Made available in DSpace on 2016-08-17T14:53:22Z (GMT). No. of bitstreams: 1 Dissertacao Allan James.pdf: 3170694 bytes, checksum: 054a9e74e81a7c2099800246d0b6c530 (MD5) Previous issue date: 2012-09-28 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The union of methodologies for optimal control and dynamics programming has stimulated the development of algorithms for realization of discrete control systems of the type linear quadratic regulator (DLQR). The methodology is based on reinforcement learning methods based on temporal differences and approximate dynamic programming. The proposed method combines the approach of the value function by method RLS (recursive least squares) and approximate policy iteration schemes heuristic dynamic programming (HDP). The approach is directed to the assessment of convergence of the solution DLQR and the heuristic weighting matrices 􀜳 and 􀜴 of the utility function associated with DLQR. The investigation of convergence properties related to consistency, persistent excitation and polarization of the RLS estimator is performed. The methodology involved in a project achievements online DLQR controllers and is evaluated in a fourth order multivariable dynamic system. / A união das metodologias de controle ótimo e de programação dinâmica tem impulsionado o desenvolvimento de algoritmos para realizações de sistemas de controle discreto do tipo regulador linear quadrático (DLQR). A metodologia utilizada neste trabalho é fundamentada sobre métodos de aprendizagem por reforço baseados em diferenças temporais e programação dinâmica aproximada. O método proposto combina a aproximação da função valor através do método RLS (mínimos quadrados recursivos) e iteração de política aproximada em esquemas de programação dinâmica heurística (HDP). A abordagem é orientada para a avaliação da convergência da solução DLQR e para a sintonia heurística das matrizes de ponderação 􀜳 e 􀜴da função de utilidade associada ao DLQR. É realizada a investigação das propriedades de convergência relacionadas à consistência, excitação persistente e polarização do estimador RLS. A metodologia contempla realizações de projetos de forma online de controladores DLQR e é avaliada em um sistema dinâmico multivariável de quarta ordem.

Made available in DSpace on 2016-08-17T14:53:28Z (GMT). No. of bitstreams: 1 Dissertacao Gustavo Araujo.pdf: 2606649 bytes, checksum: efb1a5ded768b058f25d23ee8967bd38 (MD5) Previous issue date: 2014-04-28 / In this work the main objective is to present the development of learning algorithms for online application for the solution of algebraic Hamilton-Jacobi-Bellman equation. The concepts covered are focused on developing the methodology for control systems, through techniques that aims to design online adaptive controllers to reject noise sensors, parametric variations and modeling errors. Concepts of neurodynamic programming and reinforcement learning are are discussed to design algorithms where the context of a given operating point causes the control system to adapt and thus present the performance according to specifications design. Are designed methods for online estimation of adaptive critic focusing efforts on techniques for gradient estimating of the environment value function. / Neste trabalho o principal objetivo é apresentar o desenvolvimento de algoritmos de aprendizagem para execução online para a solução da equação algébrica de Hamilton-Jacobi-Bellman. Os conceitos abordados se concentram no desenvolvimento da metodologia para sistemas de controle, por meio de técnicas que tem como objetivo o projeto online de controladores adaptativos são projetados para rejeitar ruídos de sensores, variações paramétricas e erros de modelagem. Conceitos de programação neurodinâmica e aprendizagem por reforço são abordados para desenvolver algoritmos onde a contextualização de determinado ponto de operação faz com que o sistema de controle se adapte e, dessa forma, apresente o desempenho de acordo com as especificações de projeto. Desenvolve-se métodos para a estimação online do crítico adaptativo concentrando os esforços em técnicas de estimação do gradiente da função valor do ambiente.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2016-07-01T11:43:52Z No. of bitstreams: 1 germandavidyagimoromisato.pdf: 4216499 bytes, checksum: a1b6dec404f94fd91a0a919755636775 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2016-07-13T16:00:06Z (GMT) No. of bitstreams: 1 germandavidyagimoromisato.pdf: 4216499 bytes, checksum: a1b6dec404f94fd91a0a919755636775 (MD5) / Made available in DSpace on 2016-07-13T16:00:06Z (GMT). No. of bitstreams: 1 germandavidyagimoromisato.pdf: 4216499 bytes, checksum: a1b6dec404f94fd91a0a919755636775 (MD5) Previous issue date: 2012-08-02 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este trabalho tem como objetivo apresentar uma nova metodologia baseada em Programação Dinâmica Dual Determinística (PDDD) para o cálculo da Energia Firme de sistemas energéticos. A Energia Firme tem uma relação direta com os certificados de energia garantida atribuídos às usinas hidráulicas, os quais representam o limite superior para os contratos de energia estabelecidos com os consumidores (distribuidores e consumidores livres). Neste contexto, este trabalho possui uma importância relevante para o cenário atual do Setor Elétrico Brasileiro (SEB). Os resultados são comparados com aqueles obtidos pela metodologia em vigor no SEB, o qual é baseado em métodos heurísticos. / The objective of this work is to introduce a new methodology based in The Deterministic Dual Dynamic Programming (DDDP) to calculate the firm energy of energetic systems. The firm energy is directly related to the guaranteed energy certificates assigned to hydraulic power plants. These energy certificates represent the limits of energy contracts that can be established with consumers (energy distributors and free consumers). In this context, this work has a relevant importance to the current scenario of the Brazilian Electric Sector (BES). The results are compared to those obtained by the BES approved computational model based in heuristic methods.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-03-20T13:40:45Z No. of bitstreams: 1 wellingtoncarlosdaconceicao.pdf: 4259949 bytes, checksum: 52410bbb422df8d4e80e7f6956efc71e (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-03-21T13:12:55Z (GMT) No. of bitstreams: 1 wellingtoncarlosdaconceicao.pdf: 4259949 bytes, checksum: 52410bbb422df8d4e80e7f6956efc71e (MD5) / Made available in DSpace on 2017-03-21T13:12:55Z (GMT). No. of bitstreams: 1 wellingtoncarlosdaconceicao.pdf: 4259949 bytes, checksum: 52410bbb422df8d4e80e7f6956efc71e (MD5) Previous issue date: 2016-12-12 / O sistema de produção de energia elétrica brasileiro é um sistema hidrotérmico de grande porte com forte predominância de usinas hidrelétricas. O planejamento e operação do sistema é realizado considerando diversos fatores, tais como, estocasticidade das afluências, usinas hidrelétricas em cascata e acoplamento temporal da operação. A resolução deste tipodeproblemaéfeitaconsiderandodiversoshorizontesdeplanejamento. Oplanejamento da operação de médio prazo compreende um período de 5 anos de estudo, e este período é discretizado em base mensal. O presente trabalho apresenta uma metodologia alternativa para resolução do problema de planejamento da operação de médio prazo de sistemas hidrotérmicos utilizando a Programação Dinâmica Estocástica (PDE) com discretização dointercâmbiodeenergiaentreossubsistemas(PDE-INT).Alémdisso, utiliza-seatécnica de sistemas equivalentes de energia e o algoritmo de fechos convexos (convex hull) para obtenção da função de custo futuro a partir dos pontos obtidos pela PDE-INT. Nesta abordagem, para cálculo da política energética, os subsistemas são considerados isolados, e desta forma, as variáveis que compõem o espaço de estados que são discretizadas são a energia armazenada e o intercâmbio líquido entre os subsistemas. Inicialmente, para análise e avaliação da metodologia proposta na resolução do problema de planejamento hidrotérmico, criou-se um sistema tutorial, composto por dois subsistemas. Em seguida, a metodologia foi utilizada considerando todo o sistema elétrico brasileiro, representado por quatro subsistemas ou submercados. Os resultados mostraram que com a técnica de separação dos subsistemas há uma redução significativa no tempo computacional quando comparados com as técnicas tradicionais que utilizam programação dinâmica. Desta forma, a metodologia proposta pode ser utilizada para uma análise rápida e inicial do caso em estudo, servindo como base para estudos e refinamentos posteriores. / The Brazilian power production system is a large scale hydrothermal system with a strong predominance of hydroelectric power plants. The electric power system operation planning must take into consideration several factors, such as uncertainty of the water inflows, hydroelectric plants in cascade and temporal coupling. This problem is solved considering different planning horizon. The long-term operation planning problem is generally solved by a chain of computational models that consider a period of 5 years ahead with monthly discretization. This work presents an alternative strategy to solve hydrothermalsystemsoperationplanningbyStochasticDynamicProgramming(SDP)with discretization of energy interchange between subsystems (SDP-INT). Under the presented approach, the hydroelectric plants are grouped into energy equivalent subsystems and the expected operation cost functions are modeled by a piecewise linear approximation, by means of the convex hull algorithm. Also, under this methodology, the subsystems are solved isolated, but the net energy interchange (export – import) between subsystems is set as a state variable of the cost function, together with the energy storage Initially, for the analysis and evaluation of the proposed methodology applied on solving the hydrothermalplanningproblem, themethodologyisusedinatutorialsystem, composedof two subsystems. Next, a simulation with the whole Brazilian electrical system considering four subsystems is presented. The results have shown that this subsystems separation technique reduces significantly the computation time when compared with the traditional techniques, demonstrating the effectiveness of the proposed methodology. Thus, the proposed methodology can be used for a fast and initial analysis of the case study, serving as a basis for further studies.

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2018-05-10T12:15:28Z No. of bitstreams: 1 alexandredasilvafernandes.pdf: 3326554 bytes, checksum: f4dfcfe70bde99c5ebe4501f03add83e (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2018-05-22T15:33:53Z (GMT) No. of bitstreams: 1 alexandredasilvafernandes.pdf: 3326554 bytes, checksum: f4dfcfe70bde99c5ebe4501f03add83e (MD5) / Made available in DSpace on 2018-05-22T15:33:53Z (GMT). No. of bitstreams: 1 alexandredasilvafernandes.pdf: 3326554 bytes, checksum: f4dfcfe70bde99c5ebe4501f03add83e (MD5) Previous issue date: 2018-02-20 / O planejamento da operação do Sistema Interligado Nacional constitui-se uma tarefa de alta complexidade, seja pela quantidade acentuada de usinas hidrelétricas e termelétricas distribuídas nos quatro submercados interligados, ou pelas características marcantes da operação das hidrelétricas, no que diz respeito às incertezas dos cenários hidrológicos futuros e aos acoplamentos espacial e temporal. O objetivo deste planejamento é a determinação de uma política ótima de despacho das usinas do sistema de modo a minimizar o valor esperado dos custos operativos no horizonte considerado. Uma importante restrição do problema é o suprimento da demanda de energia elétrica, dado pela diferença entre a carga efetiva de cada submercado e a geração das usinas não simuladas, esta última composta pela energias alternativas (eólica, solar, biomassa), pequenas centrais hidrelétricas, entre outros. Entretanto, a crescente penetração da geração renovável, aliada às incertezas das fontes naturais como eólica e solar (pois dependem de fatores climáticos e por isso são imprevisíveis), contribui com a necessidade de representação da demanda em diversos cenários para um correto despacho das usinas e uma operação do sistema mais confiável. Sabendo que os modelos oficiais atuais tratam apenas as incertezas oriundas dos cenários hidrológicos, devido à dificuldade de implementação e alocação de memória na consideração de outras incertezas na Programação Dinâmica Dual Estocástica, o trabalho desenvolvido nesta dissertação propõe metodologias que incluem os diversos cenários de demanda, além de representar com maior detalhe a geração das hidrelétricas. Além disso, são propostos algoritmos de representação analítica da Função de Custo Imediato em sistemas isolados e com múltiplas áreas na busca por uma redução das dimensões do problema tratado. Finalmente, são realizados testes em sistemas tutorias e os resultados são analisados para avaliar as performances computacionais das metodologias propostas. / The operation schedulling of Brazilian System constitutes a task of high complexity, either due to the large number of hydro and thermal plants distributed in the four interconnected submarkets, or due to the outstanding characteristics of the hydro plants, with respect to the uncertainties in the hydrological scenarios future and due to spatial and temporal couplings. The objective of this planning is the determination of an optimal dispatch policy of plants that minimizes the expected value of the operating costs in the considered horizon. An important constraint is the supply of demand, which is obtained by the difference between the effective load of each submarket and the generation of non-simulated plants, composed of renewable energies (wind, solar, biomass), small hydropower plants, and others. However, the growing penetration of renewable generation, coupled with the uncertainties of natural sources such as wind and solar (because they depend on climatic factors and are therefore unpredictable), contributes to the need to represent demand in different scenarios for a correct dispatch of the plants and a more reliable system operation. Knowing that the current official models deal only with the uncertainties arising from the hydrological scenarios, due to the difficulty of implementation and memory allocation in the consideration of other uncertainties in Stochastic Dual Dynamic Programming, this work proposes methodologies that include the several scenarios demand, besides representing in greater detail the generation of hydroelectric plants. In addition, algorithms are proposed for analytical representation of the Immediate Cost Function in isolated systems with multiple areas in the search for a reduction of the dimensions of the problem. Finally, tests are performed on tutorial systems and the results are analyzed to evaluate the computational performances of the proposed methodologies.

Dans les régions semi-arides, les systèmes de production agricole dépendent fortement de l'irrigation et font face à des difficultés croissantes (épuisement des ressources naturelles, forte volatilité des prix du marché, hausse des coûts de l'énergie, incertitude sur les changements climatiques). Modéliser ces systèmes agricoles et la façon dont ils s'adaptent est important pour les décideurs politiques afin de mieux évaluer leur flexibilité et leur résilience. Pour comprendre la capacité des systèmes agricoles à s'adapter, il est essentiel de considérer l'ensemble du processus de décision : des décisions sur le long-terme à l'échelle de l'exploitation aux décisions de court-terme à l'échelle de la parcelle. Pour ce faire, cette thèse conçoit un système de production agricole adaptable dans un contexte de diminution de l'eau et de changement climatique. Elle fournit une méthodologie guidant l'acquisition de données, leur analyse et la conception de modèle. Elle présente le modèle de simulation NAMASTE représentant les décisions des agriculteurs, les interactions entre agriculteurs pour l'utilisation des ressources communes et met l'accent sur la rétroaction entre pratiques agricoles et évolution de la nappe phréatique. Le modèle a été initialement développé pour résoudre les problèmes critiques de baisse des eaux souterraines liés aux pratiques agricoles dans un bassin versant du sud-ouest de l'Inde. Sa structure, ses cadres conceptuels et ses formalismes peuvent être utilisés dans d'autres contextes agricoles. / In semi-arid regions, agricultural production systems depend greatly on irrigation and encounter increasing challenges (depletion of natural resources, high volatility in market prices, rise in energy costs, growing uncertainty about climate change). Modeling farming systems and how these systems change and adapt to these challenges is particularly interesting for policy makers to better assess their flexibility and resiliency. To understand the ability of farming systems to adapt, it is essential to consider the entire decision-making process: from long-term decisions at the farm scale to short-term decisions at the plot level. To this end, the thesis conceives a flexible and resilient agricultural production system under a context of water scarcity and climate change. It provides a step-by-step methodology that guides data acquisition and analysis and model design. It proposes a simulation model NAMASTE that simulates the farmers' decisions in different time and space scales, represents the interactions between farmers for resource uses and emphasizes the feedback and retroaction between farming practices and changes in the water table. The model was initially developed to address critical issues of groundwater depletion and farming practices in a watershed in southwestern India. Its structure, frameworks and formalisms can be used in other agricultural contexts.

La plupart des travaux de recherches sur les problèmes d'ordonnancement traitent le cas des ressources renouvelables, c'est-à-dire des ressources qui sont exigées en début d'exécution de chaque tâche et sont restituées en fin d'exécution. Peu d'entre eux abordent les problèmes à ressources consommables, c'est-à-dire des ressources non restituées en fin d'exécution. Le problème de gestion de projet à contraintes de ressources (RCPSP) est le problème à ressources renouvelables le plus traité dans la littérature. Dans le cadre de cette thèse, nous nous sommes intéressés à une généralisation du problème RCPSP qui correspond au cas où les tâches sont remplacées par des événements liés par des relations de précédence étendues. Chaque événement peut produire ou consommer une quantité de ressources à sa date d'occurrence et la fonction économique reste la durée totale à minimiser. Nous avons nommé cette généralisation ERCPSP (Extended RCPSP). Nous avons élaboré des modèles de programmation linéaire pour résoudre ce problème. Nous avons proposé plusieurs bornes inférieures algorithmiques exploitant les travaux de la littérature sur les problèmes cumulatifs. Ensuite, nous avons élargi la portée des méthodes utilisées pour la mise en place de méthodes de séparation et évaluation. Nous avons traité aussi des cas particuliers par des méthodes basées sur la programmation dynamique. / This thesis investigates the Extended Resource Constrained Project Scheduling Problem (ERCPSP). ERCPSP is a general scheduling problem where the availability of a resource is depleted and replenished at the occurrence times of a set of events. It is an extension of the Resource Constrained Project Scheduling Problem (RCPSP) where activities are replaced by events, which have to be scheduled subject to generalized precedence relations. We are interested in this thesis in proposing new methodologies and approaches to solve ERCPSP. First, we study some polynomial cases of this problem and we propose a dynamic programming algorithm to solve the parallel chain case. Then, we propose lower bounds, mixed integer programming models, and a branch-and-bound method to solve ERCPSP. Finally, we develop an instance generator dedicated to this problem.

Avec l’avènement des dispositifs nomades tels que les smartphones et les tablettes, la reconnaissance automatique de l’écriture manuscrite cursive à partir d’un signal en ligne est devenue durant les dernières décennies un besoin réel de la vie quotidienne à l’ère numérique. Dans le cadre de cette thèse, nous proposons de nouvelles stratégies pour un système de reconnaissance de mots manuscrits en-ligne. Ce système se base sur une méthode collaborative segmentation/reconnaissance et en utilisant des analyses à deux niveaux : caractère et bi-caractères. Plus précisément, notre système repose sur une segmentation de mots manuscrits en graphèmes afin de créer un treillis à L niveaux. Chaque noeud de ce treillis est considéré comme un caractère potentiel envoyé à un moteur de Reconnaissance de Caractères Isolés (RCI) basé sur un SVM. Pour chaque noeud, ce dernier renvoie une liste de caractères associés à une liste d’estimations de probabilités de reconnaissance. Du fait de la grande diversité des informations résultant de la segmentation en graphèmes, en particulier à cause de la présence de morceaux de caractères et de ligatures, l’injection de chacun des noeuds du treillis dans le RCI engendre de potentielles ambiguïtés au niveau du caractère. Nous proposons de lever ces ambiguïtés en utilisant des modèles de bi-caractères, basés sur une régression logistique dont l’objectif est de vérifier la cohérence des informations à un niveau de reconnaissance plus élevé. Finalement, les résultats renvoyés par le RCI et l’analyse des modèles de bi-caractères sont utilisés dans la phase de décodage pour parcourir le treillis dans le but de trouver le chemin optimal associé à chaque mot dans le lexique. Deux méthodes de décodage sont proposées (recherche heuristique et programmation dynamique), la plus efficace étant basée sur de la programmation dynamique. / With the advent of mobile devices such as tablets and smartphones over the last decades, on-line handwriting recognition has become a very highly demanded service for daily life activities and professional applications. This thesis presents a new approach for on-line handwriting recognition. This approach is based on explicit segmentation/recognition integrated in a two level analysis system: character and bi-character. More specifically, our system segments a handwritten word in a sequence of graphemes to be then used to create a L-levels lattice of graphemes. Each node of the lattice is considered as a character to be submitted to a SVM based Isolated Character Recognizer (ICR). The ICR returns a list of potential character candidates, each of which is associated with an estimated recognition probability. However, each node of the lattice is a combination of various segmented graphemes. As a consequence, a node may contain some ambiguous information that cannot be handled by the ICR at character level analysis. We propose to solve this problem using "bi-character" models based on Logistic Regression, in order to verify the consistency of the information at a higher level of analysis. Finally, the recognition results provided by the ICR and the bi-character models are used in the word decoding stage, whose role is to find the optimal path in the lattice associated to each word in the lexicon. Two methods are presented for word decoding (heuristic search and dynamic programming), and dynamic programming is found to be the most effective.

Dans les maisons et bâtiments intelligents, il devient nécessaire de limiter l'intervention humaine sur le système énergétique, afin de fluctuer automatiquement l'énergie consommée par les appareils consommateurs. Pour cela, un système de mesure de la consommation électrique d'équipements est aussi nécessaire et peut être déployé de deux façons : intrusive ou non-intrusive. La première solution consiste à relever la consommation de chaque appareil, ce qui est inenvisageable à une grande échelle pour des raisons pratiques liées à l'entretien et aux coûts. Donc, la solution non-intrusive (NILM pour Non-Intrusive Load Monitoring), qui est capable d'identifier les différents appareils en se basant sur les signatures extraites d'une consommation globale, est plus prometteuse. Le problème le plus difficile des algorithmes NILM est comment discriminer les appareils qui ont la même caractéristique énergétique. Pour surmonter ce problème, dans cette thèse, nous proposons d'utiliser une information externe pour améliorer la performance des algorithmes existants. Les premières informations additionnelles proposées considèrent l'état précédent de chaque appareil comme la probabilité de transition d'état ou la distance de Hamming entre l'état courant et l'état précédent. Ces informations sont utilisées pour sélectionner l'ensemble le plus approprié des dispositifs actifs parmi toutes les combinaisons possibles. Nous résolvons ce problème de minimisation en norme l1 par un algorithme d'exploration exhaustive. Nous proposons également d'utiliser une autre information externe qui est la probabilité de fonctionnement de chaque appareil fournie par un réseau de capteurs sans fil (WSN pour Wireless Sensor Network) déployé dans le bâtiment. Ce système baptisé SmartSense, est différent de la solution intrusive car seul un sous-ensemble de tous les dispositifs est surveillé par les capteurs, ce qui rend le système moins intrusif. Trois approches sont appliquées dans le système SmartSense. La première approche applique une détection de changements de niveau sur le signal global de puissance consommé et les compare avec ceux existants pour identifier les dispositifs correspondants. La deuxième approche vise à résoudre le problème de minimisation en norme l1 avec les algorithmes heuristiques de composition Paréto-algébrique et de programmation dynamique. Les résultats de simulation montrent que la performance des algorithmes proposés augmente significativement avec la probabilité d'opération des dispositifs surveillés par le WSN. Comme il n'y a qu'un sous-ensemble de tous les appareils qui sont surveillés par les capteurs, ceux qui sont sélectionnés doivent satisfaire quelques critères tels qu'un taux d'utilisation élevé ou des confusions dans les signatures sélectionnées avec celles des autres. / In smart homes, human intervention in the energy system needs to be eliminated as much as possible and an energy management system is required to automatically fluctuate the power consumption of the electrical devices. To design such system, a load monitoring system is necessary to be deployed in two ways: intrusive or non-intrusive. The intrusive approach requires a high deployment cost and too much technical intervention in the power supply. Therefore, the Non-Intrusive Load Monitoring (NILM) approach, in which the operation of a device can be detected based on the features extracted from the aggregate power consumption, is more promising. The difficulty of any NILM algorithm is the ambiguity among the devices with the same power characteristics. To overcome this challenge, in this thesis, we propose to use an external information to improve the performance of the existing NILM algorithms. The first proposed additional features relate to the previous state of each device such as state transition probability or the Hamming distance between the current state and the previous state. They are used to select the most suitable set of operating devices among all possible combinations when solving the l1-norm minimization problem of NILM by a brute force algorithm. Besides, we also propose to use another external feature that is the operating probability of each device provided by an additional Wireless Sensor Network (WSN). Different from the intrusive load monitoring, in this so-called SmartSense system, only a subset of all devices is monitored by the sensors, which makes the system quite less intrusive. Two approaches are applied in the SmartSense system. The first approach applies an edge detector to detect the step-changes on the power signal and then compare with the existing library to identify the corresponding devices. Meanwhile, the second approach tries to solve the l1-norm minimization problem in NILM with a compositional Pareto-algebraic heuristic and dynamic programming algorithms. The simulation results show that the performance of the proposed algorithms is significantly improved with the operating probability of the monitored devices provided by the WSN. Because only part of the devices are monitored, the selected ones must satisfy some criteria including high using rate and more confusions on the selected patterns with the others.

Abstract This thesis deals with the pump schedule optimisation of regional water distribution systems. The aims and the possible applications of the presented methods differ from each other; all of them are intended to solve a particular but realistic problem. The developed techniques use the capacity of the water reservoirs in order to find the optimal pump-schedule of the system. The optimisation task is always deterministic and discrete in time; the stochastic behaviour of the water consumptions is approximated by expected values. A so-called neutral genetic algorithm equipped with new constraint handling is presented first. The method is able to solve the scheduling problems of real-size and complex networks, e.g. the network of Budapest with coupled hydraulic simulations where both variable and fixed speed pumps are in the network. The results are compared to other ones obtained by widely used genetic algorithms and state-of-the-art general purpose optimisation solvers. A dynamic programming based method was also carried out which provides the global optimum of the so-called ’combinatorial’ pump scheduling problems. This modelling type is very common in the industry, which can be used if the operation points of the pumps take discrete values. The basic idea of the method is exploiting the ’permutational invariance’ of the model which results in a perfect discretisation of the state space without any loss of information. An approximate dynamic programming technique is also presented which solves the same type of problems as the formerly mentioned genetic algorithm does. The technique splits the water network model into smaller units, namely into the so-called well fields and the main distribution system. The state space of the main distribution system was further decreased while the quality of the results does not decay. A part of the test examples is the same as in the case of the former presented genetic algorithm; thus, the two methods can be compared. Finally, a small water network fed by a single variable speed pump was investigated. The presented methods are based on the minimisation of the specific energy consumption. The gained results are compared to ones obtained using a high-resolution discrete dynamic program. Novel optimisation techniques for water distribution network pump scheduling were developed in this work. A particular focus was put on the dynamics between pumping, water reservoirs, and water use. The work shows the applicability of the approach via numerous realistic simulation case studies. / Tiivistelmä Työ käsittelee alueellisten vedenjakelujärjestelmien pumppauksen aikataulutuksen optimointia. Esitettyjen menetelmien tavoitteet ja mahdolliset sovellukset poikkeavat toisistaan. Kaikki on kuitenkin tarkoitettu tiettyjen todellisten ongelmien ratkaisemiseen. Kehitetyt tekniikat käyttävät vesivarastojen kapasiteettia optimaalisen pumppausohjelman löytämiseksi. Jokainen optimointitehtävä on aikadiskreetti ja deterministinen, vedenkulutuksen stokastista käyttäytymistä on approksimoitu odotusarvoilla. Ensimmäiseksi työssä esitetään ns. neutraaleja geneettisiä algoritmeja varustettuna rajoitusten käsittelyllä. Menetelmällä voidaan ratkaista skedulointiohjelmia reaalimittakaavaisille ja monimutkaisille verkostoille (esim. Budapestin verkosto varustettuna hydraulisilla simuloinneilla, sekä muuttuvanopeuksisilla että vakionopeuksisilla verkoston pumpuilla). Tuloksia verrataan toisiin yleisesti käytössä olevilla geneettisillä algoritmeilla saatuihin, sekä johtavilla yleiskäyttöisillä optimointitekniikoilla saatuihin tuloksiin. Työssä käytettiin myös dynaamiseen ohjelmointiin pohjaavaa menetelmää, jolla saadaan globaali optimi ns. "kombinatoorisille" pumppauksen aikataulutusongelmille. Tällainen mallinnustapa on hyvin yleistä teollisuudessa. Sitä voidaan käyttää, jos pumppujen toimintapisteet saavat diskreettejä arvoja. Menetelmän perusajatuksena on "permutationaalisen invarianssin" hyväksikäyttäminen, josta seuraa tila-avaruuden virheetön diskretointi ilman informaation häviämistä. Työssä esitellään myös approksimoidun dynaamisen ohjelmoinnin tekniikka, jonka avulla voidaan ratkaista samantyyppisiä ongelmia kuin yllämainituilla geneettisillä algoritmeilla. Tämä tekniikka jakaa vesijohtoverkoston mallin pienempiin yksiköihin: lähdekenttiin ja pääjakeluverkostoon. Pääjakeluverkoston tila-avaruutta voitiin edelleen pienentää ilman, että tulosten laatu heikkeni. Osa käsitellyistä esimerkkitapauksista on samoja kuin edellämainittujen geneettisten algoritmien osalla, joten tuloksia voidaan verrata. Lopuksi tutkittiin pienen muuttuvanopeuksisella pumpulla syötetyn vesijohtoverkoston toimintaa. Esitetyt menetelmät perustuvat ominaisenergiankulutuksen minimointiin. Saatuja tuloksia verrataan korkearesoluutioisella diskreetillä dynaamisella ohjelmoinnilla saatuihin tuloksiin. Työssä kehitettiin uusia optimointitekniikoita vedenjakelujärjestelmien pumppauksen aikataulutuksen optimintiin. Erityisesti työssä keskityttiin pumppauksen, vesitornien ja kuluttajien käyttäytymisen väliseen dynamiikkaan. Työssä osoitettiin tekniikoiden toimivuus realististen esimerkkisimulointien avulla. / Kivonat Jelen doktori disszertáció regionális ivóvízellátó-hálózatok üzemvitel-optimalizációjával foglalkozik. A bemutatott módszerek alkalmazhatósági köre rendszerint eltér egymástól, mindegyik egy-egy speciális, de a való életben is előforduló problémára kíván megoldást nyújtani. A kidolgozott módszerek a medencék tárolókapacitását kihasználva, az optimális szivattyú-menetrendet keresve kívánják megtalálni az adott vízműhálózat üzemviteloptimumát. Az optimalizáció egy időben diszkrét, ugyanakkor determinisztikus feladat megoldását igényli, a vízfogyasztások sztochasztikus viselkedését a várható értékekkel közelítettem. Elsőként egy új mellékfeltétel-kezeléssel ellátott, ún. neutrális genetikus algoritmus bemutatása a cél. A kidolgozott módszer alkalmas nagy, valós méretű (pl. Budapest) és bonyolultságú (kapcsolt hidraulikai szimulációk, frekvenciaváltós és direkt szivattyúk a hálózatban) ivóvízhálózatok napi üzemvitel optimalizálására. Az eredményeket más genetikus algoritmusokkal és a világ élvonalába tartozó, de általános célú optimalizációs módszerekkel hasonlítottam össze. Kidolgozásra került egy dinamikus programozás alapú, a valós, globális optimumot adó módszer is. Az algoritmus a gyakorlatban elterjedt, ún. "kombinációs" hálózatként modellezhető vízműhálózat típusokra alkalmazható, ahol a szivattyúk munkapontjai diszkrét értékek. A megoldás alapját az ún. "permutációs invariancia" jelensége adja, mely lehetővé teszi az állapottér információveszteség nélküli, tökéletes diszkretizációját. Egy, a korábban bemutatott genetikus algoritmuséhoz hasonló problémakört megoldó, de közelítő dinamikus programozás alapú módszer is bemutatásra kerül. Az algoritmus a hálózat kisebb részegységekre (víztermelő területekre és fő elosztó hálózatra) való felbontásával és a fő elosztó hálózat állapotterének önkényes, de a megoldás jóságán jelentősen nem rontó csökkentésével éri el a program futtatásához szükséges számítási igény csökkentését. A tesztfeladatok egy része megegyezik a genetikus algoritmus tesztfeladataival, így azok közvetlenül összehasonlíthatóak. Végül bemutatásra kerül egy kisméretű, mindössze egy darab változtatható fordulat- számú szivattyúval táplált rendszer energetikai vizsgálata. Az itt bemutatott módszerek mind a fajlagos energiafelhasználás minimalizálásán alapulnak. Az eredményeket egy nagyfelbontású dinamikus programozás alapú módszerhez hasonlítottam.