Modern IT infrastructures are constructed by large scale computing systems and administered by IT service providers. Manually maintaining such large computing systems is costly and inefficient. Service providers often seek automatic or semi-automatic methodologies of detecting and resolving system issues to improve their service quality and efficiency. This dissertation investigates several data-driven approaches for assisting service providers in achieving this goal. The detailed problems studied by these approaches can be categorized into the three aspects in the service workflow: 1) preprocessing raw textual system logs to structural events; 2) refining monitoring configurations for eliminating false positives and false negatives; 3) improving the efficiency of system diagnosis on detected alerts. Solving these problems usually requires a huge amount of domain knowledge about the particular computing systems. The approaches investigated by this dissertation are developed based on event mining algorithms, which are able to automatically derive part of that knowledge from the historical system logs, events and tickets. In particular, two textual clustering algorithms are developed for converting raw textual logs into system events. For refining the monitoring configuration, a rule based alert prediction algorithm is proposed for eliminating false alerts (false positives) without losing any real alert and a textual classification method is applied to identify the missing alerts (false negatives) from manual incident tickets. For system diagnosis, this dissertation presents an efficient algorithm for discovering the temporal dependencies between system events with corresponding time lags, which can help the administrators to determine the redundancies of deployed monitoring situations and dependencies of system components. To improve the efficiency of incident ticket resolving, several KNN-based algorithms that recommend relevant historical tickets with resolutions for incoming tickets are investigated. Finally, this dissertation offers a novel algorithm for searching similar textual event segments over large system logs that assists administrators to locate similar system behaviors in the logs. Extensive empirical evaluation on system logs, events and tickets from real IT infrastructures demonstrates the effectiveness and efficiency of the proposed approaches.

The Internet of today is very different from how it used to be. Modern networked applications are becoming increasingly diverse. Consequently, a variety of requirements must be met by the network. Efforts to make the underlying mechanisms of the Internet more flexible have therefore been made to adapt to this diversification. In this thesis, we explore how information about application requirements can be leveraged to optimize the network protocol stack of end-hosts during run-time. In addition, we improve the visibility of the network to the end-host in order to enable additional flexibility in the usage of the network's resources. We conduct tests in real-world testbeds and examine how services might be developed to optimize latency, throughput, and availability for various network traffic scenarios, including 360-degree video streaming, drone autopilots, and connected vehicles. We show how multi-connectivity, where the end-host is connected via multiple network paths simultaneously, may be used to significantly reduce latency and increase availability, while minimizing the overhead imposed on the network by carefully considering the network selection process. Furthermore, we describe an architecture that allows the user equipment and network functionality inside the 5G core network to cooperatively optimize the resource usage of the network. / The Internet of today is very different from how it used to be. Modern networked applications are becoming increasingly diverse. Consequently, a variety of requirements must be met by the network. This presents a massive challenge, since the Internet was originally designed on best-effort principle.  To address this challenge, we explore how Internet end-hosts can flexibly adapt to the needs of individual applications, by dynamically configuring the network protocol stack during run-time. In addition, we improve the visibility of the network, allowing end-hosts to better utilize the resources of the network.  We conduct tests in real-world testbeds and examine how services might be developed to optimize latency, throughput, and availability for various network traffic scenarios. We also show how multiple network paths can be used simultaneously to significantly reduce latency and increase availability, while minimizing the overhead imposed on the network. Furthermore, we describe an architecture that allows the user equipment and network functionality inside the 5G core network to cooperatively optimize the resource usage of the network. / <p>Paper II was published as a manuscript in the thesis. It is an extended version of the paper, which adds additional material that had to be cut from the original paper due to page limit restrictions.</p>

In future service markets a selection of functionally equal services is omnipresent. The evolving challenge, finding the best-fit service, requires a distinction between the non-functional service characteristics (e.g., response time, price, availability). Service providers commonly capture those quality characteristics in so-called Service Level Agreements (SLAs). However, a service selection based on SLAs is inadequate, because the static SLAs generally do not consider the dynamic service behaviors and quality changes in a service-oriented environment. Furthermore, the profit-oriented service providers tend to embellish their SLAs by flexibly handling their correctness. Within the SOC (Service Oriented Computing) research project of the Karlsruhe University of Applied Sciences and the Linnaeus University of Sweden, a service broker framework for an optimized web service selection is introduced. Instead of relying on the providers’ quality assertions, a distributed knowledge is developed by automatically monitoring and measuring the service quality during each service consumption. The broker aims at optimizing the service selection based on the past real service performances and the defined quality preferences of a unique consumer.This thesis work concerns the design, implementation and evaluation of appropriate machine learning methods with focus on the broker’s best-fit web service selection. Within the time-critical service optimization the performance and scalability of the broker’s machine learning plays an important role. Therefore, high- performance algorithms for predicting the future non-functional service characteristics within a continuous machine learning process were implemented. The introduced so-called foreground-/background-model enables to separate the real-time request for a best-fit service selection from the time-consuming machine learning. The best-fit services for certain consumer call contexts (e.g., call location and time, quality preferences) are continuously pre-determined within the asynchronous background-model. Through this any performance issues within the critical path from the service request up to the best-fit service recommendation are eliminated. For evaluating the implemented best-fit service selection a sophisticated test data scenario with real-world characteristics was created showing services with different volatile performances, cyclic performance behaviors and performance changes in the course of time. Besides the significantly improved performance, the new implementation achieved an overall high selection accuracy. It was possible to determine in 70% of all service optimizations the actual best-fit service and in 94% of all service optimizations the actual two best-fit services.

abstract: Optimization of on-demand transportation systems and ride-sharing services involves solving a class of complex vehicle routing problems with pickup and delivery with time windows (VRPPDTW). Previous research has made a number of important contributions to the challenging pickup and delivery problem along different formulation or solution approaches. However, there are a number of modeling and algorithmic challenges for a large-scale deployment of a vehicle routing and scheduling algorithm, especially for regional networks with various road capacity and traffic delay constraints on freeway bottlenecks and signal timing on urban streets. The main thrust of this research is constructing hyper-networks to implicitly impose complicated constraints of a vehicle routing problem (VRP) into the model within the network construction. This research introduces a new methodology based on hyper-networks to solve the very important vehicle routing problem for the case of generic ride-sharing problem. Then, the idea of hyper-networks is applied for (1) solving the pickup and delivery problem with synchronized transfers, (2) computing resource hyper-prisms for sustainable transportation planning in the field of time-geography, and (3) providing an integrated framework that fully captures the interactions between supply and demand dimensions of travel to model the implications of advanced technologies and mobility services on traveler behavior. / Dissertation/Thesis / Doctoral Dissertation Civil, Environmental and Sustainable Engineering 2018