O fenômeno do congestionamento, decorrente do rápido aumento da demanda por todos os meios de transporte só tende a se agravar, já que sistemas de transporte (vistos como um todo) têm um grande impacto na economia mundial. No caso do transporte veicular em particular, é notório que a demanda por mobilidade é uma das características da nossa sociedade. O impacto direto e indireto dos congestionamentos em áreas urbanas e interurbanas é imenso, e precisam ser avaliados adequadamente para que seus efeitos sejam pelo menos minorados. Esta dissertação apresenta o AVNET, uma modelagem baseada em agentes para avali- ação do balanceamento de carga em redes de tráfego veicular, capaz de investigar micros- copicamente a interação entre oferta, demanda e as particularidades do comportamento dos motoristas, aqui tratados como agentes autônomos capazes de perceber o estado do ambiente e se adaptar a ele utilizando replanejamento heurístico. O principal objetivo do AVNET é investigar a interação entre a percepção que o agente possui do tráfego e a consequente adaptação através da mudança de rota durante a viagem. De forma cíclica, o AVNET propõe que o estado do ambiente influencia na percepção do agente, e a ação do agente influencia no estado do ambiente. As medidas de balanceamento de carga visam avaliar o desempenho do ponto de vista do motorista, ao invés de abordar a avaliação do ponto de vista da rede como algumas abordagens tradicionalmente propõe. Experimentos foram realizados a partir da variação nas condições de oferta - utili- zando uma rede com topologia em estilo de grade e uma abstração de algumas vias arte- riais da cidade de Porto Alegre/RS - variação nas condições de demanda - o tipo de dis- tribuição e número de viagens - e dos tipos de agentes utilizados. Os resultados ajudam a responder como será o balanceamento de carga de redes de tráfego veicular conforme as condições de oferta e demanda do ambiente, e de percepção/ação dos agentes. / The phenomenon of congestion, due to the rapid increase in demand for all means of transport is only going to worsen, since systems transport (seen as a whole) have a major impact on the world economy. In the case of vehicular transport in particular, it is clear that the demand for mobility is a characteristic of our society. The direct and indirect impact of congestion in urban and long distance is immense, and must be properly evaluated for their effects are at least mitigated. This dissertation presents the AVNET, an agent-basead modelling to evaluate load bal- ancing in networks of vehicular traffic, able to microscopically investigate the interaction between supply, demand and the peculiarities of the behavior of drivers, here treated as autonomous agents, capable to perceive the state of the environment and adapt to it using heuristic redesign. The main goal of AVNET is to investigate the interaction between the perception that the agent has the traffic and the consequent adaptation by changing the route during the trip. Cyclically, the AVNET propose that the state of the environment influences the perception of the agent and the agent’s action influences the state of the environment. Experiments were performed from the variation in supply conditions - using a network grid topology and an abstraction of some arterial roads in the city of Porto Alegre/RS - changes in demand conditions - the type of distribution and number of trips - and the types of agents used. The results will help answer how the balancing network load of vehicular traffic as conditions of supply and demand of the environment, and perception / action agents.

O bom desempenho de uma aplicação paralela é obtido conforme o modo como as técnicas de paralelização são empregadas. Para utilizar essas técnicas, é preciso encontrar uma forma adequada de extrair o paralelismo. Esta extração pode ser feita através de um grafo representativo da aplicação. Neste trabalho são aplicados métodos de particionamento de grafos para otimizar as comunicações entre os processos que fazem parte de uma computação paralela. Nesse contexto, a alocação dos processos almeja minimizar a quantidade de comunicações entre processadores. Esta técnica é frequentemente adotada em Processamento de Alto Desempenho - PAD. No entanto, a construção de grafo geralmente está embutida no programa, cujas estruturas de dados privadas são empregadas na contrução do grafo. A proposta é usar ferramentas diretamente em programas MPI, empregando, apenas, os recursos padr ões da norma MPI 1.2. O objetivo é fornecer uma biblioteca (b -MPI) portável para o escalonamento estático de programas MPI. O escalonamento estático realizado pela biblioteca é feito através do mapeamento de processos Esse mapeamento busca agrupar os processos que trocam muitas informações em um mesma máquina, o que nesse caso diminui o volume de dados trafegados pela rede. O mapeamento será realizado estaticamente após uma execução prévia do programa MPI. As aplicações alvo para o uso da b -MPI são aquelas que mantêm o mesmo padrão de comunicação após execuções sucessivas. A validação da biblioteca foi realizada atrav és da Transformada Rápida de Fourier disponível no pacote FFTW, da resolução do Problema de Transferência de Calor através do Método de Schwarz e Multigrid e da Fatora ção LU implementada no benchmark HPL. Os resultados mostraram que a b -MPI pode ser utilizada para distribuir os processos e cientemente minimizando o volume de mensagens trafegadas pela rede. / A good performance of a parallel application is obtained according to the mode as the parallelization techniques are applied. To make use of these techniques, is necessary to nd an appropriate way to extract the parallelism. This extraction can be done through a representative graph of the application. In this work, methods of partitioning graphs are applied to optimize the communication between processes that belong to a parallel computation. In this context, the processes allocation aims to minimize the communication amount between processors. This technique is frequently adopted in High Performance Computing - HPC. However, the graph building is generally inside the program, that has private data structures employed in the graph building. The proposal is to utilize tools directly in MPI programs, employing only standard resources of the MPI 1.2 norm. The goal is to provide a portable library (b -MPI) to static schedule MPI programs. The static scheduling realized by the library is done through the mapping of processes. This mapping seeks to cluster the processes that exchange a lot of information in the same machine that, in this case decreases the data volume passed through the net. The mapping will be done staticly after a previous execution of a MPI program. The target applications to make use of b -MPI are those whose keep the same communication pattern after successives executions. The library validation is done through the available applications in the FFTW package, the solving of the problem of Heat Transference through the Additive Schwarz Method and Multigrid and the LU factorization implemented in the HPL benchmark. The results show that b -MPI can be utilized to distribute the processes ef ciently minimizing the volume of messages exchanged through the network.

Orientador: Flavio Keidi Miyazawa / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-15T17:39:45Z (GMT). No. of bitstreams: 1 Vignatti_AndreLuis_D.pdf: 822237 bytes, checksum: d9b8ad70708a9313f0d1ed9d64d39302 (MD5) Previous issue date: 2010 / Resumo: Nesta tese, estudamos versões de teoria dos jogos dos problemas de empacotamento de itens e balanceamento de carga. Consideramos que a implementação de um algoritmo centralizado de controle é inviável, fazendo com que as entidades participantes do sistema ajam de maneira egoísta. Assim, a escolha egoísta de estratégias pelas entidades pode ou não levar a um estado estável do sistema, chamado de equilíbrio de Nash. Dependendo das condições definidas pelo modelo utilizado, devemos embutir certas regras para as entidades, contanto que as entidades tenham incentivo de utilizá-las e que, além disso, façam com que o sistema alcance um equilíbrio de Nash. Os principais resultados desta tese são relativos ao tempo de convergência para o equilíbrio de Nash, ou seja, buscamos saber quantas vezes os agentes mudam suas estratégias até alcançarem o equilíbrio de Nash, seja agindo de maneira completamente egoísta ou seguindo certas regras. Para o jogo de empacotamento de itens, apresentamos limitantes teóricos para o tempo de convergência, olhando ambos os casos de atualizações seqüenciais ou simultâneas das estratégias. Para o jogo de balanceamento de carga consideramos um modelo distribuído assíncrono com entidades heterogêneas, apresentando algumas regras que as entidades devem seguir e realizamos simulações para comparar as regras apresentadas / Abstract: In this thesis, we study game-theorical versions of the bin packing and load balancing problems. We consider that the implementation of a centralized controller algorithm is not feasible, making the entities that participate in the system act in a selfish way. Thus, the selfish choice of the strategies by the entities may or may not lead to a stable state of the system, called Nash equilibrium. Depending on the conditions defined by the considered model, we must build certain rules for entities, provided that the entities have incentive to use them and also make the system reach a Nash equilibrium. The main results of this thesis are related to the convergence time to Nash equilibrium, i.e., we seek to know how many times the agents change their strategies until they reach a Nash equilibrium, whether they act in a completely selfish way or follow certain rules. For the bin packing game, we present theoretical bounds for the convergence time, considering both the cases of sequential or simultaneous updates of the strategies. For the load balancing game, we consider an asynchronous distributed model with heterogeneous entities, presenting some rules that the entities must follow and we carry out simulations to compare the presented rules / Doutorado / Teoria da Computação / Doutor em Ciência da Computação

Estuda-se nesta tese o conteúdo jurídico do princípio da impessoalidade, previsto no art. 37, caput, da Constituição Federal de 1988, especificamente para fins de parametrização, controle e responsabilidade das decisões administrativas. Estruturam-se três eixos temáticos: a) noções introdutórias ideias de aproximação necessárias ao contexto e ao conceito do princípio da impessoalidade e do alcance de sua projeção nas decisões administrativas (póspositivismo e neoconstitucionalismo; constitucionalização; julgamento por princípios; relevância dos princípios; interesse público; direito administrativo como sistema; neutralidade política e a questão da justiça); b) impessoalidade no direito administrativo comprovação de que o princípio da impessoalidade ostenta arquétipo aberto para conferir maiores cobertura e proteção aos valores tutelados pelo texto constitucional, com ênfase à organização administrativa impessoal para assegurar um agir naturalmente impessoal (instrumentalização recíproca de princípios constitucionais; antecedentes históricos; direito estrangeiro; doutrina brasileira; impessoalidade na Constituição, nas leis e na jurisprudência; conceito de impessoalidade); c) impessoalidade nas decisões administrativas construção de um conceito de impessoalidade específico para as decisões administrativas, concebido desde a ideia de ponderação e conciliação de todos os interesses legítimos públicos e privados envolvidos em cada caso concreto (conceito e distinção de decisão administrativa impessoal em relação à decisão judicial imparcial; garantias e requisitos para a adoção de decisões impessoais, com destaque para os deveres de fundamentação (motivação), processualização e participação; algumas implicações de decisões impessoais [funcionário de fato; diminuição da discricionariedade; desvio de poder; motivação na dispensa de empregados públicos; responsabilidade civil extracontratual do Estado; necessidade de reconhecimento dos direitos dos administrados; nepotismo e revisitação da reformatio in pejus]; consequências da quebra da impessoalidade nas decisões administrativas [anulação; responsabilização do Estado e responsabilização do servidor] e, finalmente, técnicas para adoção de decisões administrativas impessoais). / This essay intends to analyze the juridical concept of the principle of impersonality, embraced in the article 37 of the Constitution of 1988, in order to establish standards of parameterization, control and liability in the administrative decisions. The essay comprises three main fields of analysis: a) introductory concepts preliminary approach to comprehend the theoretical and the political context in which is developed the scope and the enforcementof the principle of impersonality in the processes that lead to administrative decisions (postpositivism and neoconstitutionalism; the enforcement of principles; public interest; Administrative Law as a system; politic neutrality and the issue of Justice); b) the principle of impersonality within the Administrative Law - analysis of the scope of protection of the principle, aiming to demonstrate that its juridical concept must be considered in a wide open perspective in order to guarantee a strong protection of the constitutional values. In this part, it will be emphasized that the development of a impartial administrative conduct is closely related to the idea of a impartial administrative organization. (historical background; foreign legislation; Brazilian legal doctrine; the principle of the impersonality within the constitutional rules, the specific legislation and the judicial precedents; juridical concept of the principle); c) the enforcement of the principle of impersonality in administrative decisions - In this part it is developed the juridical concept of the principle in the field of the deliberative administrative proceedings. This juridical concept embraces the idea of balancing and conciliating all legitimate interests - public or private - involved in a determined situation that requires a administrative deliberation (distinctions between impersonal and impartial administrative decisions; standards to create a impersonal decision-making; specific implications of impersonal decisions; legal consequences arising from the disregard of the principle of impersonality in administrative decisions; legal techniques that lead to a impersonal administrative decision-making).

Balancing is usually done in the later phases of creating a game to make sure everything comes together to an enjoyable experience. Most of the time balancing is done with a series of playthroughs by the designers or by outsourced play testers and the imbalances found are corrected followed by more playthroughs. This method occupies a lot of time and might therefore not find everything. In this study I use information gathered from interviews with experienced designers and designer texts along with features from methods frequently used for aiding the designers to make a conceptual design of a tool that is aimed towards simplifying the process of balancing and reducing the amount of work hours having to be spent on this phase.

In today's world, more and more phone calls are made over IP. This results in an increasing demand for scalable IP telephony equipment. Ingate Systems AB produces firewalls specialized in handling IP telephony. They have an inherent limit in the number of concurrent phone calls that they can handle. This can be a bottleneck at high loads. There is a load balancing solution available in the platform, but it has a number of drawbacks, such as media latency and client capability requirements, limiting its usage. Many companies provide load balancing solutions for SIP. However, it appears few handle all the problematic scenarios that the Ingate firewall does. This master's thesis aims to add load balancing functionality to the Ingate firewall, so that it can handle all types of clients. By splitting the firewall into two completely separate layers - a SIP layer and a firewall layer - the concept of a virtual machine emerges. A machine is no longer restricted to its physical SIP and firewall layers. Instead, virtual machines are used to process calls. They still have SIP and firewall layers, but the layers can reside on different physical machines. This thesis demonstrates the operation of an innovative load balancing implementation. The implementation was evaluated, and using four machines the test setup performed 50% better than the original Ingate platform, while still retaining all functionality -- something that was not possible with the original platform. This surpassed both the company's and my own expectations.

La conception d’un entrepôt de données parallèle consiste à choisir l’architecture matérielle,à fragmenter le schéma d’entrepôt de données, à allouer les fragments générés, à répliquer les fragments pour assurer une haute performance du système et à définir la stratégie de traitement et d’équilibrage de charges. L’inconvénient majeur de ce cycle de conception est son ignorance de l’interdépendance entre les sous-problèmes liés à la conception d’un EDP et l’utilisation des métriques hétérogènes pour atteindre le même objectif. Notre première proposition définie un modèle de coût analytique pour le traitement parallèle des requêtes OLAP dans un environnement cluster. Notre deuxième proposition prend en considération l’interdépendance existante entre la fragmentation et l’allocation. Dans ce contexte, nous avons proposé une nouvelle approche de conception d’un EDP sur un cluster de machine. Durant le processus de fragmentation, notre approche décide si le schéma de fragmentation généré est pertinent pour le processus d’allocation. Les résultats obtenus sont très encourageant et une validation est faite sur Teradata. Notre troisième proposition consiste à présenter une méthode de conception qui est une extension de notre travail. Dans cette phase, une méthode de réplication originale, basée sur la logique floue, est intégrée. / Designing a parallel data warehouse consists of choosing the hardware architecture, fragmenting the data warehouse schema, allocating the generated fragments, replicating fragments to ensure high system performance and defining the treatment strategy and load balancing.The major drawback of this design cycle is its ignorance of the interdependence between subproblems related to the design of PDW and the use of heterogeneous metrics to achieve thesame goal. Our first proposal defines an analytical cost model for parallel processing of OLAP queries in a cluster environment. Our second takes into account the interdependence existing between fragmentation and allocation. In this context, we proposed a new approach to designa PDW on a cluster machine. During the fragmentation process, our approach determines whether the fragmentation pattern generated is relevant to the allocation process or not. The results are very encouraging and validation is done on Teradata. For our third proposition, we presented a design method which is an extension of our work. In this phase, an original method of replication, based on fuzzy logic is integrated.

The use of underwater systems has grown significantly, and they can be used both for military and civilian purposes. Many of their parts are replaceable. An underwater vehicle can be equipped with different devices depending on the taskit should carry out. This can make the vehicle unbalanced, which means that the demand for balancing systems will increase in line with the increasing use of underwater systems. The goal of the thesis is to deliver a method for balancing based on parameters estimated both in static and dynamic operation. The parameters define a nonlinear physical model that can describe the underwater vehicle in different environments and conditions. The main idea in the proposed method for parameter estimation based on static operation data is to solve equilibrium equations when the on-board control system is used to maintain two different orientations. The balancing can then be done by solving an optimisation problem that gives information about where additional weights or float material should be installed. The static parameter estimation has been evaluated successfully in simulations together with three ways of solving the balancing problem. The dynamic parameter estimation has also been evaluated in simulations. In this case, the estimated parameters seem to have the same sign as the true ones but it seems difficult to obtain accurate estimates of some of the parameters. However, the total dynamic model was good except the prediction of the vertical movements. In particular, the model could explain the rotations of the vehicle well. The reason for the worse performance for the vertical movements might be some difficulties when generating suitable excitation signals. The work done by Feras Faez Elias in connection to this master thesis made a contribution to a patent application that Saab AB has filed where Feras Faez Elias was one of the inventors.

The co-optimization of energy and reserves has become a standard requirement in integrated markets. This is due to the inverse relationship that exists between energy and reserves. The provision of reserves generally reduces the amount of primary energy a generating unit can produce and vice versa. This suggests that these products should be procured through a simultaneous auction to ensure optimal procurement and pricing. Furthermore, forward markets dictate that this co-optimization of energy and reserves be done over a multi-period planning horizon. This dissertation addresses the problem of optimal scheduling and pricing of energy and reserves over a multi-period planning horizon using an optimal power flow formulation. The extension of the problem from a static optimization problem to a dynamic optimization problem is presented. Price definitions for energy and reserves in terms of shadow prices emanating from the optimization algorithm are provided. It is shown that the proposed formulation of prices leads to the cascading of reserve prices and eliminates the problem of “price reversal” where lower quality reserves are priced higher than higher ii quality reserves. Pricing conditions are also established for the downward substitution of higher quality reserves for lower quality reserves. The proposed pricing formulations are tested on the IEEE 24 Bus Reliability Test System and on the South African power network. The simulated results show that cascading of reserve prices does occur and that prices of different types of reserves are equal when downward substitution of reserves occurs. Zonal reserve requirements result in higher energy and reserve prices, which in term result in higher procurement costs to the system operator and higher profits to market participants. Congestion on the network also results in higher procurement costs to the system operator and higher profits to market participants in the case of zonal pricing of reserves. / Dissertation (MEng)--University of Pretoria, 2013. / gm2014 / Electrical, Electronic and Computer Engineering / unrestricted

Dynamic balancing of computation and communication load is vital for the execution stability and performance of distributed, parallel simulations deployed on shared, unreliable resources of large-scale environments. High Level Architecture (HLA) based simulations can experience a decrease in performance due to imbalances that are produced initially and/or during run-time. These imbalances are generated by the dynamic load changes of distributed simulations or by unknown, non-managed background processes resulting from the non-dedication of shared resources. Due to the dynamic execution characteristics of elements that compose distributed simulation applications, the computational load and interaction dependencies of each simulation entity change during run-time. These dynamic changes lead to an irregular load and communication distribution, which increases overhead of resources and execution delays. A static partitioning of load is limited to deterministic applications and is incapable of predicting the dynamic changes caused by distributed applications or by external background processes. Due to the relevance in dynamically balancing load for distributed simulations, many balancing approaches have been proposed in order to offer a sub-optimal balancing solution, but they are limited to certain simulation aspects, specific to determined applications, or unaware of HLA-based simulation characteristics. Therefore, schemes for balancing the communication and computational load during the execution of distributed simulations are devised, adopting a hierarchical architecture. First, in order to enable the development of such balancing schemes, a migration technique is also employed to perform reliable and low-latency simulation load transfers. Then, a centralized balancing scheme is designed; this scheme employs local and cluster monitoring mechanisms in order to observe the distributed load changes and identify imbalances, and it uses load reallocation policies to determine a distribution of load and minimize imbalances. As a measure to overcome the drawbacks of this scheme, such as bottlenecks, overheads, global synchronization, and single point of failure, a distributed redistribution algorithm is designed. Extensions of the distributed balancing scheme are also developed to improve the detection of and the reaction to load imbalances. These extensions introduce communication delay detection, migration latency awareness, self-adaptation, and load oscillation prediction in the load redistribution algorithm. Such developed balancing systems successfully improved the use of shared resources and increased distributed simulations' performance.