ABSTRACT The environment in which services are provisioned in existing networks has a number of shortcomings. Neither the service domain nor the services therein have a standardised structure. Signalling between terminals and services uses network protocols that are inappropriately oriented towards bearer management. The control of bearer connections, and the view of call states, is maintained in the network layer, making bearer management difficult and limited. A service-centric service provisioning environment is proposed, which advocates a structured service domain, and a structured approach to service development and provisioning. A direct communication path between terminals and services at the application layer, that utilises high-level, service-oriented protocols, is proposed. Control of the call / session layer and the bearer network, and view of connection states is relocated to the application layer, facilitating bearer manipulation by services located in the service domain. It is shown that the capabilities and features of services provisioned in the proposed service provisioning environment are of a greater range, more advanced and more complex. It is also shown that the proposed service provisioning environment brings about potential efficiency gains for the initiation of 2-party calls, and significant efficiency gains for the initiation of multiparty calls.

Dans le contexte du cloud computing, l'IaaS fournit des ressources de calcul virtualisées à la demande suivant un modèle de paiement à l'utilisation. Du point de vue de l'utilisateur, ce nouveau paradigme fournit un stock inépuisable de ressources, qui peuvent être dynamiquement demandées et relâchées. L'IaaS permet l'exécution de calculs scientifiques sur un budget de fonctionnement plutôt que sur un investissement initial important. L'ordonnancement sur une telle plateforme élastique constitue un défi important dans le grand nombre de tâches et de ressources à prendre en compte pour réaliser le provisioning, mais également dans le grand nombre de plateformes et de modèles économiques disponibles. Nous avons abordé ce problème en concevant un système de courtage côté client capable (1) d'automatiser le provisioning en fonction d'une stratégie sélectionnée par l'utilisateur et (2) de simuler l'exécution afin de fournir à l'utilisateur une estimation des coûts et temps qu'impliquent les différentes stratégies. Son architecture ouverte permet de s'adapter à un grand nombre de fournisseur de cloud et de stratégies de provisioning. Des expérimentations à grande échelle ont été menées sur plusieurs plateformes de clouds avec des applications de type bag-of-tasks et workflows. Elles montrent la capacité de nos outils à exécuter différents types de workloads sur des plateformes variés et à simuler avec une grande précision ces exécutions. / In the field of cloud computing, IaaS provide virtualized on-demand computing resources on a pay-per-use model. From the user point of view, the cloud provides an inexhaustible supply of resources, which can be dynamically claimed and released. IaaS is especially useful to execute scientific computations using operating budget instead of using a big initial investment. Provisioning the resources depending on the workload is an important challenge, especially regarding the big number of jobs and resoruces to take into account, but also the large amount of available platforms and economic model. We advocate the need for brokers on the client-side with two main capabilities: (1) automate the provisioning depending on the strategy selected by the user and (2) able to simulate an execution in order to provide the user with an estimation of the costs and times of his workload's execution. Many provisioning strategies and cloud providers can be used in this broker thanks to its open architecture. Large scale experiments have been conducted on many cloud platforms and show our tool's ability to execute different kind of workloads on various platforms and to simulate these executions with high accuracy.

S ohledem na stále rostoucí počty prodaných IoT zařízeních se postupně začínají objevovat projekty, ve kterých jsou IoT zařízení použity ve stovkách až tisících. Tyto projekty však z časových důvodů neumožňují ruční konfiguraci každého zařízení zvlášť, čímž vzniká poptávka po protokolech, které dokáží rychle, ale přitom i bezpečně, nastavit nové IoT zařízení. Cílem této práce je vytvořit protokol, který umožní automatický přenos přihlašovacích údajů k Wi-Fi síti do nově zakoupeného IoT zařízení. Navržený protokol používá speciální konfigurační zařízení, ve kterém budou uloženy přihlašovací údaje všech zařízeních kompatibilních s tímto protokolem v rámci dané administrativní domény, a které bude poskytovat tyto přihlašovací údaje nenakonfigurovaným IoT zařízením za předpokladu, že je možné ověřit jejich identitu. K ověření identity nenakonfigurovaných zařízení je použita asymetrické kryptografie. Protokol byl implementován pomocí IoT zařízeních ESP32, přičemž ke komunikaci mezi nenakonfigurovanými je využit nespojovaný komunikační protokol ESP-NOW.

To achieve “provisioning elasticity”, the cloud needs to manage its available resources on demand. A-priori, static, VM provisioning introduces no runtime overhead but fails to handle unanticipated changes in resource demands. Dynamic provisioning addresses this problem but introduces runtime overhead. To avoid sub-optimal provisioning my PhD thesis adopts a hybrid approach that combines static and dynamic provisioning. The idea is to adapt an initial static placement of VMs in response to evolving load characteristics. My work is focused on broadening the applicability of clouds by looking at how the infrastructure can be more effectively used to support historically atypical applications (e.g. those that are interactive in nature with tighter QoS constraints). To accomplish this I have developed a family of related algorithms that collectively improve resource sharing on physical machines to permit load variation to be better addressed and to lessen the probability of VM interference due to resource contention. The family includes three core dynamic provisioning algorithms. The first algorithm provides for the short-term, controlled sharing of resources between co-hosted VMs, the second identifies pairs (and by extrapolation larger groups) of VMs that are predicted to be "compatible" in terms of the resources they need. This allows the cloud provider to do co-location to make the first algorithm more effective. The final, third, algorithm deals with under-utilized physical machines by re-packing the VMs on those machines while also considering their compatibility. This final algorithm both addresses the possibility of the second algorithm creating underutilized machines as a result of pairing and migration and also handles underutilization arising from “holes” left by the termination of short-duration VMs (another form of atypical VM application). I have also created a surprisingly simple static provisioning algorithm that considers compatibility to minimize VM interference that can be used before my dynamic algorithms. My evaluation is primarily simulation-based though I have also implemented the core algorithms on a small test-bed system to ensure correctness. The results obtained from my simulation experiments suggest that hybrid static and dynamic provisioning approaches are both feasible and should be effective supporting a broad range of applications in cloud environments. / February 2017

Dynamic provisioning of server boxes to applications entails an inherent performance-power trade-off for the service provider, a trade-off that has not been studied in detail. The optimal number of replicas to be dynamically provisioned to an application is ultimately the configuration that results in the highest revenue. The service provider should thus dynamically provision resources for an application only as long as the resulting reward from hosting more clients exceeds its operational costs for power and cooling. We introduce a novel cost-aware dynamic provisioning approach for the database tier of a dynamic content site. Our approach employs Support Vector Machine regression for learning a dynamically adaptive system model. We leverage this lightweight on-line learning approach for two cost-aware dynamic provisioning techniques. The first is a temperature-aware scheme which avoids temperature hot-spots within the set of provisioned machines, and hence reduces cooling costs. The second is a more general cost-aware provisioning technique using a utility function expressing monetary costs for both performance and power.

Dynamic provisioning of server boxes to applications entails an inherent performance-power trade-off for the service provider, a trade-off that has not been studied in detail. The optimal number of replicas to be dynamically provisioned to an application is ultimately the configuration that results in the highest revenue. The service provider should thus dynamically provision resources for an application only as long as the resulting reward from hosting more clients exceeds its operational costs for power and cooling. We introduce a novel cost-aware dynamic provisioning approach for the database tier of a dynamic content site. Our approach employs Support Vector Machine regression for learning a dynamically adaptive system model. We leverage this lightweight on-line learning approach for two cost-aware dynamic provisioning techniques. The first is a temperature-aware scheme which avoids temperature hot-spots within the set of provisioned machines, and hence reduces cooling costs. The second is a more general cost-aware provisioning technique using a utility function expressing monetary costs for both performance and power.

<p>This master’s thesis intention is to develop a Java language framework with XAP providing state provisioning function. The idea is that the state from an application should be transferred between different application instances opening up for continuous application use. By using our framework prototype, applications which are provided by XAP can implement the state provisioning function. We first introduce our framework and its core mechanisms. To be able to verify it, we also present an evaluation of the feasibility and practicability of our framework.</p>

With the emergence of the cloud computing paradigm, we can now provide dynamic resource provisioning at unprecedented levels of scalability. This flexibility constitutes a rich environment for researchers to experiment with new designs. Such experimental novel designs can take advantage of adaptation, controllability, self- configuration, and scheduling techniques to provide improved resource utilization while achieving service level agreements. This dissertation uses control and scheduling theories to develop new designs to improve resource utilization and service level agreement satisfaction. We optimize resource provisioning using the Cutting Stock problem formulation and control theory within feedback frameworks. We introduce a model-based method of control to manipulate the scheduling problem’s formulation model to achieve desired results. We also present a control based method using Kalman filters for admission control. Finally, we present two case studies — the Yakkit media social application and the Rigi Cloud testbed for deploying virtual ma- chine experiments. The results of our investigations demonstrate that our approaches and techniques can optimize resource utilization, decrease service level agreement violations, and provide scheduling guarantees. / Graduate / 0790 / 0984 / rd@uvic.ca

An investigation was made into the characteristics of program elements and removals of Weapon Replaceable Assemblies aggregated at the system level for the purpose of developing a method to predict removals during initial provisioning periods. From examination of nine avionic systems over a 28 month period a binomial model was developed using a removal rate based on aircraft-months as a program element. The model is to be used before Fleet data are generated by obtaining aircraft-month estimates from the contractor and removal rate estimates from similar operational equipments. A probability distribution reflecting the degree of certainty is selected as a prior estimate. Then, as Fleet experience is accumulated the distribution is updated using Bayesian techniques and maturity growth curves. This distribution is used to give an estimate of current removal rate and to extrapolate to future removal rates.

Cloud computing setups are a huge investment of resources and personnel to maintain. As<br />the workload on a system is a major contributing factor to both the performance of the<br />system and a representation of the needs of system users, a clear understanding of the<br />workload is critical to organizations that support supercomputing systems. In this paper,<br />we analyze traces from two production level supercomputers to infer the characteristics of<br />their workloads, and make observations as to the needs of supercomputer users based on<br />them. We particularly focus on the usage of graphical processing units by domain<br />scientists. Based on this analysis, we generate a synthetic workload that can be used for<br />testing future systems, and make observations as to e"cient resource provisioning. / Master of Science