its present international status. The third chapter provides details on the preparation and characterization techniques followed through out the study on MgB2. Fourth chapter discusses the effect of processing temperature and chemical doping using nano sized dopants on the superconducting properties of MgB2 Fifth chapter deals with the optimization of processing parameters and novel preparation techniques for wire fabrication. Sixth chapter furnishes the preparation of multifilamentary wires with various filament configurations, their electromechanical properties and it also incorporates the development of an MgB2 coil and a general purpose conduction cooled current lead.
Resumo:
Assembly job shop scheduling problem (AJSP) is one of the most complicated combinatorial optimization problem that involves simultaneously scheduling the processing and assembly operations of complex structured products. The problem becomes even more complicated if a combination of two or more optimization criteria is considered. This thesis addresses an assembly job shop scheduling problem with multiple objectives. The objectives considered are to simultaneously minimizing makespan and total tardiness. In this thesis, two approaches viz., weighted approach and Pareto approach are used for solving the problem. However, it is quite difficult to achieve an optimal solution to this problem with traditional optimization approaches owing to the high computational complexity. Two metaheuristic techniques namely, genetic algorithm and tabu search are investigated in this thesis for solving the multiobjective assembly job shop scheduling problems. Three algorithms based on the two metaheuristic techniques for weighted approach and Pareto approach are proposed for the multi-objective assembly job shop scheduling problem (MOAJSP). A new pairing mechanism is developed for crossover operation in genetic algorithm which leads to improved solutions and faster convergence. The performances of the proposed algorithms are evaluated through a set of test problems and the results are reported. The results reveal that the proposed algorithms based on weighted approach are feasible and effective for solving MOAJSP instances according to the weight assigned to each objective criterion and the proposed algorithms based on Pareto approach are capable of producing a number of good Pareto optimal scheduling plans for MOAJSP instances.
Resumo:
Over-sampling sigma-delta analogue-to-digital converters (ADCs) are one of the key building blocks of state of the art wireless transceivers. In the sigma-delta modulator design the scaling coefficients determine the overall signal-to-noise ratio. Therefore, selecting the optimum value of the coefficient is very important. To this end, this paper addresses the design of a fourthorder multi-bit sigma-delta modulator for Wireless Local Area Networks (WLAN) receiver with feed-forward path and the optimum coefficients are selected using genetic algorithm (GA)- based search method. In particular, the proposed converter makes use of low-distortion swing suppression SDM architecture which is highly suitable for low oversampling ratios to attain high linearity over a wide bandwidth. The focus of this paper is the identification of the best coefficients suitable for the proposed topology as well as the optimization of a set of system parameters in order to achieve the desired signal-to-noise ratio. GA-based search engine is a stochastic search method which can find the optimum solution within the given constraints.
Resumo:
A Multi-Objective Antenna Placement Genetic Algorithm (MO-APGA) has been proposed for the synthesis of matched antenna arrays on complex platforms. The total number of antennas required, their position on the platform, location of loads, loading circuit parameters, decoupling and matching network topology, matching network parameters and feed network parameters are optimized simultaneously. The optimization goal was to provide a given minimum gain, specific gain discrimination between the main and back lobes and broadband performance. This algorithm is developed based on the non-dominated sorting genetic algorithm (NSGA-II) and Minimum Spanning Tree (MST) technique for producing diverse solutions when the number of objectives is increased beyond two. The proposed method is validated through the design of a wideband airborne SAR
Resumo:
This paper presents a new approach to the design of combinational digital circuits with multiplexers using Evolutionary techniques. Genetic Algorithm (GA) is used as the optimization tool. Several circuits are synthesized with this method and compared with two design techniques such as standard implementation of logic functions using multiplexers and implementation using Shannons decomposition technique using GA. With the proposed method complexity of the circuit and the associated delay can be reduced significantly
Resumo:
In this report, we discuss the application of global optimization and Evolutionary Computation to distributed systems. We therefore selected and classified many publications, giving an insight into the wide variety of optimization problems which arise in distributed systems. Some interesting approaches from different areas will be discussed in greater detail with the use of illustrative examples.
Resumo:
En este trabajo se implementa una metodologa para incluir momentos de orden superior en la seleccin de portafolios, haciendo uso de la Distribucin Hiperblica Generalizada, para posteriormente hacer un anlisis comparativo frente al modelo de Markowitz.
Resumo:
Muchas de las nuevas aplicaciones emergentes de Internet tales como TV sobre Internet, Radio sobre Internet,Video Streamming multi-punto, entre otras, necesitan los siguientes requerimientos de recursos: ancho de banda consumido, retardo extremo-a-extremo, tasa de paquetes perdidos, etc. Por lo anterior, es necesario formular una propuesta que especifique y provea para este tipo de aplicaciones los recursos necesarios para su buen funcionamiento. En esta tesis, proponemos un esquema de ingeniera de trfico multi-objetivo a travs del uso de diferentes rboles de distribucin para muchos flujos multicast. En este caso, estamos usando la aproximacin de mltiples caminos para cada nodo egreso y de esta forma obtener la aproximacin de mltiples rboles y a travs de esta forma crear diferentes rboles multicast. Sin embargo, nuestra propuesta resuelve la fraccin de la divisin del trfico a travs de mltiples rboles. La propuesta puede ser aplicada en redes MPLS estableciendo rutas explcitas en eventos multicast. En primera instancia, el objetivo es combinar los siguientes objetivos ponderados dentro de una mtrica agregada: mxima utilizacin de los enlaces, cantidad de saltos, el ancho de banda total consumido y el retardo total extremo-a-extremo. Nosotros hemos formulado esta funcin multi-objetivo (modelo MHDB-S) y los resultados obtenidos muestran que varios objetivos ponderados son reducidos y la mxima utilizacin de los enlaces es minimizada. El problema es NP-duro, por lo tanto, un algoritmo es propuesto para optimizar los diferentes objetivos. El comportamiento que obtuvimos usando este algoritmo es similar al que obtuvimos con el modelo. Normalmente, durante la transmisin multicast los nodos egresos pueden salir o entrar del rbol y por esta razn en esta tesis proponemos un esquema de ingeniera de trfico multi-objetivo usando diferentes rboles para grupos multicast dinmicos. (en el cual los nodos egresos pueden cambiar durante el tiempo de vida de la conexin). Si un rbol multicast es recomputado desde el principio, esto podra consumir un tiempo considerable de CPU y adems todas las comuicaciones que estn usando el rbol multicast sern temporalmente interrumpida. Para aliviar estos inconvenientes, proponemos un modelo de optimizacin (modelo dinmico MHDB-D) que utilice los rboles multicast previamente computados (modelo esttico MHDB-S) adicionando nuevos nodos egreso. Usando el mtodo de la suma ponderada para resolver el modelo analtico, no necesariamente es correcto, porque es posible tener un espacio de solucin no convexo y por esta razn algunas soluciones pueden no ser encontradas. Adicionalmente, otros tipos de objetivos fueron encontrados en diferentes trabajos de investigacin. Por las razones mencionadas anteriormente, un nuevo modelo llamado GMM es propuesto y para dar solucin a este problema un nuevo algoritmo usando Algoritmos Evolutivos Multi-Objetivos es propuesto. Este algoritmo esta inspirado por el algoritmo Strength Pareto Evolutionary Algorithm (SPEA). Para dar una solucin al caso dinmico con este modelo generalizado, nosotros hemos propuesto un nuevo modelo dinmico y una solucin computacional usando Breadth First Search (BFS) probabilstico. Finalmente, para evaluar nuestro esquema de optimizacin propuesto, ejecutamos diferentes pruebas y simulaciones. Las principales contribuciones de esta tesis son la taxonoma, los modelos de optimizacin multi-objetivo para los casos esttico y dinmico en transmisiones multicast (MHDB-S y MHDB-D), los algoritmos para dar solucin computacional a los modelos. Finalmente, los modelos generalizados tambin para los casos esttico y dinmico (GMM y GMM Dinmico) y las propuestas computacionales para dar slucin usando MOEA y BFS probabilstico.
Resumo:
An algorithm is presented for the generation of molecular models of defective graphene fragments, containing a majority of 6-membered rings with a small number of 5- and 7-membered rings as defects. The structures are generated from an initial random array of points in 2D space, which are then subject to Delaunay triangulation. The dual of the triangulation forms a Voronoi tessellation of polygons with a range of ring sizes. An iterative cycle of refinement, involving deletion and addition of points followed by further triangulation, is performed until the user-defined criteria for the number of defects are met. The array of points and connectivities are then converted to a molecular structure and subject to geometry optimization using a standard molecular modeling package to generate final atomic coordinates. On the basis of molecular mechanics with minimization, this automated method can generate structures, which conform to user-supplied criteria and avoid the potential bias associated with the manual building of structures. One application of the algorithm is the generation of structures for the evaluation of the reactivity of different defect sites. Ab initio electronic structure calculations on a representative structure indicate preferential fluorination close to 5-ring defects.
Resumo:
This paper deals with the design of optimal multiple gravity assist trajectories with deep space manoeuvres. A pruning method which considers the sequential nature of the problem is presented. The method locates feasible vectors using local optimization and applies a clustering algorithm to find reduced bounding boxes which can be used in a subsequent optimization step. Since multiple local minima remain within the pruned search space, the use of a global optimization method, such as Differential Evolution, is suggested for finding solutions which are likely to be close to the global optimum. Two case studies are presented.
Resumo:
A novel Swarm Intelligence method for best-fit search, Stochastic Diffusion Search, is presented capable of rapid location of the optimal solution in the search space. Population based search mechanisms employed by Swarm Intelligence methods can suffer lack of convergence resulting in ill defined stopping criteria and loss of the best solution. Conversely, as a result of its resource allocation mechanism, the solutions SDS discovers enjoy excellent stability.
