Le contrôle hétérarchique des systèmes de production flexibles (FMS) préconise un contrôle peu complexe et hautement réactif supporté par des entités décisionnelles locales (DEs). En dépit d'avancées prometteuses, ces architectures présentent un comportement myope car les DEs ont une visibilité informationnelle limitée sue les autres DEs, ce qui rend difficile la garantie d'une performance globale minimum. Cette thèse se concentre sur les approches permettant de réduire cette myopie. D'abord, une définition et une typologie de cette myopie dans les FMS sont proposées. Ensuite, nous proposons de traiter explicitement le comportement myope avec une architecture semi-hétérarchique. Dans celle-ci, une entité décisionnelle globale (GDE) traite différents types de décisions myopes à l'aide des différentes techniques d'optimisation basée sur la simulation (SbO). De plus, les SbO peuvent adopter plusieurs rôles, permettant de réduire le comportement myope de plusieurs façons. Il est également possible d'avoir plusieurs niveaux d'autonomie en appliquant différents modes d'interaction. Ainsi, notre approche accepte des configurations dans lesquelles certains comportements myopes sont réduits et d'autres sont acceptés. Notre approche a été instanciée pour contrôler la cellule flexible AIP- PRIMECA de l'Université de Valenciennes. Les résultats des simulations ont montré que l'architecture proposée peut réduire les comportements myopes en établissant un équilibre entre la réactivité et la performance globale. Des expérimentations réelles ont été réalisées sur la cellule AIP-PRIMECA pour des scenarios dynamiques et des résultats prometteurs ont été obtenus. / Heterarchical-based control for flexible manufacturing systems (FMS) localizes control capabilities in decisional entities (DE), resulting in highly reactive and low complex control architectures. However, these architectures present myopic behavior since DEs have limited visibility of other DEs and their behavior, making difficult to ensure certain global performance. This dissertation focuses on reducing myopic behavior. At first, a definition and a typology of myopic behavior in FMS is proposed. In this thesis, myopic behavior is dealt explicitly so global performance can be improved. Thus, we propose a semi-heterarchical architecture in which a global decisional entity (GDE) deals with different kinds of myopic decisions using simulation-based optimization (SbOs). Different optimization techniques can be used so myopic decisions can be dealt individually, favoring GDE modularity. Then, the SbOs can adopt different roles, being possible to reduce myopic behavior in different ways. More, it is also possible to grant local decisional entities with different autonomy levels by applying different interaction modes. In order to balance reactivity and global performance, our approach accepts configurations in which some myopic behaviors are reduced and others are accepted. Our approach was instantiated to control the assembly cell at Valenciennes AIPPRIMECA center. Simulation results showed that the proposed architecture reduces myopic behavior whereby it strikes a balance between reactivity and global performance. The real implementation on the assembly cell verified the effectiveness of our approach under realistic dynamic scenarios, and promising results were obtained.

The objective of reservoir management is to maximize a key performance indicator (net present value in this study) at a minimum cost. A typical approach includes engineering analysis, followed by the economic value of the technical study. In general, operators are inclined to spend more effort on the engineering side to the detriment of the economic area, leading to unbalanced and occasionally suboptimal results. Moreover, most of the optimization methods used for production scheduling focus on a given recovery phase, or medium-term strategy, as opposed to an integrated solution that allocates resources from discovery to field abandonment. This thesis addresses the optimization of a reservoir under both technical and economic constraints. In particular, the method presented introduces a life cycle maximization approach to establish the best exploitation strategy throughout the life of the project. Deterministic studies are combined with stochastic modeling and risk analysis to assess decision making under uncertainty. To demonstrate the validity of the model, this document offers two case studies and the optimal times associated with each recovery phase. In contrast with traditional depletion strategies, where the optimization is done myopically by maximizing the net present value at each recovery phase, our results suggest that time is dramatically reduced when the net present value is optimized globally by maximizing the NPV for the life of the project. Furthermore, the sensitivity analysis proves that the original oil in place and non-engineering parameters such as the price of oil are the most influential variables. The case studies clearly show the greater economic efficiency of this life cycle approach, confirming the potential of this optimization technique for practical reservoir management. / text

In the thesis, we address the fundamental problem of opportunistic spectrum access in a multi-channel communication system. Specifically, we consider a communication system in which a user has access to multiple channels, but is limited to sensing and transmitting only on one at a given time. We explore how the smart user should exploit past observations and the knowledge of the stochastic properties of these channels to maximize its transmission rate by switching channels opportunistically. Formally, we provide a generic analysis on the opportunistic spectrum access problem by casting the problem into the restless multi-armed bandit (RMAB) problem, one of the most well-known generalizations of the classic multi-armed bandit (MAB) problem, which is of fundamental importance in stochastic decision theory. Despite the significant research efforts in the field, the RMAB problem in its generic form still remains open. Until today, very little result is reported on the structure of the optimal policy. Obtaining the optimal policy for a general RMAB problem is often intractable due to the exponential computation complexity. Hence, a natural alternative is to seek a simple myopic policy maximizing the short-term reward. Therefore, we develop three axioms characterizing a family of functions which we refer to as regular functions, which are generic and practically important. We then establish the optimality of the myopic policy when the reward function can be expressed as a regular function and the discount factor is bounded by a closed-form threshold determined by the reward function. We also illustrate how the derived results, generic in nature, are applied to analyze a class of RMAB problems arising from multi-channel opportunistic access. Next, we further investigate the more challenging problem where the user has to decide the number of channels to sense in each slot in order to maximize its utility (e.g., throughput). After showing the exponential complexity of the problem, we develop a heuristic v-step look-ahead strategy. In the developed strategy, the parameter v allows to achieve a desired tradeoff between social efficiency and computation complexity. We demonstrate the benefits of the proposed strategy via numerical experiments on several typical settings.

No description available.

Shipment Consolidation (SCL) is a logistics strategy that combines two or more orders or shipments so that a larger quantity can be dispatched on the same vehicle to the same market region. This dissertation aims to emphasize the importance and substantial cost saving opportunities that come with SCL in a logistics supply chain, by offering new models or by improving on the current body of literature. Our research revolves around "three main axes" in SCL: Single-Item Shipment Consolidation (SISCL), Multi-Item Shipment Consolidation (MISCL), and Pricing and Shipment Consolidation. We investigate those topics by employing various Operations Research concepts or techniques such as renewal theory, dynamic optimization, and simulation. In SISCL, we focus on analytical models, when the orders arrive randomly. First, we examine the conditions under which an SCL program enables positive savings. Then, in addition to the current SCL policies used in practice and studied in the literature, i.e. Quantity-Policy (Q-P), Time-Policy (T-P) and Hybrid Policy (H-P), we introduce a new one that we call the Controlled Dispatch Policy (CD-P). Moreover, we provide a cost-based comparison of those policies. We show that the Q-P yields the lowest cost per order amongst the others, yet with the highest randomness in dispatch times. On the other hand, we also show that, between the service-level dependent policies (i.e. the CD-P, H-P and T-P), H-P provides the lowest cost per order, while CD-P turns out to be more flexible and responsive to dispatch times, again with a lower cost than the T-P. In MISCL, we construct dispatch decision rules. We employ a myopic analysis, and show that it is optimal, when costs and the order-arrival processes are dependent on the type of items. In a dynamic setting, we apply the concept of time-varying probability to integrate the dispatching and load planning decisions. For the most common dispatch objectives such as cost per order, cost per unit time or cost per unit weight, we use simulation and observe that the variabilities in both cost and the optimal consolidation cycle are smaller for the objective of cost per unit weight. Finally on our third axis, we study the joint optimization of pricing and time-based SCL policy. We do this for a price- and time-sensitive logistics market, both for common carriage (transport by a public, for-hire trucking company) and private carriage (employing one's own fleet of trucks). The main motivation for introducing pricing in SCL decisions stems from the fact that transportation is a service, and naturally demand is affected by price. Suitable pricing decisions may influence the order-arrival rates, enabling extra savings. Those savings emanate from two sources: Scale economies (in private carriage) or discount economies (in common carriage) that come with SCL, and additional revenue generated by employing an appropriate pricing scheme. Throughout the dissertation, we offer numerical examples and as many managerial insights as possible. Suggestions for future research are offered.

Shipment Consolidation (SCL) is a logistics strategy that combines two or more orders or shipments so that a larger quantity can be dispatched on the same vehicle to the same market region. This dissertation aims to emphasize the importance and substantial cost saving opportunities that come with SCL in a logistics supply chain, by offering new models or by improving on the current body of literature. Our research revolves around "three main axes" in SCL: Single-Item Shipment Consolidation (SISCL), Multi-Item Shipment Consolidation (MISCL), and Pricing and Shipment Consolidation. We investigate those topics by employing various Operations Research concepts or techniques such as renewal theory, dynamic optimization, and simulation. In SISCL, we focus on analytical models, when the orders arrive randomly. First, we examine the conditions under which an SCL program enables positive savings. Then, in addition to the current SCL policies used in practice and studied in the literature, i.e. Quantity-Policy (Q-P), Time-Policy (T-P) and Hybrid Policy (H-P), we introduce a new one that we call the Controlled Dispatch Policy (CD-P). Moreover, we provide a cost-based comparison of those policies. We show that the Q-P yields the lowest cost per order amongst the others, yet with the highest randomness in dispatch times. On the other hand, we also show that, between the service-level dependent policies (i.e. the CD-P, H-P and T-P), H-P provides the lowest cost per order, while CD-P turns out to be more flexible and responsive to dispatch times, again with a lower cost than the T-P. In MISCL, we construct dispatch decision rules. We employ a myopic analysis, and show that it is optimal, when costs and the order-arrival processes are dependent on the type of items. In a dynamic setting, we apply the concept of time-varying probability to integrate the dispatching and load planning decisions. For the most common dispatch objectives such as cost per order, cost per unit time or cost per unit weight, we use simulation and observe that the variabilities in both cost and the optimal consolidation cycle are smaller for the objective of cost per unit weight. Finally on our third axis, we study the joint optimization of pricing and time-based SCL policy. We do this for a price- and time-sensitive logistics market, both for common carriage (transport by a public, for-hire trucking company) and private carriage (employing one's own fleet of trucks). The main motivation for introducing pricing in SCL decisions stems from the fact that transportation is a service, and naturally demand is affected by price. Suitable pricing decisions may influence the order-arrival rates, enabling extra savings. Those savings emanate from two sources: Scale economies (in private carriage) or discount economies (in common carriage) that come with SCL, and additional revenue generated by employing an appropriate pricing scheme. Throughout the dissertation, we offer numerical examples and as many managerial insights as possible. Suggestions for future research are offered.

Dans cette thèse, nous abordons le problème fondamental de l'accès au spectre opportuniste dans un système de communication multi-canal. Plus précisément, nous considérons un système de communication dans lequel un utilisateur a accès à de multiples canaux, tout en étant limité à la détection et la transmission sur un sous-ensemble de canaux. Nous explorons comment l'utilisateur intelligent exploite ses observations passées et les propriétés stochastiques de ces canaux afin de maximiser son débit. Formellement, nous fournissons une analyse générique sur le problème d'accès au spectre opportuniste en nous basant sur le problème de `restless multi-bandit’ (RMAB), l'une des généralisations les plus connues du problème classique de multi-armed bandit (MAB), un problème fondamental dans la théorie de décision stochastique. Malgré les importants efforts de la communauté de recherche dans ce domaine, le problème RMAB dans sa forme générique reste encore ouvert. Jusqu'à aujourd'hui, très peu de résultats sont connus sur la structure de la politique optimale. L'obtention de la politique optimale pour un problème RMAB général est intraçable dû la complexité de calcul exponentiel. Par conséquent, une alternative naturelle est de se focaliser sur la politique myopique qui maximise la récompense à immédiate, tout en ignorant celles du futur. Donc, nous développons trois axiomes caractérisant une famille de fonctions que nous appelons fonctions régulières, qui sont génériques et pratiquement importantes. Nous établissons ensuite l'optimalité de la politique myopique lorsque la fonction de récompense peut être exprimée comme une fonction régulière et le facteur de discount est borné par un seuil déterminé par la fonction de récompense. Nous illustrons également l'application des résultats pour analyser une classe de problèmes RMAB dans l'accès opportuniste. Ensuite, nous étudions un problème plus difficile, où l'utilisateur doit configurer le nombre de canaux à accéder afin de maximiser son utilité (par exemple, le débit). Après avoir montré la complexité exponentielle du problème, nous développons une stratégie heuristique v-step look-ahead. Dans la stratégie développée, le paramètre v permet de parvenir à un compromis souhaité entre l'efficacité sociale et de la complexité de calcul. Nous démontrons les avantages de la stratégie proposée via des simulations numériques sur plusieurs scénarios typiques. / In the thesis, we address the fundamental problem of opportunistic spectrum access in a multi-channel communication system. Specifically, we consider a communication system in which a user has access to multiple channels, but is limited to sensing and transmitting only on one at a given time. We explore how the smart user should exploit past observations and the knowledge of the stochastic properties of these channels to maximize its transmission rate by switching channels opportunistically. Formally, we provide a generic analysis on the opportunistic spectrum access problem by casting the problem into the restless multi-armed bandit (RMAB) problem, one of the most well-known generalizations of the classic multi-armed bandit (MAB) problem, which is of fundamental importance in stochastic decision theory. Despite the significant research efforts in the field, the RMAB problem in its generic form still remains open. Until today, very little result is reported on the structure of the optimal policy. Obtaining the optimal policy for a general RMAB problem is often intractable due to the exponential computation complexity. Hence, a natural alternative is to seek a simple myopic policy maximizing the short-term reward. Therefore, we develop three axioms characterizing a family of functions which we refer to as regular functions, which are generic and practically important. We then establish the optimality of the myopic policy when the reward function can be expressed as a regular function and the discount factor is bounded by a closed-form threshold determined by the reward function. We also illustrate how the derived results, generic in nature, are applied to analyze a class of RMAB problems arising from multi-channel opportunistic access. Next, we further investigate the more challenging problem where the user has to decide the number of channels to sense in each slot in order to maximize its utility (e.g., throughput). After showing the exponential complexity of the problem, we develop a heuristic v-step look-ahead strategy. In the developed strategy, the parameter v allows to achieve a desired tradeoff between social efficiency and computation complexity. We demonstrate the benefits of the proposed strategy via numerical experiments on several typical settings.

Dans de nombreux domaines dans lesquels les mesures ou les données sont disponibles séquentiellement, il est important de savoir décider le plus tôt possible, même si c’est à partir d’informations encore incomplètes. C’est le cas par exemple en milieu hospitalier où l’apprentissage de règles de décision peut se faire à partir de cas complètement documentés, mais où, devant un nouveau patient, il peut être crucial de prendre une dé- cision très rapidement. Dans ce type de contextes, un compromis doit être optimisé entre la possibilité d’arriver à une meilleure décision en attendant des mesures supplé- mentaires, et le coût croissant associé à chaque nouvelle mesure. Nous considérons dans cette thèse un nouveau cadre général de classification précoce de séries temporelles où le coût d’attente avant de prendre une décision est explicitement pris en compte lors de l’optimisation du compromis entre la qualité et la précocité de prédictions. Nous proposons donc un critère formel qui exprime ce compromis, ainsi que deux approches différentes pour le résoudre. Ces approches sont intéressantes et apportent deux propriétés désirables pour décider en ligne : (i) elles estiment en ligne l’instant optimal dans le futur où une minimisation du critère peut être prévue. Elles vont donc au-delà des approches classiques qui décident d’une façon myope, à chaque instant, d’émettre une prédiction ou d’attendre plus d’information, (ii) ces approches sont adaptatives car elles prennent en compte les propriétés de la série temporelle en entrée pour estimer l’instant optimal pour la classifier. Des expériences extensives sur des données contrôlées et sur des données réelles montrent l’intérêt de ces approches pour fournir des prédictions précoces, fiables, adaptatives et non myopes, ce qui est indispensable dans de nombreuses applications. / Early classification of time series is becoming increasingly a valuable task for assisting in decision making process in many application domains. In this setting, information can be gained by waiting for more evidences to arrive, thus helping to make better decisions that incur lower misclassification costs, but, meanwhile, the cost associated with delaying the decision generally increases, rendering the decision less attractive. Making early predictions provided that are accurate requires then to solve an optimization problem combining two types of competing costs. This thesis introduces a new general framework for time series early classification problem. Unlike classical approaches that implicitly assume that misclassification errors are cost equally and the cost of delaying the decision is constant over time, we cast the the problem as a costsensitive online decision making problem when delaying the decision is costly. We then propose a new formal criterion, along with two approaches that estimate the optimal decision time for a new incoming yet incomplete time series. In particular, they capture the evolutions of typical complete time series in the training set thanks to a segmentation technique that forms meaningful groups, and leverage these complete information to estimate the costs for all future time steps where data points still missing. These approaches are interesting in two ways: (i) they estimate, online, the earliest time in the future where a minimization of the criterion can be expected. They thus go beyond the classical approaches that myopically decide at each time step whether to make a decision or to postpone the call one more time step, and (ii) they are adaptive, in that the properties of the incoming time series are taken into account to decide when is the optimal time to output a prediction. Results of extensive experiments on synthetic and real data sets show that both approaches successfully meet the behaviors expected from early classification systems.

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18855号 / 医博第3966号 / 新制||医||1007(附属図書館) / 31806 / 京都大学大学院医学研究科医学専攻 / (主査)教授 河野 憲二, 教授 黒田 知宏, 教授 富樫 かおり / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

No description available.