@phdthesis{Eismann2023,
  author    = {Eismann, Simon},
  title     = {Performance Engineering of Serverless Applications and Platforms},
  doi       = {10.25972/OPUS-30313},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-303134},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {Serverless computing is an emerging cloud computing paradigm that offers a highlevel application programming model with utilization-based billing. It enables the deployment of cloud applications without managing the underlying resources or worrying about other operational aspects. Function-as-a-Service (FaaS) platforms implement serverless computing by allowing developers to execute code on-demand in response to events with continuous scaling while having to pay only for the time used with sub-second metering. Cloud providers have further introduced many fully managed services for databases, messaging buses, and storage that also implement a serverless computing model. Applications composed of these fully managed services and FaaS functions are quickly gaining popularity in both industry and in academia. However, due to this rapid adoption, much information surrounding serverless computing is inconsistent and often outdated as the serverless paradigm evolves. This makes the performance engineering of serverless applications and platforms challenging, as there are many open questions, such as: What types of applications is serverless computing well suited for, and what are its limitations? How should serverless applications be designed, configured, and implemented? Which design decisions impact the performance properties of serverless platforms and how can they be optimized? These and many other open questions can be traced back to an inconsistent understanding of serverless applications and platforms, which could present a major roadblock in the adoption of serverless computing. In this thesis, we address the lack of performance knowledge surrounding serverless applications and platforms from multiple angles: we conduct empirical studies to further the understanding of serverless applications and platforms, we introduce automated optimization methods that simplify the operation of serverless applications, and we enable the analysis of design tradeoffs of serverless platforms by extending white-box performance modeling.},
  subject      = {Leistungsbewertung},
  language  = {en}
}
@phdthesis{Schmitt2022,
  author    = {Schmitt, Norbert},
  title     = {Measurement, Modeling, and Emulation of Power Consumption of Distributed Systems},
  doi       = {10.25972/OPUS-27658},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-276582},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {Today's cloud data centers consume an enormous amount of energy, and energy consumption will rise in the future. An estimate from 2012 found that data centers consume about 30 billion watts of power, resulting in about 263TWh of energy usage per year. The energy consumption will rise to 1929TWh until 2030. This projected rise in energy demand is fueled by a growing number of services deployed in the cloud. 50\% of enterprise workloads have been migrated to the cloud in the last decade so far. Additionally, an increasing number of devices are using the cloud to provide functionalities and enable data centers to grow. Estimates say more than 75 billion IoT devices will be in use by 2025. The growing energy demand also increases the amount of CO2 emissions. Assuming a CO2-intensity of 200g CO2 per kWh will get us close to 227 billion tons of CO2. This emission is more than the emissions of all energy-producing power plants in Germany in 2020. However, data centers consume energy because they respond to service requests that are fulfilled through computing resources. Hence, it is not the users and devices that consume the energy in the data center but the software that controls the hardware. While the hardware is physically consuming energy, it is not always responsible for wasting energy. The software itself plays a vital role in reducing the energy consumption and CO2 emissions of data centers. The scenario of our thesis is, therefore, focused on software development. Nevertheless, we must first show developers that software contributes to energy consumption by providing evidence of its influence. The second step is to provide methods to assess an application's power consumption during different phases of the development process and to allow modern DevOps and agile development methods. We, therefore, need to have an automatic selection of system-level energy-consumption models that can accommodate rapid changes in the source code and application-level models allowing developers to locate power-consuming software parts for constant improvements. Afterward, we need emulation to assess the energy efficiency before the actual deployment.},
  subject      = {Leistungsbedarf},
  language  = {en}
}
@phdthesis{Grohmann2022,
  author    = {Grohmann, Johannes Sebastian},
  title     = {Model Learning for Performance Prediction of Cloud-native Microservice Applications},
  doi       = {10.25972/OPUS-26160},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-261608},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {One consequence of the recent coronavirus pandemic is increased demand and use of online services around the globe. At the same time, performance requirements for modern technologies are becoming more stringent as users become accustomed to higher standards. These increased performance and availability requirements, coupled with the unpredictable usage growth, are driving an increasing proportion of applications to run on public cloud platforms as they promise better scalability and reliability. With data centers already responsible for about one percent of the world's power consumption, optimizing resource usage is of paramount importance. Simultaneously, meeting the increasing and changing resource and performance requirements is only possible by optimizing resource management without introducing additional overhead. This requires the research and development of new modeling approaches to understand the behavior of running applications with minimal information. However, the emergence of modern software paradigms makes it increasingly difficult to derive such models and renders previous performance modeling techniques infeasible. Modern cloud applications are often deployed as a collection of fine-grained and interconnected components called microservices. Microservice architectures offer massive benefits but also have broad implications for the performance characteristics of the respective systems. In addition, the microservices paradigm is typically paired with a DevOps culture, resulting in frequent application and deployment changes. Such applications are often referred to as cloud-native applications. In summary, the increasing use of ever-changing cloud-hosted microservice applications introduces a number of unique challenges for modeling the performance of modern applications. These include the amount, type, and structure of monitoring data, frequent behavioral changes, or infrastructure variabilities. This violates common assumptions of the state of the art and opens a research gap for our work. In this thesis, we present five techniques for automated learning of performance models for cloud-native software systems. We achieve this by combining machine learning with traditional performance modeling techniques. Unlike previous work, our focus is on cloud-hosted and continuously evolving microservice architectures, so-called cloud-native applications. Therefore, our contributions aim to solve the above challenges to deliver automated performance models with minimal computational overhead and no manual intervention. Depending on the cloud computing model, privacy agreements, or monitoring capabilities of each platform, we identify different scenarios where performance modeling, prediction, and optimization techniques can provide great benefits. Specifically, the contributions of this thesis are as follows: Monitorless: Application-agnostic prediction of performance degradations. To manage application performance with only platform-level monitoring, we propose Monitorless, the first truly application-independent approach to detecting performance degradation. We use machine learning to bridge the gap between platform-level monitoring and application-specific measurements, eliminating the need for application-level monitoring. Monitorless creates a single and holistic resource saturation model that can be used for heterogeneous and untrained applications. Results show that Monitorless infers resource-based performance degradation with 97\% accuracy. Moreover, it can achieve similar performance to typical autoscaling solutions, despite using less monitoring information. SuanMing: Predicting performance degradation using tracing. We introduce SuanMing to mitigate performance issues before they impact the user experience. This contribution is applied in scenarios where tracing tools enable application-level monitoring. SuanMing predicts explainable causes of expected performance degradations and prevents performance degradations before they occur. Evaluation results show that SuanMing can predict and pinpoint future performance degradations with an accuracy of over 90\%. SARDE: Continuous and autonomous estimation of resource demands. We present SARDE to learn application models for highly variable application deployments. This contribution focuses on the continuous estimation of application resource demands, a key parameter of performance models. SARDE represents an autonomous ensemble estimation technique. It dynamically and continuously optimizes, selects, and executes an ensemble of approaches to estimate resource demands in response to changes in the application or its environment. Through continuous online adaptation, SARDE efficiently achieves an average resource demand estimation error of 15.96\% in our evaluation. DepIC: Learning parametric dependencies from monitoring data. DepIC utilizes feature selection techniques in combination with an ensemble regression approach to automatically identify and characterize parametric dependencies. Although parametric dependencies can massively improve the accuracy of performance models, DepIC is the first approach to automatically learn such parametric dependencies from passive monitoring data streams. Our evaluation shows that DepIC achieves 91.7\% precision in identifying dependencies and reduces the characterization prediction error by 30\% compared to the best individual approach. Baloo: Modeling the configuration space of databases. To study the impact of different configurations within distributed DBMSs, we introduce Baloo. Our last contribution models the configuration space of databases considering measurement variabilities in the cloud. More specifically, Baloo dynamically estimates the required benchmarking measurements and automatically builds a configuration space model of a given DBMS. Our evaluation of Baloo on a dataset consisting of 900 configuration points shows that the framework achieves a prediction error of less than 11\% while saving up to 80\% of the measurement effort. Although the contributions themselves are orthogonally aligned, taken together they provide a holistic approach to performance management of modern cloud-native microservice applications. Our contributions are a significant step forward as they specifically target novel and cloud-native software development and operation paradigms, surpassing the capabilities and limitations of previous approaches. In addition, the research presented in this paper also has a significant impact on the industry, as the contributions were developed in collaboration with research teams from Nokia Bell Labs, Huawei, and Google. Overall, our solutions open up new possibilities for managing and optimizing cloud applications and improve cost and energy efficiency.},
  subject      = {Cloud Computing},
  language  = {en}
}
@techreport{MetzgerRafetsederSchroederetal.2016,
  type      = {Working Paper},
  author    = {Metzger, Florian and Rafetseder, Albert and Schr{\"o}der, Svenja and Zwickl, Patrick},
  title     = {The Prospects of Cloud Gaming: Do the Benefits Outweigh the Costs?},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-242452},
  pages     = {10},
  year      = {2016},
  abstract  = {In recent years, cloud gaming has become a popular research topic and has claimed many benefits in the commercial domain over conventional gaming. While, cloud gaming platforms have frequently failed in the past, they have received a new impetus over the last years that brought it to the edge of commercial breakthrough. The fragility of the cloud gaming market may be caused by the high investment costs, offered pricing models or competition from existing "{\`a} la carte" platforms. This paper aims at investigating the costs and benefits of both platform types through a twofold approach. We first take on the perspective of the customers, and investigate several cloud gaming platforms and their pricing models in comparison to the costs of other gaming platforms. Then, we explore engagement metrics in order to assess the enjoyment of playing the offered games. Lastly, coming from the perspective of the service providers, we aim to identify challenges in cost-effectively operating a large-scale cloud gaming service while maintaining high QoE values. Our analysis provides initial, yet still comprehensive reasons and models for the prospects of cloud gaming in a highly competitive market.},
  subject      = {Cloud Computing},
  language  = {en}
}
@phdthesis{Bauer2021,
  author    = {Bauer, Andr{\´e}},
  title     = {Automated Hybrid Time Series Forecasting: Design, Benchmarking, and Use Cases},
  doi       = {10.25972/OPUS-22025},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-220255},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2021},
  abstract  = {These days, we are living in a digitalized world. Both our professional and private lives are pervaded by various IT services, which are typically operated using distributed computing systems (e.g., cloud environments). Due to the high level of digitalization, the operators of such systems are confronted with fast-paced and changing requirements. In particular, cloud environments have to cope with load fluctuations and respective rapid and unexpected changes in the computing resource demands. To face this challenge, so-called auto-scalers, such as the threshold-based mechanism in Amazon Web Services EC2, can be employed to enable elastic scaling of the computing resources. However, despite this opportunity, business-critical applications are still run with highly overprovisioned resources to guarantee a stable and reliable service operation. This strategy is pursued due to the lack of trust in auto-scalers and the concern that inaccurate or delayed adaptations may result in financial losses. To adapt the resource capacity in time, the future resource demands must be "foreseen", as reacting to changes once they are observed introduces an inherent delay. In other words, accurate forecasting methods are required to adapt systems proactively. A powerful approach in this context is time series forecasting, which is also applied in many other domains. The core idea is to examine past values and predict how these values will evolve as time progresses. According to the "No-Free-Lunch Theorem", there is no algorithm that performs best for all scenarios. Therefore, selecting a suitable forecasting method for a given use case is a crucial task. Simply put, each method has its benefits and drawbacks, depending on the specific use case. The choice of the forecasting method is usually based on expert knowledge, which cannot be fully automated, or on trial-and-error. In both cases, this is expensive and prone to error. Although auto-scaling and time series forecasting are established research fields, existing approaches cannot fully address the mentioned challenges: (i) In our survey on time series forecasting, we found that publications on time series forecasting typically consider only a small set of (mostly related) methods and evaluate their performance on a small number of time series with only a few error measures while providing no information on the execution time of the studied methods. Therefore, such articles cannot be used to guide the choice of an appropriate method for a particular use case; (ii) Existing open-source hybrid forecasting methods that take advantage of at least two methods to tackle the "No-Free-Lunch Theorem" are computationally intensive, poorly automated, designed for a particular data set, or they lack a predictable time-to-result. Methods exhibiting a high variance in the time-to-result cannot be applied for time-critical scenarios (e.g., auto-scaling), while methods tailored to a specific data set introduce restrictions on the possible use cases (e.g., forecasting only annual time series); (iii) Auto-scalers typically scale an application either proactively or reactively. Even though some hybrid auto-scalers exist, they lack sophisticated solutions to combine reactive and proactive scaling. For instance, resources are only released proactively while resource allocation is entirely done in a reactive manner (inherently delayed); (iv) The majority of existing mechanisms do not take the provider's pricing scheme into account while scaling an application in a public cloud environment, which often results in excessive charged costs. Even though some cost-aware auto-scalers have been proposed, they only consider the current resource demands, neglecting their development over time. For example, resources are often shut down prematurely, even though they might be required again soon. To address the mentioned challenges and the shortcomings of existing work, this thesis presents three contributions: (i) The first contribution-a forecasting benchmark-addresses the problem of limited comparability between existing forecasting methods; (ii) The second contribution-Telescope-provides an automated hybrid time series forecasting method addressing the challenge posed by the "No-Free-Lunch Theorem"; (iii) The third contribution-Chamulteon-provides a novel hybrid auto-scaler for coordinated scaling of applications comprising multiple services, leveraging Telescope to forecast the workload intensity as a basis for proactive resource provisioning. In the following, the three contributions of the thesis are summarized: Contribution I - Forecasting Benchmark To establish a level playing field for evaluating the performance of forecasting methods in a broad setting, we propose a novel benchmark that automatically evaluates and ranks forecasting methods based on their performance in a diverse set of evaluation scenarios. The benchmark comprises four different use cases, each covering 100 heterogeneous time series taken from different domains. The data set was assembled from publicly available time series and was designed to exhibit much higher diversity than existing forecasting competitions. Besides proposing a new data set, we introduce two new measures that describe different aspects of a forecast. We applied the developed benchmark to evaluate Telescope. Contribution II - Telescope To provide a generic forecasting method, we introduce a novel machine learning-based forecasting approach that automatically retrieves relevant information from a given time series. More precisely, Telescope automatically extracts intrinsic time series features and then decomposes the time series into components, building a forecasting model for each of them. Each component is forecast by applying a different method and then the final forecast is assembled from the forecast components by employing a regression-based machine learning algorithm. In more than 1300 hours of experiments benchmarking 15 competing methods (including approaches from Uber and Facebook) on 400 time series, Telescope outperformed all methods, exhibiting the best forecast accuracy coupled with a low and reliable time-to-result. Compared to the competing methods that exhibited, on average, a forecast error (more precisely, the symmetric mean absolute forecast error) of 29\%, Telescope exhibited an error of 20\% while being 2556 times faster. In particular, the methods from Uber and Facebook exhibited an error of 48\% and 36\%, and were 7334 and 19 times slower than Telescope, respectively. Contribution III - Chamulteon To enable reliable auto-scaling, we present a hybrid auto-scaler that combines proactive and reactive techniques to scale distributed cloud applications comprising multiple services in a coordinated and cost-effective manner. More precisely, proactive adaptations are planned based on forecasts of Telescope, while reactive adaptations are triggered based on actual observations of the monitored load intensity. To solve occurring conflicts between reactive and proactive adaptations, a complex conflict resolution algorithm is implemented. Moreover, when deployed in public cloud environments, Chamulteon reviews adaptations with respect to the cloud provider's pricing scheme in order to minimize the charged costs. In more than 400 hours of experiments evaluating five competing auto-scaling mechanisms in scenarios covering five different workloads, four different applications, and three different cloud environments, Chamulteon exhibited the best auto-scaling performance and reliability while at the same time reducing the charged costs. The competing methods provided insufficient resources for (on average) 31\% of the experimental time; in contrast, Chamulteon cut this time to 8\% and the SLO (service level objective) violations from 18\% to 6\% while using up to 15\% less resources and reducing the charged costs by up to 45\%. The contributions of this thesis can be seen as major milestones in the domain of time series forecasting and cloud resource management. (i) This thesis is the first to present a forecasting benchmark that covers a variety of different domains with a high diversity between the analyzed time series. Based on the provided data set and the automatic evaluation procedure, the proposed benchmark contributes to enhance the comparability of forecasting methods. The benchmarking results for different forecasting methods enable the selection of the most appropriate forecasting method for a given use case. (ii) Telescope provides the first generic and fully automated time series forecasting approach that delivers both accurate and reliable forecasts while making no assumptions about the analyzed time series. Hence, it eliminates the need for expensive, time-consuming, and error-prone procedures, such as trial-and-error searches or consulting an expert. This opens up new possibilities especially in time-critical scenarios, where Telescope can provide accurate forecasts with a short and reliable time-to-result. Although Telescope was applied for this thesis in the field of cloud computing, there is absolutely no limitation regarding the applicability of Telescope in other domains, as demonstrated in the evaluation. Moreover, Telescope, which was made available on GitHub, is already used in a number of interdisciplinary data science projects, for instance, predictive maintenance in an Industry 4.0 context, heart failure prediction in medicine, or as a component of predictive models of beehive development. (iii) In the context of cloud resource management, Chamulteon is a major milestone for increasing the trust in cloud auto-scalers. The complex resolution algorithm enables reliable and accurate scaling behavior that reduces losses caused by excessive resource allocation or SLO violations. In other words, Chamulteon provides reliable online adaptations minimizing charged costs while at the same time maximizing user experience.},
  subject      = {Zeitreihenanalyse},
  language  = {en}
}
@phdthesis{Herbst2018,
  author    = {Herbst, Nikolas Roman},
  title     = {Methods and Benchmarks for Auto-Scaling Mechanisms in Elastic Cloud Environments},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-164314},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2018},
  abstract  = {A key functionality of cloud systems are automated resource management mechanisms at the infrastructure level. As part of this, elastic scaling of allocated resources is realized by so-called auto-scalers that are supposed to match the current demand in a way that the performance remains stable while resources are efficiently used. The process of rating cloud infrastructure offerings in terms of the quality of their achieved elastic scaling remains undefined. Clear guidance for the selection and configuration of an auto-scaler for a given context is not available. Thus, existing operating solutions are optimized in a highly application specific way and usually kept undisclosed. The common state of practice is the use of simplistic threshold-based approaches. Due to their reactive nature they incur performance degradation during the minutes of provisioning delays. In the literature, a high-number of auto-scalers has been proposed trying to overcome the limitations of reactive mechanisms by employing proactive prediction methods. In this thesis, we identify potentials in automated cloud system resource management and its evaluation methodology. Specifically, we make the following contributions: We propose a descriptive load profile modeling framework together with automated model extraction from recorded traces to enable reproducible workload generation with realistic load intensity variations. The proposed Descartes Load Intensity Model (DLIM) with its Limbo framework provides key functionality to stress and benchmark resource management approaches in a representative and fair manner. We propose a set of intuitive metrics for quantifying timing, stability and accuracy aspects of elasticity. Based on these metrics, we propose a novel approach for benchmarking the elasticity of Infrastructure-as-a-Service (IaaS) cloud platforms independent of the performance exhibited by the provisioned underlying resources. We tackle the challenge of reducing the risk of relying on a single proactive auto-scaler by proposing a new self-aware auto-scaling mechanism, called Chameleon, combining multiple different proactive methods coupled with a reactive fallback mechanism. Chameleon employs on-demand, automated time series-based forecasting methods to predict the arriving load intensity in combination with run-time service demand estimation techniques to calculate the required resource consumption per work unit without the need for a detailed application instrumentation. It can also leverage application knowledge by solving product-form queueing networks used to derive optimized scaling actions. The Chameleon approach is first in resolving conflicts between reactive and proactive scaling decisions in an intelligent way. We are confident that the contributions of this thesis will have a long-term impact on the way cloud resource management approaches are assessed. While this could result in an improved quality of autonomic management algorithms, we see and discuss arising challenges for future research in cloud resource management and its assessment methods: The adoption of containerization on top of virtual machine instances introduces another level of indirection. As a result, the nesting of virtual resources increases resource fragmentation and causes unreliable provisioning delays. Furthermore, virtualized compute resources tend to become more and more inhomogeneous associated with various priorities and trade-offs. Due to DevOps practices, cloud hosted service updates are released with a higher frequency which impacts the dynamics in user behavior.},
  subject      = {Cloud Computing},
  language  = {en}
}
@phdthesis{Spinner2017,
  author    = {Spinner, Simon},
  title     = {Self-Aware Resource Management in Virtualized Data Centers},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-153754},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2017},
  abstract  = {Enterprise applications in virtualized data centers are often subject to time-varying workloads, i.e., the load intensity and request mix change over time, due to seasonal patterns and trends, or unpredictable bursts in user requests. Varying workloads result in frequently changing resource demands to the underlying hardware infrastructure. Virtualization technologies enable sharing and on-demand allocation of hardware resources between multiple applications. In this context, the resource allocations to virtualized applications should be continuously adapted in an elastic fashion, so that "at each point in time the available resources match the current demand as closely as possible" (Herbst el al., 2013). Autonomic approaches to resource management promise significant increases in resource efficiency while avoiding violations of performance and availability requirements during peak workloads. Traditional approaches for autonomic resource management use threshold-based rules (e.g., Amazon EC2) that execute pre-defined reconfiguration actions when a metric reaches a certain threshold (e.g., high resource utilization or load imbalance). However, many business-critical applications are subject to Service-Level-Objectives defined on an application performance metric (e.g., response time or throughput). To determine thresholds so that the end-to-end application SLO is fulfilled poses a major challenge due to the complex relationship between the resource allocation to an application and the application performance. Furthermore, threshold-based approaches are inherently prone to an oscillating behavior resulting in unnecessary reconfigurations. In order to overcome the deficiencies of threshold-based approaches and enable a fully automated approach to dynamically control the resource allocations of virtualized applications, model-based approaches are required that can predict the impact of a reconfiguration on the application performance in advance. However, existing model-based approaches are severely limited in their learning capabilities. They either require complete performance models of the application as input, or use a pre-identified model structure and only learn certain model parameters from empirical data at run-time. The former requires high manual efforts and deep system knowledge to create the performance models. The latter does not provide the flexibility to capture the specifics of complex and heterogeneous system architectures. This thesis presents a self-aware approach to the resource management in virtualized data centers. In this context, self-aware means that it automatically learns performance models of the application and the virtualized infrastructure and reasons based on these models to autonomically adapt the resource allocations in accordance with given application SLOs. Learning a performance model requires the extraction of the model structure representing the system architecture as well as the estimation of model parameters, such as resource demands. The estimation of resource demands is a key challenge as they cannot be observed directly in most systems. The major scientific contributions of this thesis are: - A reference architecture for online model learning in virtualized systems. Our reference architecture is based on a set of model extraction agents. Each agent focuses on specific tasks to automatically create and update model skeletons capturing its local knowledge of the system and collaborates with other agents to extract the structural parts of a global performance model of the system. We define different agent roles in the reference architecture and propose a model-based collaboration mechanism for the agents. The agents may be bundled within virtual appliances and may be tailored to include knowledge about the software stack deployed in a specific virtual appliance. - An online method for the statistical estimation of resource demands. For a given request processed by an application, the resource time consumed for a specified resource within the system (e.g., CPU or I/O device), referred to as resource demand, is the total average time the resource is busy processing the request. A request could be any unit of work (e.g., web page request, database transaction, batch job) processed by the system. We provide a systematization of existing statistical approaches to resource demand estimation and conduct an extensive experimental comparison to evaluate the accuracy of these approaches. We propose a novel method to automatically select estimation approaches and demonstrate that it increases the robustness and accuracy of the estimated resource demands significantly. - Model-based controllers for autonomic vertical scaling of virtualized applications. We design two controllers based on online model-based reasoning techniques in order to vertically scale applications at run-time in accordance with application SLOs. The controllers exploit the knowledge from the automatically extracted performance models when determining necessary reconfigurations. The first controller adds and removes virtual CPUs to an application depending on the current demand. It uses a layered performance model to also consider the physical resource contention when determining the required resources. The second controller adapts the resource allocations proactively to ensure the availability of the application during workload peaks and avoid reconfiguration during phases of high workload. We demonstrate the applicability of our approach in current virtualized environments and show its effectiveness leading to significant increases in resource efficiency and improvements of the application performance and availability under time-varying workloads. The evaluation of our approach is based on two case studies representative of widely used enterprise applications in virtualized data centers. In our case studies, we were able to reduce the amount of required CPU resources by up to 23\% and the number of reconfigurations by up to 95\% compared to a rule-based approach while ensuring full compliance with application SLO. Furthermore, using workload forecasting techniques we were able to schedule expensive reconfigurations (e.g., changes to the memory size) during phases of load load and thus were able to reduce their impact on application availability by over 80\% while significantly improving application performance compared to a reactive controller. The methods and techniques for resource demand estimation and vertical application scaling were developed and evaluated in close collaboration with VMware and Google.},
  subject      = {Cloud Computing},
  language  = {en}
}
@phdthesis{Fehrmann2015,
  author    = {Fehrmann, Sven},
  title     = {Ontologiebasiertes Cloud Computing},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-111929},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2015},
  abstract  = {Die Dissertation „Ontologiebasiertes Cloud Computing" im Fachbereich Wirtschaftsinformatik behandelt das Thema Cloud Computing und veranschaulicht die M{\"o}glichkeiten der theoretischen und praktischen Nutzung einer Ontologie f{\"u}r das Cloud Computing. Neben den Private und Public Clouds sowie Hybrid-L{\"o}sungen wird vor allem eine ausgefeilte Virtualisierungstechnologie die Zukunft im IT-Bereich mitgestalten. Die Vielfalt und Anzahl der angebotenen Services nimmt besonders auf dem Sektor der Public Clouds weiterhin stark zu, w{\"a}hrend im Hybrid-Bereich ansprechende L{\"o}sungen noch ausstehen. Das Nutzen eines Cloud-Services ist in der Regel einfach und wird mit den fallenden Preisen zunehmend interessanter. Eine Reihe von Punkten, die im Vorfeld genau betrachtet und festgelegt werden m{\"u}ssen, wie Aspekte der IT-Sicherheit, des Datenschutzes und der Kosten, erm{\"o}glichen eine wirtschaftliche und rechtssichere Inanspruchnahme eines Cloud-Services. Vor der Nutzung eines Services m{\"u}ssen zudem der Wert, die Nutzungsh{\"a}ufigkeit und die Geheimhaltungsstufe der eigenen Daten bekannt sein, um sicher bestimmen zu k{\"o}nnen, ob alle Informationen oder nur ein Teil zum Auslagern geeignet sind. Dazu bedarf es einer klaren Festlegung der vertraglichen Rahmenbedingungen und einer Regelung bez{\"u}glich des Schadensersatzes bei einem Ausfall. Ein aktives Change Management sollte schon vor der Einf{\"u}hrung eines Services Akzeptanz f{\"u}r die sich im IT-Umfeld {\"a}ndernden Aufgabengebiete schaffen. Vergleichbare Alternativen zu finden, dies war die Zielvorgabe der durchgef{\"u}hrten, breiten Untersuchung von 15 Serviceanbietern, verbunden mit dem Aufbau einer Ontologie. Auf einem sehr dynamischen Cloud Computing Markt k{\"o}nnen diese Untersuchungen nat{\"u}rlich nur eine Momentaufnahme abbilden, denn neue Provider etablieren sich, schon l{\"a}nger bestehende ver{\"a}ndern und verbessern ihre Angebote. Damit diese Momentaufnahme nicht in einem statischen Endzustand verbleibt, wurde eine Ontologie aufgebaut, die die konsistente Einpflege ver{\"a}nderter Sachverhalte zul{\"a}sst. Die Idealvorstellung ist es, dass beim Bekanntwerden einer neuen Information diese auch immer in die Ontologie einfließt. Die Anbieteruntersuchung zeigt, dass Cloud-Services heute schon ein hohes Potential haben. Um sich einen Gesamt{\"u}berblick {\"u}ber die unterschiedlichen Services und ihre Angebote zu verschaffen, ist eine Ontologie besonders geeignet. Die aufgebaute Cloud-Ontologie beinhaltet eine Service-Auswahl, die auf die Literatur- und Anbieteruntersuchung aufbaut. {\"A}hnlich einer Suchmaschine hilft sie, sich {\"u}ber bestehende Angebote auf dem Markt zu informieren. Und sie vereinfacht die Selektion, definiert klar bekannte technische Details, erleichtert die Suche z. B. nach ben{\"o}tigten Zusatzdienstleistungen {\"u}ber standardisierte Schnittstellen, versucht Transparenz und Nachvollziehbarkeit bei den Abrechnungsmodellen herzustellen, um eine Vergleichbarkeit {\"u}berhaupt erst zu erm{\"o}glichen. Der gr{\"o}ßte Vorteil liegt in der Zeitersparnis: Die Recherche nach passenden Cloud-Services wird durch formalisierte und somit vergleichbare Kriterien verk{\"u}rzt. Bei mehreren passenden Anbietern l{\"a}sst sich {\"u}ber weitere Abfragen oder Kostenvergleiche der jeweils f{\"u}r den Nutzer beste Anbieter gezielt finden. Ebenso k{\"o}nnen Services mit signifikanten Ausschlusskriterien fr{\"u}hzeitig aus der Auswahl entfernt werden. Durch das Verbot bestimmter Zuweisungen oder durch die Forderung von Mindestbedingungen innerhalb der Ontologie wird die Einpflege falscher Sachverhalte verhindert und sie erweist sich damit wesentlich unempfindlicher als viele Programme. Die Aufgabenstellung bei der Modellerstellung lag darin, zu einer allgemeinen Aussagekraft der modellierten Abh{\"a}ngigkeiten zu kommen. Außerdem erf{\"u}llt die Cloud-Ontologie die vier typischen Anforderungen an eine Ontologie: Sie ist ausschließlich durch die standardisierte Sprache OWL beschrieben, kann durch einen Inferenzalgorithmus (z. B. Pellet) ausgewertet werden, unterscheidet eindeutig zwischen 80 Klassen und 342 Individuals und bildet zahlreiche Informationen {\"u}ber 2657 Verkn{\"u}pfungen ab. Die Ontologie kann mit geringem Aufwand auch in ein Programm mit einer ansprechenden Oberfl{\"a}che {\"u}berf{\"u}hrt werden, wie der programmierte Prototyp beweist. In der Praxis m{\"u}ssen f{\"u}r Unternehmen verst{\"a}rkt Hilfsmittel angeboten werden oder in den Vordergrund r{\"u}cken, wie Cloud-Ontologien, die die Auswahl von Services erleichtern, Vergleiche erst erm{\"o}glichen, die Suche verk{\"u}rzen und zum Schluss zu Ergebnissen f{\"u}hren, die den Vorstellungen des k{\"u}nftigen Nutzers entsprechen.},
  subject      = {Cloud Computing},
  language  = {de}
}
@book{JonesNobisRoechneretal.2010,
  author    = {Jones, Christopher and Nobis, Ralf and R{\"o}chner, Susanne and Thal, Paul},
  title     = {Internet der Zukunft},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-55736},
  publisher      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2010},
  abstract  = {Wie kaum eine andere technische Neuerung hat das Internet das t{\"a}gliche Leben von Millionen von Menschen ver{\"a}ndert. Quasi im Gegenzug ver{\"a}ndern mittlerweile aber auch Millionen von Menschen ihrerseits das Internet. Aus dem einfachen User wurde der Creator. Diese Entwicklung wird vielerorts unter den Begriff des Web 2.0 gefasst, das vor allem als Schlagwort die ver{\"a}nderte Rollenverteilung im Web beschreibt. Das Web 2.0 l{\"a}sst sich aber auch typologisch begreifen, als Zusammenfassung vieler Ein-zelph{\"a}nomene, die den Typus Web 2.0 charakterisieren. Diese Ph{\"a}nomene befinden sich aber (wie auch das Web selbst) in einem stetigen Wandel und Weiterentwicklungs-prozess, sodass sie sowohl dem Web 2.0 als auch dem Internet der Zukunft zugeh{\"o}rig zu sein scheinen: W{\"a}hrend die Potentiale des Cloud Computing und der Augmented Reality wohl noch in den Kinderschuhen stecken, haben soziale Netzwerke, ubiquit{\"a}res Computing und Mashups die Medienlandschaft bereits grundlegend ver{\"a}ndert. Eine stetige technische und {\"o}konomische Weiterentwicklung dieser Ph{\"a}nomene kann allerdings nur auf den geleiteten Bahnen des Rechts stattfinden. Fraglich ist aber gerade - wie es im Bereich der neuen Medien so oft der Fall ist -, ob das Recht {\"u}ber die n{\"o}tigen Rahmenbedingungen verf{\"u}gt, um den besagten Entwicklungen entgegenzutreten. Das Memorandum Internet der Zukunft zeigt diese rechtlichen Hintergr{\"u}nde f{\"u}r die wichtigsten aktuellen IT-Erscheinungen auf und beleuchtet die besagten Ph{\"a}nomene aus technischer und {\"o}konomischer Sicht, was letztlich auch dem interdisziplin{\"a}ren Charakter der Rechtsinformatik Rechnung tr{\"a}gt.},
  subject      = {Cloud Computing},
  language  = {de}
}