Supervised student theses

[ 2021 ] [ 2020 ] [ 2019 ] [ 2018 ] [ 2017 ] [ 2016 ] [ 2014 ] [ 2012 ] [ 2011 ] [ 2010 ] [ 2009 ] [ 2007 ] [ 1999 ]

2021 [ to top ]

A Self-Learning Meta-Optimization Framework for Adaptation Planning. Hadry, Marius; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2021, May).

[ BibTeX ] [ EndNote ]

2020 [ to top ]

Situation-Aware Meta-Optimization of Platooning Coordination Strategies. Hefter, Johannes; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, September).

[ BibTeX ] [ EndNote ]

Optimizing Storage Assignment and Order Picking in Mezzanine Warehouses using Nature-Inspired Algorithms. Müller, Patrick; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, September).

[ BibTeX ] [ EndNote ]

Minimizing Makespan in Flow Shop Scheduling Problems Using Optimization Algorithms. Schleicher, Johannes; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, September).

[ BibTeX ] [ EndNote ]

Optimal Platooning Coordination using Multiple Objectives. Hoang Tran, Ha Giang; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, September).

[ BibTeX ] [ EndNote ]

Predicting Performance Degradations of Microservice Applications. Straesser, Martin; Thesis; University of Wuerzburg. (2020, May).

Wuerzburg Software Engineering Award 2020: Best Master Thesis

[ BibTeX ] [ EndNote ] [ Download ]

Solving the Rich Vehicle Routing Problem with Bio-inspired Algorithms. König, Maximilian; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, January).

[ BibTeX ] [ EndNote ]

Minimising Setup Times in Production Environments Using Nature-Inspired Optimisation. Hartmann, Stephan; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, March).

[ BibTeX ] [ EndNote ]

Combining Platooning with Corridor Control Systems. Johnson, Andre; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2020, November).

[ BibTeX ] [ EndNote ]

2019 [ to top ]

Comparison of Compensation Mechanisms for Intra-Platoon Position Effects. Stubenrauch, Kevin; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, July).

Würzburg Software Engineering Award sponsored by Bosch Rexroth

[ BibTeX ] [ EndNote ]

Towards Self-Aware Multirotor Formations. Kaiser, Dennis; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, September).

Würzburg Software Engineering Award sponsored by infosim

[ BibTeX ] [ EndNote ] [ Download ]

Neukonzeptualisierung des Programmiervorkurses mit Fokus auf Übung und Vertiefung. Migendt, Christian; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, July).

[ BibTeX ] [ EndNote ]

An Evaluation Tool for Cost-Aware Vehicle Route Calculation. Hadry, Marius; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, August).

[ BibTeX ] [ EndNote ]

Analysis of Centralized Platooning Coordination Approaches. Dalhof, Florian; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, August).

[ BibTeX ] [ EndNote ]

Mosquitto Swatter: Demonstrating MQTT Vulnerabilities. Metzler, Samuel; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, February).

[ BibTeX ] [ EndNote ]

Hypercall Interface Testing for the Example of Hyper-V. Beierlieb, Lukas; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, December).

Würzburg Software Engineering Award Runner Up Masterthesis

[ BibTeX ] [ EndNote ] [ Download ]

Heat-aware and CPU Boost-oriented Server Load Rotation. Knapp, Andreas; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, November).

[ BibTeX ] [ EndNote ]

Review of Security Mechanisms in Publish/Subscribe Systems and their Applicability in IoT Context. Geiger, Ariane; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2019, January).

[ BibTeX ] [ EndNote ]

2018 [ to top ]

Performance Evaluation of Security Network Function Reordering. Fella, Nicolas; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, December).

[ BibTeX ] [ EndNote ]

DIMAQS - Dynamic Identification of Malicious Query Sequences. Jobst, Michael; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, June).

[ BibTeX ] [ EndNote ]

Design of an Industry 4.0 Demonstrator. König, Philipp; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, September).

[ BibTeX ] [ EndNote ]

Automatic Identification of Parametric Dependencies for Performance Models. Elflein, Sven; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, September).

Würzburg Software Engineering Award sponsored by Bosch Rexroth

[ BibTeX ] [ EndNote ]

Fully Automated Deployment and Benchmarking of Security Information and Event Management Systems. Heilmann, Jan-Philipp; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, June).

[ BibTeX ] [ EndNote ]

P-Seminar: Umgang mit Mikroelektronik am Beispiel eines Quadrocopters. Otto, Rebecca; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, December).

[ BibTeX ] [ EndNote ]

Blackbox Learning of Parametric Dependencies for Performance Models from Monitoring Data. Ackermann, Vanessa; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, March).

[ BibTeX ] [ EndNote ]

Performance and Security Influence of Augmenting DDoS Protection Systems using SDN and NFV. Beierlieb, Lukas; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, January).

Würzburg Software Engineering Award sponsored by Infosim GmbH & Co. KG

[ BibTeX ] [ EndNote ] [ Download ]

An Evaluation and Benchmarking Solution for Security Information and Event Management Systemes. Ben Yahya, Ala Eddine; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2018, March).

[ BibTeX ] [ EndNote ]

2017 [ to top ]

Dynamic Hybrid Forecasting for Self-Aware Systems. Züfle, Marwin; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, October).

Würzburg Software Engineering Award sponsored by infosim

[ BibTeX ] [ EndNote ] [ Download ]

Model-Based Network Analysis and Optimization. Herrnleben, Stefan; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017).

Best Master Thesis Award 2018 of GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems (MMB)

[ BibTeX ] [ EndNote ] [ Download ]

Evaluation der Performanz von IDSes in virtualisierten Netzwerk-Infrastrukturen. Stoll, Jonathan; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, June).

[ BibTeX ] [ EndNote ]

Self-Aware Multidimensional Auto-Scaling. Lesch, Veronika; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, September).

Würzburg Software Engineering Award sponsored by Bosch Rexroth

[ BibTeX ] [ EndNote ] [ Download ]

Cybersecurity Risk Exposure: Towards a Novel Determination Approach based on OSINT. Leonhardt, Alexander; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, October).

[ BibTeX ] [ EndNote ]

A Framework for a Dynamic Function-Chaining-Controller for Virtualized Network Security Appliances. Ciner, Hayreddin; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, October).

[ BibTeX ] [ EndNote ]

A Packet-Filtering Firewall for Cloud Computing. Hempfling, Christina; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, September).

[ BibTeX ] [ EndNote ]

Evaluating Approaches for Online Resource Demand Estimation. Krauss, Torsten; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, September).

[ BibTeX ] [ EndNote ]

Cluster Analysis for Resource Demand Estimation. Schaefers, Karsten; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2017, August).

[ BibTeX ] [ EndNote ]

2016 [ to top ]

P-Seminar: Raspberry Pi als Mediencenter für die Oberstufe. Frauendorfer, Katja; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016, April).

[ BibTeX ] [ EndNote ]

Reliable Resource Demand Estimation. Grohmann, Johannes; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016, October).

[ Abstract ] [ BibTeX ] [ EndNote ]

Resource demands are key parameters of performance models used to predict the behavior of data centers. They define the amount of time a request spends obtaining a limited resource like the CPU. Requests can be grouped into different workload classes. Measuring these resource demands is usually unfeasible in practice. Therefore, several different approaches to estimate the resource demands of different workload classes exist. However, different use-cases with individual properties influence the accuracy of the estimators. Among others the number of different workload classes to estimate is known to have an impact on the solution quality, but affects some approaches more than others. Additionally, most approaches offer specific parameters to configure and optimize the estimators. Nevertheless, in order to optimize the parameters of one estimation approach or to choose the best estimator for a given scenario either expert knowledge or exhaustive testing is required. While some works on comparing different approaches and configurations exist, we extend this by learning on a given training set and specially adapting the estimation approaches in order to optimize performance for the required target scenario. We simplify automated resource demand estimation by designing a framework for ready-to-use reliable resource demand estimation. In order to do so, we develop generic algorithms that can be used to autonomously optimize parameter configurations of black-box estimation approaches on a given training set. Secondly, machine learning algorithms analyze the behavior of the resource demand estimators on different training traces and automatically pick the best approach for a prior unseen trace. The framework is modularized and configurable and can be trained on any kind of trace data. We implement different algorithms for optimization as well as machine learning and evaluate them on a training set containing measurements of a real system. The results show that parameter optimization is very promising and can increase the accuracy of single approaches of up to 10%. When recommending one approach as opposed to running all simultaneously, comparable results can be achieved, while saving more than 50% of the runtime. However, a combination of both approaches does not seem useful on our data set.

@mastersthesis{grohmann16,
  abstract = {Resource demands are key parameters of performance models used to predict the behavior of data centers. They define the amount of time a request spends obtaining a limited resource like the CPU. Requests can be grouped into different workload classes. Measuring these resource demands is usually unfeasible in practice. Therefore, several different approaches to estimate the resource demands of different workload classes exist. However, different use-cases with individual properties influence the accuracy of the estimators. Among others the number of different workload classes to estimate is known to have an impact on the solution quality, but affects some approaches more than others. Additionally, most approaches offer specific parameters to configure and optimize the estimators. Nevertheless, in order to optimize the parameters of one estimation approach or to choose the best estimator for a given scenario either expert knowledge or exhaustive testing is required. While some works on comparing different approaches and configurations exist, we extend this by learning on a given training set and specially adapting the estimation approaches in order to optimize performance for the required target scenario. We simplify automated resource demand estimation by designing a framework for ready-to-use reliable resource demand estimation. In order to do so, we develop generic algorithms that can be used to autonomously optimize parameter configurations of black-box estimation approaches on a given training set. Secondly, machine learning algorithms analyze the behavior of the resource demand estimators on different training traces and automatically pick the best approach for a prior unseen trace. The framework is modularized and configurable and can be trained on any kind of trace data. We implement different algorithms for optimization as well as machine learning and evaluate them on a training set containing measurements of a real system. The results show that parameter optimization is very promising and can increase the accuracy of single approaches of up to 10%. When recommending one approach as opposed to running all simultaneously, comparable results can be achieved, while saving more than 50% of the runtime. However, a combination of both approaches does not seem useful on our data set.},
  address = {Am Hubland, Informatikgeb{ä}ude, 97074 W{ü}rzburg, Germany},
  author = {Grohmann, Johannes},
  keywords = {Instrumentation_profiling_and_workload_characterization LibReDE Multi-criteria_optimization Optimization Resource_management Self-adaptive-systems Statistical_estimation_and_machine_learning Supervised_by_Nikolas_Herbst Thesis_supervised_by_SE_member Thesis_supervised_by_Simon_Spinner Tool descartes se2_mastersthesis t_studentthesis},
  month = {October},
  school = {University of W{ü}rzburg},
  title = {{Reliable Resource Demand Estimation}},
  type = {{Master Thesis}},
  year = 2016
}

%0 Thesis
%1 grohmann16
%A Grohmann, Johannes
%C Am Hubland, Informatikgebäude, 97074 Würzburg, Germany
%D 2016
%T Reliable Resource Demand Estimation
%X Resource demands are key parameters of performance models used to predict the behavior of data centers. They define the amount of time a request spends obtaining a limited resource like the CPU. Requests can be grouped into different workload classes. Measuring these resource demands is usually unfeasible in practice. Therefore, several different approaches to estimate the resource demands of different workload classes exist. However, different use-cases with individual properties influence the accuracy of the estimators. Among others the number of different workload classes to estimate is known to have an impact on the solution quality, but affects some approaches more than others. Additionally, most approaches offer specific parameters to configure and optimize the estimators. Nevertheless, in order to optimize the parameters of one estimation approach or to choose the best estimator for a given scenario either expert knowledge or exhaustive testing is required. While some works on comparing different approaches and configurations exist, we extend this by learning on a given training set and specially adapting the estimation approaches in order to optimize performance for the required target scenario. We simplify automated resource demand estimation by designing a framework for ready-to-use reliable resource demand estimation. In order to do so, we develop generic algorithms that can be used to autonomously optimize parameter configurations of black-box estimation approaches on a given training set. Secondly, machine learning algorithms analyze the behavior of the resource demand estimators on different training traces and automatically pick the best approach for a prior unseen trace. The framework is modularized and configurable and can be trained on any kind of trace data. We implement different algorithms for optimization as well as machine learning and evaluate them on a training set containing measurements of a real system. The results show that parameter optimization is very promising and can increase the accuracy of single approaches of up to 10%. When recommending one approach as opposed to running all simultaneously, comparable results can be achieved, while saving more than 50% of the runtime. However, a combination of both approaches does not seem useful on our data set.

Assessment of the Influence of I/O-Load Factors on Service Migration Performance. Liu, Xiaofen; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016, December).

[ BibTeX ] [ EndNote ]

Cyber-Physical Systems - Models and Security Aspects. Hempfling, Christina; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016, December).

[ BibTeX ] [ EndNote ]

Local Approximation of NFV Workloads. Schmitt, Norbert; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016, October).

[ BibTeX ] [ EndNote ] [ Download ]

Design and Evaluation of a Proactive, Application-Aware Elasticity Mechanism. Bauer, André; Thesis; University of Würzburg; Am Hubland, Informatikgebäude, 97074 Würzburg, Germany. (2016).

[ Abstract ] [ BibTeX ] [ EndNote ] [ Download ]

In order to guarantee a reliable service quality to their customers and due to the increasing complexity of cloud applications, SaaS cloud providers usually run their business critical applications with a fixed amount of resources. This approach has drawbacks such as a higher costs (e.g., bad energy efficiency, if the system is not fully utilized), or bad performance regarding unexpected work peaks. Amazon with its EC2, for instance, provides a configurable scheduled-based and rule-based auto-scaler. However, this reactive scaling has a latency depending on resource type in the order of minutes. Therefore, proactive and application aware auto-scalers are required - intelligent controllers, which can reconfigure the system on time, to ensure high availability and constant performance under changing conditions. The existing auto-scalers can be classified into five groups and prominent examples of each class were investigated. The result of this observation is that the existing controllers are either application-specific or generic. I.e. the auto-scalers can either perform well only on the chosen system or they perform far beyond their means. In this thesis, a novel proactive, application-aware elasticity mechanism called Chameleon is introduced. The proposed controller employs established forecast methods for short-, mid- and long-term predictions of the arriving load intensity, application knowledge, and resource demand estimation to calculate the required resources per work unit. While taking these information into account, the mechanism reconfigures the deployment of an application in a way that the supply of resources matches the current and estimated future demand for resources. I.e., Chameleon consists of two mechanisms: (I) a reactive rule-based controller as fall-back insurance and (II) a proactive controller which has three major building blocks: (a) continuous workload forecasting (using a modified version of WCF) with dynamic forecast method selection, (b) a descriptive performance model/ application knowledge (DML Model@RunTime), and (c) optimized resource demand estimation approaches (using the tool LibReDE). In the evaluation, Chameleon is compared against four different state-of-the-art controllers in a private CloudStack-based environment. The BUNGEE elasticity benchmark framework and metrics are used to conduct and analyse the row of experiments. As workload scenarios, a CPU intensive http application that solves nxn matrices (whereas n is the request parameter) and SPECjEnterprise2010 is used. The applications are driven with variable load profiles (extracted with LIMBO from the FIFA World Cup 1998 trace) generated with JMeter (instead of Faban - as classically used by SPECjEnterprise2010). During the CPU intensive scenario Chameleon achieves the best scaling behaviour (based on user and elasticity metrics) and in the SPECjEnterprise2010 the second best user metrics.

@mastersthesis{Bauer2016,
  abstract = {In order to guarantee a reliable service quality to their customers and due to the increasing complexity of cloud applications, SaaS cloud providers usually run their business critical applications with a fixed amount of resources. This approach has drawbacks such as a higher costs (e.g., bad energy efficiency, if the system is not fully utilized), or bad performance regarding unexpected work peaks. Amazon with its EC2, for instance, provides a configurable scheduled-based and rule-based auto-scaler. However, this reactive scaling has a latency depending on resource type in the order of minutes. Therefore, proactive and application aware auto-scalers are required - intelligent controllers, which can reconfigure the system on time, to ensure high availability and constant performance under changing conditions. The existing auto-scalers can be classified into five groups and prominent examples of each class were investigated. The result of this observation is that the existing controllers are either application-specific or generic. I.e. the auto-scalers can either perform well only on the chosen system or they perform far beyond their means. In this thesis, a novel proactive, application-aware elasticity mechanism called Chameleon is introduced. The proposed controller employs established forecast methods for short-, mid- and long-term predictions of the arriving load intensity, application knowledge, and resource demand estimation to calculate the required resources per work unit. While taking these information into account, the mechanism reconfigures the deployment of an application in a way that the supply of resources matches the current and estimated future demand for resources. I.e., Chameleon consists of two mechanisms: (I) a reactive rule-based controller as fall-back insurance and (II) a proactive controller which has three major building blocks: (a) continuous workload forecasting (using a modified version of WCF) with dynamic forecast method selection, (b) a descriptive performance model/ application knowledge (DML Model@RunTime), and (c) optimized resource demand estimation approaches (using the tool LibReDE). In the evaluation, Chameleon is compared against four different state-of-the-art controllers in a private CloudStack-based environment. The BUNGEE elasticity benchmark framework and metrics are used to conduct and analyse the row of experiments. As workload scenarios, a CPU intensive http application that solves nxn matrices (whereas n is the request parameter) and SPECjEnterprise2010 is used. The applications are driven with variable load profiles (extracted with LIMBO from the FIFA World Cup 1998 trace) generated with JMeter (instead of Faban - as classically used by SPECjEnterprise2010). During the CPU intensive scenario Chameleon achieves the best scaling behaviour (based on user and elasticity metrics) and in the SPECjEnterprise2010 the second best user metrics.},
  address = {Am Hubland, Informatikgeb{ä}ude, 97074 W{ü}rzburg, Germany},
  author = {Bauer, Andr{é}},
  keywords = {Analytical_and_simulation-based_analysis Application-aware BUNGEE Chameleon Cloud DML Elasticity Instrumentation_profiling_and_workload_characterization LIMBO LibReDE Metrics_and_benchmarking_methodologies Online_monitoring_and_forecasting Performance Power-energy_efficient_computing Prediction Resource_management SPEC Self-adaptive-systems Self-aware-computing Statistical_estimation_and_machine_learning Supervised_by_Nikolas_Herbst Thesis_supervised_by_SE_member Thesis_supervised_by_Simon_Spinner Virtualization WCF descartes se2_mastersthesis t_studentthesis},
  month = {Septembter},
  school = {University of W{ü}rzburg},
  title = {{Design and Evaluation of a Proactive, Application-Aware Elasticity Mechanism}},
  type = {{Master Thesis}},
  year = 2016
}

%0 Thesis
%1 Bauer2016
%A Bauer, André
%C Am Hubland, Informatikgebäude, 97074 Würzburg, Germany
%D 2016
%T Design and Evaluation of a Proactive, Application-Aware Elasticity Mechanism
%X In order to guarantee a reliable service quality to their customers and due to the increasing complexity of cloud applications, SaaS cloud providers usually run their business critical applications with a fixed amount of resources. This approach has drawbacks such as a higher costs (e.g., bad energy efficiency, if the system is not fully utilized), or bad performance regarding unexpected work peaks. Amazon with its EC2, for instance, provides a configurable scheduled-based and rule-based auto-scaler. However, this reactive scaling has a latency depending on resource type in the order of minutes. Therefore, proactive and application aware auto-scalers are required - intelligent controllers, which can reconfigure the system on time, to ensure high availability and constant performance under changing conditions. The existing auto-scalers can be classified into five groups and prominent examples of each class were investigated. The result of this observation is that the existing controllers are either application-specific or generic. I.e. the auto-scalers can either perform well only on the chosen system or they perform far beyond their means. In this thesis, a novel proactive, application-aware elasticity mechanism called Chameleon is introduced. The proposed controller employs established forecast methods for short-, mid- and long-term predictions of the arriving load intensity, application knowledge, and resource demand estimation to calculate the required resources per work unit. While taking these information into account, the mechanism reconfigures the deployment of an application in a way that the supply of resources matches the current and estimated future demand for resources. I.e., Chameleon consists of two mechanisms: (I) a reactive rule-based controller as fall-back insurance and (II) a proactive controller which has three major building blocks: (a) continuous workload forecasting (using a modified version of WCF) with dynamic forecast method selection, (b) a descriptive performance model/ application knowledge (DML Model@RunTime), and (c) optimized resource demand estimation approaches (using the tool LibReDE). In the evaluation, Chameleon is compared against four different state-of-the-art controllers in a private CloudStack-based environment. The BUNGEE elasticity benchmark framework and metrics are used to conduct and analyse the row of experiments. As workload scenarios, a CPU intensive http application that solves nxn matrices (whereas n is the request parameter) and SPECjEnterprise2010 is used. The applications are driven with variable load profiles (extracted with LIMBO from the FIFA World Cup 1998 trace) generated with JMeter (instead of Faban - as classically used by SPECjEnterprise2010). During the CPU intensive scenario Chameleon achieves the best scaling behaviour (based on user and elasticity metrics) and in the SPECjEnterprise2010 the second best user metrics.

2014 [ to top ]

Modeling Variations in Load Intensity Profiles. von Kistowski, Jóakim; Thesis; Karlsruhe Institute of Technology (KIT); Am Fasanengarten 5, 76131 Karlsruhe, Germany. (2014, March).

Gesellschaft zur Förderung des Forschungstransfers (GFFT) Prize "Best Master Thesis"

[ Abstract ] [ BibTeX ] [ EndNote ] [ Download ]

Today's software systems are expected to deliver reliable performance under highly variable load intensities while at the same time making efficient use of dynamically allocated resources. Conventional benchmarking frameworks provide limited support for emulating such highly variable and dynamic load profiles and workload scenarios. Industrial benchmarks typically use workloads with constant or stepwise increasing load intensity, or they simply replay recorded workload traces. Based on this observation, I identify the need for means allowing flexible definition of load profiles and address this by introducing two meta-models at different abstraction levels. At the lower abstraction level, the Descartes Load Intensity Meta-Model (DLIM) offers a structured and accessible way of describing the load intensity over time by editing and combining mathematical functions. The high-level Descartes Load Intensity Meta-Model (hl-DLIM) allows the description of load variations using few defined parameters that characterize the seasonal patterns, trends, bursts, and noise parts. Using these parameters, hl-DLIM is capable of describing a subset of most common load intensity variations. During the work on this thesis I developed LIMBO - an Eclipse-based tool for modeling variable load intensity profiles based on DLIM and hl-DLIM as underlying modeling formalisms. LIMBO provides visualization for DLIM instances and a model creation wizard based on hl-DLIM parameters. It also offers three automated model extraction processes with which to extract DLIM and hl-DLIM instances from existing arrival rate traces. It also offers a model-to-model transformation from hl-DLIM to DLIM. I demonstrate that both meta-models are capable of capturing real-world load profiles with acceptable accuracy, having an average median deviation of 19.9% from the original trace. This is done by comparing nine different real life traces, which were measured over duration of two weeks to seven months, to their respective model instances as extracted by the automated model extraction processes. I also evaluate the usability and accessibility of LIMBO based on a questionnaire which was answered by eight computer scientists from five different organizations within the performance engineering community.

@mastersthesis{Kistowski2014,
  abstract = {{Today's software systems are expected to deliver reliable performance under highly variable load intensities while at the same time making efficient use of dynamically allocated resources. Conventional benchmarking frameworks provide limited support for emulating such highly variable and dynamic load profiles and workload scenarios. Industrial benchmarks typically use workloads with constant or stepwise increasing load intensity, or they simply replay recorded workload traces. Based on this observation, I identify the need for means allowing flexible definition of load profiles and address this by introducing two meta-models at different abstraction levels. At the lower abstraction level, the Descartes Load Intensity Meta-Model (DLIM) offers a structured and accessible way of describing the load intensity over time by editing and combining mathematical functions. The high-level Descartes Load Intensity Meta-Model (hl-DLIM) allows the description of load variations using few defined parameters that characterize the seasonal patterns, trends, bursts, and noise parts. Using these parameters, hl-DLIM is capable of describing a subset of most common load intensity variations. During the work on this thesis I developed LIMBO - an Eclipse-based tool for modeling variable load intensity profiles based on DLIM and hl-DLIM as underlying modeling formalisms. LIMBO provides visualization for DLIM instances and a model creation wizard based on hl-DLIM parameters. It also offers three automated model extraction processes with which to extract DLIM and hl-DLIM instances from existing arrival rate traces. It also offers a model-to-model transformation from hl-DLIM to DLIM. I demonstrate that both meta-models are capable of capturing real-world load profiles with acceptable accuracy, having an average median deviation of 19.9\% from the original trace. This is done by comparing nine different real life traces, which were measured over duration of two weeks to seven months, to their respective model instances as extracted by the automated model extraction processes. I also evaluate the usability and accessibility of LIMBO based on a questionnaire which was answered by eight computer scientists from five different organizations within the performance engineering community.}},
  address = {Am Fasanengarten 5, 76131 Karlsruhe, Germany},
  author = {von Kistowski, J{ó}akim},
  keywords = {Automated_model_learning Award Cloud Instrumentation_profiling_and_workload_characterization LIMBO Meta-models Supervised_by_Nikolas_Herbst Thesis_supervised_by_SE_member Tool descartes t_studentthesis},
  month = {March},
  note = {<b>Gesellschaft zur F{ö}rderung des Forschungstransfers (GFFT) Prize "Best Master Thesis"</b>},
  school = {{Karlsruhe Institute of Technology (KIT)}},
  title = {{Modeling Variations in Load Intensity Profiles}},
  type = {{Master Thesis}},
  year = 2014
}

%0 Thesis
%1 Kistowski2014
%A von Kistowski, Jóakim
%C Am Fasanengarten 5, 76131 Karlsruhe, Germany
%D 2014
%T Modeling Variations in Load Intensity Profiles
%X Today's software systems are expected to deliver reliable performance under highly variable load intensities while at the same time making efficient use of dynamically allocated resources. Conventional benchmarking frameworks provide limited support for emulating such highly variable and dynamic load profiles and workload scenarios. Industrial benchmarks typically use workloads with constant or stepwise increasing load intensity, or they simply replay recorded workload traces. Based on this observation, I identify the need for means allowing flexible definition of load profiles and address this by introducing two meta-models at different abstraction levels. At the lower abstraction level, the Descartes Load Intensity Meta-Model (DLIM) offers a structured and accessible way of describing the load intensity over time by editing and combining mathematical functions. The high-level Descartes Load Intensity Meta-Model (hl-DLIM) allows the description of load variations using few defined parameters that characterize the seasonal patterns, trends, bursts, and noise parts. Using these parameters, hl-DLIM is capable of describing a subset of most common load intensity variations. During the work on this thesis I developed LIMBO - an Eclipse-based tool for modeling variable load intensity profiles based on DLIM and hl-DLIM as underlying modeling formalisms. LIMBO provides visualization for DLIM instances and a model creation wizard based on hl-DLIM parameters. It also offers three automated model extraction processes with which to extract DLIM and hl-DLIM instances from existing arrival rate traces. It also offers a model-to-model transformation from hl-DLIM to DLIM. I demonstrate that both meta-models are capable of capturing real-world load profiles with acceptable accuracy, having an average median deviation of 19.9% from the original trace. This is done by comparing nine different real life traces, which were measured over duration of two weeks to seven months, to their respective model instances as extracted by the automated model extraction processes. I also evaluate the usability and accessibility of LIMBO based on a questionnaire which was answered by eight computer scientists from five different organizations within the performance engineering community.

2012 [ to top ]

Workload Classification and Forecasting. Herbst, Nikolas Roman; Thesis; Karlsruhe Institute of Technology (KIT); Am Fasanengarten 5, 76131 Karlsruhe, Germany. (2012).

Forschungszentrum Informatik (FZI) Prize "Best Diploma Thesis"

[ Abstract ] [ BibTeX ] [ EndNote ] [ Download ]

Virtualization technologies enable dynamic allocation of computing resources to execution environments at run-time. To exploit optimisation potential that comes with these degrees of freedom, forecasts of the arriving work's intensity are valuable information, to continuously ensure a defined quality of service (QoS) definition and at the same time to improve the efficiency of the resource utilisation. Time series analysis offers a broad spectrum of methods for calculation of forecasts based on periodically monitored values. Related work in the field of proactive resource provisioning mostly concentrate on single methods of the time series analysis and their individual optimisation potential. This way, usable forecast results are achieved only in certain situations. In this thesis, established methods of the time series analysis are surveyed and grouped concerning their strengths and weaknesses. A dynamic approach is presented that selects based on a decision tree and direct feedback cycles, capturing the forecast accuracy, the suitable method for a given situation. The user needs to provide only his general forecast objectives. An implementation of the introduced theoretical approach is presented that continuously provides forecasts of the arriving work's intensity in configurable intervals and with controllable computational overhead during run-time. Based on real-world intensity traces, a number of different experiments and a case study is conducted. The results show, that by use of the implementation the relative error of the forecast points in relation to the arriving observations is reduced by 63% in average compared to the results of a statically selected, sophisticated method. In a case study, between 52% and 70% of the violations of a given service level agreement are prevented by applying proactive resource provisioning based on the forecast results of the introduced implementation.

@mastersthesis{Herbst2012a,
  abstract = {{Virtualization technologies enable dynamic allocation of computing resources to execution environments at run-time. To exploit optimisation potential that comes with these degrees of freedom, forecasts of the arriving work's intensity are valuable information, to continuously ensure a defined quality of service (QoS) definition and at the same time to improve the efficiency of the resource utilisation. Time series analysis offers a broad spectrum of methods for calculation of forecasts based on periodically monitored values. Related work in the field of proactive resource provisioning mostly concentrate on single methods of the time series analysis and their individual optimisation potential. This way, usable forecast results are achieved only in certain situations. In this thesis, established methods of the time series analysis are surveyed and grouped concerning their strengths and weaknesses. A dynamic approach is presented that selects based on a decision tree and direct feedback cycles, capturing the forecast accuracy, the suitable method for a given situation. The user needs to provide only his general forecast objectives. An implementation of the introduced theoretical approach is presented that continuously provides forecasts of the arriving work's intensity in configurable intervals and with controllable computational overhead during run-time. Based on real-world intensity traces, a number of different experiments and a case study is conducted. The results show, that by use of the implementation the relative error of the forecast points in relation to the arriving observations is reduced by 63% in average compared to the results of a statically selected, sophisticated method. In a case study, between 52% and 70% of the violations of a given service level agreement are prevented by applying proactive resource provisioning based on the forecast results of the introduced implementation.}},
  address = {Am Fasanengarten 5, 76131 Karlsruhe, Germany},
  author = {Herbst, Nikolas Roman},
  keywords = {Award Cloud Online_monitoring_and_forecasting Prediction Resource_management Statistical_estimation_and_machine_learning Thesis_supervised_by_Nikolaus_Huber Thesis_supervised_by_SE_member Tool WCF descartes se2_mastersthesis t_studentthesis},
  note = {<b>Forschungszentrum Informatik (FZI) Prize "Best Diploma Thesis"</b>},
  school = {{Karlsruhe Institute of Technology (KIT)}},
  title = {{Workload Classification and Forecasting}},
  type = {{Diploma Thesis}},
  year = 2012
}

%0 Thesis
%1 Herbst2012a
%A Herbst, Nikolas Roman
%C Am Fasanengarten 5, 76131 Karlsruhe, Germany
%D 2012
%T Workload Classification and Forecasting
%X Virtualization technologies enable dynamic allocation of computing resources to execution environments at run-time. To exploit optimisation potential that comes with these degrees of freedom, forecasts of the arriving work's intensity are valuable information, to continuously ensure a defined quality of service (QoS) definition and at the same time to improve the efficiency of the resource utilisation. Time series analysis offers a broad spectrum of methods for calculation of forecasts based on periodically monitored values. Related work in the field of proactive resource provisioning mostly concentrate on single methods of the time series analysis and their individual optimisation potential. This way, usable forecast results are achieved only in certain situations. In this thesis, established methods of the time series analysis are surveyed and grouped concerning their strengths and weaknesses. A dynamic approach is presented that selects based on a decision tree and direct feedback cycles, capturing the forecast accuracy, the suitable method for a given situation. The user needs to provide only his general forecast objectives. An implementation of the introduced theoretical approach is presented that continuously provides forecasts of the arriving work's intensity in configurable intervals and with controllable computational overhead during run-time. Based on real-world intensity traces, a number of different experiments and a case study is conducted. The results show, that by use of the implementation the relative error of the forecast points in relation to the arriving observations is reduced by 63% in average compared to the results of a statically selected, sophisticated method. In a case study, between 52% and 70% of the violations of a given service level agreement are prevented by applying proactive resource provisioning based on the forecast results of the introduced implementation.

2011 [ to top ]

Quantifying the Impact of Configuration Space for Elasticity Benchmarking. Herbst, Nikolas Roman; Thesis; Karlsruhe Institute of Technology (KIT); Am Fasanengarten 5, 76131 Karlsruhe, Germany. (2011).

[ Abstract ] [ BibTeX ] [ EndNote ] [ Download ]

Defining and Measuring Workloads for Elasticity Benchmarking. von Kistowski, Jóakim; Thesis; Karlsruhe Institute of Technology (KIT); Am Fasanengarten 5, 76131 Karlsruhe, Germany. (2011).

[ BibTeX ] [ EndNote ]

2010 [ to top ]

Combination of measurement and model based approaches for performance prediction in service oriented systems. Krebs, Rouven; Thesis; University of Applied Sciences Karlsruhe; Moltkestr. 30, 76133 Karlsruhe, Germany. (2010, October).

[ BibTeX ] [ EndNote ]

Focusing the Optimization of Software Architecture Models Using Non-Functional Requirements. Noorshams, Qais; Thesis; Karlsruhe Institute of Technology; Karlsruhe, Germany. (2010).

[ BibTeX ] [ EndNote ] [ Download ]

2009 [ to top ]

Performance Modeling of Storage Virtualization. Huber, Nikolaus; Thesis; Universität Karlsruhe (TH); Karlsruhe, Germany. (2009, April).

GFFT Prize

[ BibTeX ] [ EndNote ] [ Download ]

Automated Extraction of Palladio Component Models from Running Enterprise Java Applications. Brosig, Fabian; Thesis; Universität Karlsruhe (TH); Karlsruhe, Germany. (2009, June).

FZI Prize "Best Diploma Thesis"

[ BibTeX ] [ EndNote ] [ Download ]

Software implementation of the simulation environment of the system for multistage parallel processing of teletraffic in the node of the packet-switched network for traffic control algorithms performance analysis purposes. Rygielski, Piotr; Thesis; Wroclaw University of Technology; Wybrze.ze Wyspiańskiego 27, 50-370 Wroclaw, Poland. (2009, July).

The work is written in Polish language.

[ Abstract ] [ BibTeX ] [ EndNote ] [ Download ]

2007 [ to top ]

Eine Managementinfrastruktur für die Überwachung komponierter Webservices. Rathfelder, Christoph; Thesis; Universit"at Karlsruhe (TH); Karlsruhe. (2007).

[ BibTeX ] [ EndNote ]

1999 [ to top ]

Design and Development of an Electronic Commerce Environment. Kounev, Samuel; Thesis; University of Sofia; Sofia, Bulgaria. (1999, August).

[ BibTeX ] [ EndNote ]

Supervised student theses

Data privacy protection

Data privacy protection

Picture credits