TY - JOUR A1 - Elseberg, Jan A1 - Borrmann, Dorit A1 - Nüchter, Andreas T1 - Algorithmic Solutions for Computing Precise Maximum Likelihood 3D Point Clouds from Mobile Laser Scanning Platforms JF - Remote Sensing N2 - Mobile laser scanning puts high requirements on the accuracy of the positioning systems and the calibration of the measurement system. We present a novel algorithmic approach for calibration with the goal of improving the measurement accuracy of mobile laser scanners. We describe a general framework for calibrating mobile sensor platforms that estimates all configuration parameters for any arrangement of positioning sensors, including odometry. In addition, we present a novel semi-rigid Simultaneous Localization and Mapping (SLAM) algorithm that corrects the vehicle position at every point in time along its trajectory, while simultaneously improving the quality and precision of the entire acquired point cloud. Using this algorithm, the temporary failure of accurate external positioning systems or the lack thereof can be compensated for. We demonstrate the capabilities of the two newly proposed algorithms on a wide variety of datasets. KW - mapping KW - calibration KW - non-rigid registration KW - mobile laser scanning KW - algorithms Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-130478 VL - 5 IS - 11 ER - TY - JOUR A1 - Becker, Martin A1 - Caminiti, Saverio A1 - Fiorella, Donato A1 - Francis, Louise A1 - Gravino, Pietro A1 - Haklay, Mordechai (Muki) A1 - Hotho, Andreas A1 - Loreto, Virrorio A1 - Mueller, Juergen A1 - Ricchiuti, Ferdinando A1 - Servedio, Vito D. P. A1 - Sirbu, Alina A1 - Tria, Franesca T1 - Awareness and Learning in Participatory Noise Sensing JF - PLOS ONE N2 - The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments. KW - exposure Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-127675 SN - 1932-6203 VL - 8 IS - 12 ER - TY - JOUR A1 - Gageik, Nils A1 - Strohmeier, Michael A1 - Montenegro, Sergio T1 - Waypoint flight parameter comparison of an autonomous UAV JF - International Journal of Artificial Intelligence & Applications (IJAIA) N2 - The present paper compares the effect of different waypoint parameters on the flight performance of a special autonomous indoor UAV (unmanned aerial vehicle) fusing ultrasonic, inertial, pressure and optical sensors for 3D positioning and controlling. The investigated parameters are the acceptance threshold for reaching a waypoint as well as the maximal waypoint step size or block size. The effect of these parameters on the flight time and accuracy of the flight path is investigated. Therefore the paper addresses how the acceptance threshold and step size influence the speed and accuracy of the autonomous flight and thus influence the performance of the presented autonomous quadrocopter under real indoor navigation circumstances. Furthermore the paper demonstrates a drawback of the standard potential field method for navigation of such autonomous quadrocopters and points to an improvement. KW - autonomous UAV KW - Quadrocopter KW - Quadrotor KW - waypoint parameter KW - navigation Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-96833 ER - TY - JOUR A1 - Gageik, Nils A1 - Strohmeier, Michael A1 - Montenegro, Sergio T1 - An Autonomous UAV with an Optical Flow Sensor for Positioning and Navigation JF - International Journal of Advanced Robotic Systems N2 - A procedure to control all six DOF (degrees of freedom) of a UAV (unmanned aerial vehicle) without an external reference system and to enable fully autonomous flight is presented here. For 2D positioning the principle of optical flow is used. Together with the output of height estimation, fusing ultrasonic, infrared and inertial and pressure sensor data, the 3D position of the UAV can be computed, controlled and steered. All data processing is done on the UAV. An external computer with a pathway planning interface is for commanding purposes only. The presented system is part of the AQopterI8 project, which aims to develop an autonomous flying quadrocopter for indoor application. The focus of this paper is 2D positioning using an optical flow sensor. As a result of the performed evaluation, it can be concluded that for position hold, the standard deviation of the position error is 10cm and after landing the position error is about 30cm. KW - Autonomous UAV KW - Quadrocopter KW - Quadrotor KW - Optical Flow KW - positioning KW - navigation Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-96368 ER - TY - THES A1 - Sieber, Christian T1 - Holistic Evaluation of Novel Adaptation Logics for DASH and SVC T1 - Leistungsbewertung neuartiger Adaptionslogiken für DASH mit SVC N2 - Streaming of videos has become the major traffic generator in today's Internet and the video traffic share is still increasing. According to Cisco's annual Visual Networking Index report, in 2012, 60% of the global Internet IP traffic was generated by video streaming services. Furthermore, the study predicts further increase to 73% by 2017. At the same time, advances in the fields of mobile communications and embedded devices lead to a widespread adoption of Internet video enabled mobile and wireless devices (e.g. Smartphones). The report predicts that by 2017, the traffic originating from mobile and wireless devices will exceed the traffic from wired devices and states that mobile video traffic was the source of roughly half of the mobile IP traffic at the end of 2012. With the increasing importance of Internet video streaming in today's world, video content provider find themselves in a highly competitive market where user expectations are high and customer loyalty depends strongly on the user's satisfaction with the provided service. In particular paying customers expect their viewing experience to be the same across all their viewing devices and independently of their currently utilized Internet access technology. However, providing video streaming services is costly in terms of storage space, required bandwidth and generated traffic. Therefore, content providers face a trade-off between the user perceived Quality of Experience (QoE) and the costs for providing the service. Today, a variety of transport and application protocols exist for providing video streaming services, but the one utilized depends on the scenario in mind. Video streaming services can be divided up in three categories: Video conferencing, IPTV and Video-on-Demand services. IPTV and video-conferencing have severe real-time constraints and thus utilize mostly datagram-based protocols like the RTP/UDP protocol for the video transmission. Video-on-Demand services in contrast can profit from pre-encoded content, buffers at the end user's device, and mostly utilize TCP-based protocols in combination with progressive streaming for the media delivery. In recent years, the HTTP protocol on top of the TCP protocol gained widespread popularity as a cost-efficient way to distribute pre-encoded video content to customers via progressive streaming. This is due to the fact that HTTP-based video streaming profits from a well-established infrastructure which was originally implemented to efficiently satisfy the increasing demand for web browsing and file downloads. Large Content Delivery Networks (CDN) are the key components of that distribution infrastructure. CDNs prevent expensive long-haul data traffic and delays by distributing HTTP content to world-wide locations close to the customers. As of 2012, already 53% of the global video traffic in the Internet originates from Content Delivery Networks and that percentage is expected to increase to 65% by the year 2017. Furthermore, HTTP media streaming profits from existing HTTP caching infrastructure, ease of NAT and proxy traversal and firewall friendliness. Video delivery through heterogeneous wired and wireless communications networks is prone to distortions due to insufficient network resources. This is especially true in wireless scenarios, where user mobility and insufficient signal strength can result in a very poor transport service performance (e.g. high packet loss, delays and low and varying bandwidth). A poor performance of the transport in turn may degrade the Quality of Experience as perceived by the user, either due to buffer underruns (i.e. playback interruptions) for TCP-based delivery or image distortions for datagram-based real-time video delivery. In order to overcome QoE degradations due to insufficient network resources, content provider have to consider adaptive video streaming. One possibility to implement this for HTTP/TCP streaming is by partitioning the content into small segments, encode the segments into different quality levels and provide access to the segments and the quality level details (e.g. resolution, average bitrate). During the streaming session, a client-centric adaptation algorithm can use the supplied details to adapt the playback to the current environment. However, a lack of a common HTTP adaptive streaming standard led to multiple proprietary solutions developed by major Internet companies like Microsoft (Smooth Streaming), Apple (HTTP Live Streaming) and Adobe (HTTP Dynamic Streaming) loosely based on the aforementioned principle. In 2012, the ISO/IEC published the Dynamic Adaptive Streaming over HTTP (MPEG-DASH) standard. As of today, DASH is becoming widely accepted with major companies announcing their support or having already implemented the standard into their products. MPEG-DASH is typically used with single layer codecs like H.264/AVC, but recent publications show that scalable video coding can use the existing HTTP infrastructure more efficiently. Furthermore, the layered approach of scalable video coding extends the adaptation options for the client, since already downloaded segments can be enhanced at a later time. The influence of distortions on the perceived QoE for non-adaptive video streaming are well reviewed and published. For HTTP streaming, the QoE of the user is influenced by the initial delay (i.e. the time the client pre-buffers video data) and the length and frequency of playback interruptions due to a depleted video playback buffer. Studies highlight that even low stalling times and frequencies have a negative impact on the QoE of the user and should therefore be avoided. The first contribution of this thesis is the identification of QoE influence factors of adaptive video streaming by the means of crowd-sourcing and a laboratory study. MPEG-DASH does not specify how to adapt the playback to the available bandwidth and therefore the design of a download/adaptation algorithm is left to the developer of the client logic. The second contribution of this thesis is the design of a novel user-centric adaption logic for DASH with SVC. Other download algorithms for segmented HTTP streaming with single layer and scalable video coding have been published lately. However, there is little information about the behavior of these algorithms regarding the identified QoE-influence factors. The third contribution is a user-centric performance evaluation of three existing adaptation algorithms and a comparison to the proposed algorithm. In the performance evaluation we also evaluate the fairness of the algorithms. In one fairness scenario, two clients deploy the same adaptation algorithm and share one Internet connection. For a fair adaptation algorithm, we expect the behavior of the two clients to be identical. In a second fairness scenario, one client shares the Internet connection with a large HTTP file download and we expect an even bandwidth distribution between the video streaming and the file download. The forth contribution of this thesis is an evaluation of the behavior of the algorithms in a two-client and HTTP cross traffic scenario. The remainder of this thesis is structured as follows. Chapter II gives a brief introduction to video coding with H.264, the HTTP adaptive streaming standard MPEG-DASH, the investigated adaptation algorithms and metrics of Quality of Experience (QoE) for video streaming. Chapter III presents the methodology and results of the subjective studies conducted in the course of this thesis to identify the QoE influence factors of adaptive video streaming. In Chapter IV, we introduce the proposed adaptation algorithm and the methodology of the performance evaluation. Chapter V highlights the results of the performance evaluation and compares the investigated adaptation algorithms. Section VI summarizes the main findings and gives an outlook towards QoE-centric management of DASH with SVC. KW - DASH KW - DASH KW - SVC KW - crowdsourcing KW - quality of experience KW - qoe KW - progressive download KW - dynamic adaptive streaming over http Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-92362 ER - TY - THES A1 - Herrmann, Christian T1 - Robotic Motion Compensation for Applications in Radiation Oncology T1 - Robotergestützte Bewegungskompensation für Anwendungen in der Radioonkologie N2 - Aufgrund vieler Verbesserungen der Behandlungsmethoden im Laufe der letzten 60 Jahre, erlaubt die Strahlentherapie heutzutage präzise Behandlungen von statischen Tumoren. Jedoch birgt die Bestrahlung von sich bewegenden Tumoren noch große Herausforderungen in sich, da bewegliche Tumore oft den Behandlungsstrahl verlassen. Dabei reduziert sich die Strahlendosis im Tumor während sich diese im umliegenden gesunden Gewebe erhöht. Diese Forschungsarbeit zielt darauf ab, die Grenzen der Strahlentherapie zu erweitern, um präzise Behandlungen von beweglichen Tumoren zu ermöglichen. Der Fokus der Arbeit liegt auf der Erstellung eines Echtzeitsystems zur aktiven Kompensation von Tumorbewegungen durch robotergestützte Methoden. Während Behandlungen befinden sich Patienten auf einer Patientenliege, mit der statische Lagerungsfehler vor Beginn einer Behandlung korrigiert werden. Die in dieser Arbeit verwendete Patientenliege "HexaPOD" ist ein paralleler Manipulator mit sechs Freiheitsgraden, der große Lasten innerhalb eines eingeschränkten Arbeitsbereichs präzise positionieren kann. Obwohl der HexaPOD ursprünglich nicht für dynamische Anwendungen konzipiert wurde, wird dieser für eine dauerhafte Bewegungskompensation eingesetzt, in dem Patienten so bewegt werden, dass Tumore präzise im Zentralstrahl während der Dauer einer gesamten Behandlung verbleiben. Um ein echtzeitfähiges Kompensationssystem auf Basis des HexaPODs zu realisieren, muss eine Reihe an Herausforderungen bewältigt werden. Echtzeitaspekte werden einerseits durch die Verwendung eines harten Echtzeitbetriebssystems abgedeckt, andererseits durch die Messung und Schätzung von Latenzzeiten aller physikalischen Größen im System, z.B. Messungen der Tumor- und Atemposition. Neben der konsistenten und durchgängigen Berücksichtigung von akkuraten Zeitinformation, werden alle software-induzierten Latenzen adaptiv ausgeglichen. Dies erfordert Vorhersagen der Tumorposition in die nahe Zukunft. Zahlreiche Prädiktoren zur Atem- und Tumorpositionsvorhersage werden vorgeschlagen und anhand verschiedenster Metriken evaluiert. Erweiterungen der Prädiktionsalgorithmen werden eingeführt, die sowohl Atem- als auch Tumorpositionsinformationen fusionieren, um Vorhersagen ohne explizites Korrelationsmodell zu ermöglichen. Die Vorhersagen bestimmen den zukünftigen Bewegungspfad des HexaPODs, um Tumorbewegungen zu kompensieren. Dazu werden verschiedene Regler entwickelt, die eine Trajektorienverfolgung mit dem HexaPOD ermöglichen. Auf der Basis von linearer und nicht-linearer dynamischer Modellierung des HexaPODs mit Methoden der Systemidentifikation, wird zunächst ein modellprädiktiver Regler entwickelt. Ein zweiter Regler wird auf Basis einer Annahme über das Arbeitsprinzip des internen Reglers im HexaPOD entworfen. Schließlich wird ein dritter Regler vorgeschlagen, der beide vorhergehenden Regler miteinander kombiniert. Für jeden dieser Regler werden vergleichende Ergebnisse aus Experimenten mit realer Hardware und menschlichen Versuchspersonen präsentiert und diskutiert. Darüber hinaus wird die geeignete Wahl von freien Parametern in den Reglern vorgestellt. Neben einer präzisen Verfolgung der Referenztrajektorie spielt der Patientenkomfort eine entscheidende Rolle für die Akzeptanz des Systems. Es wird gezeigt, dass die Regler glatte Trajektorien realisieren können, um zu garantieren, dass sich Patienten wohl fühlen während ihre Tumorbewegung mit Genauigkeiten im Submillimeterbereich ausgeglichen wird. Gesamtfehler werden im Kompensationssystem analysiert, in dem diese zu Trajektorienverfolgungsfehlern und Prädiktionsfehlern in Beziehung gesetzt werden. Durch Ausnutzung von Eigenschaften verschiedener Prädiktoren wird gezeigt, dass die Startzeit des Systems bis die Verfolgung der Referenztrajektorie erreicht ist, wenige Sekunden beträgt. Dies gilt insbesondere für den Fall eines initial ruhenden HexaPODs und ohne Vorwissen über Tumorbewegungen. Dies zeigt die Eignung des Systems für die sehr kurz fraktionierten Behandlungen von Lungentumoren. Das Tumorkompensationssystem wurde ausschließlich auf Basis von klinischer Standard-Hardware entwickelt, die in vielen Behandlungsräumen zu finden ist. Durch ein einfaches und flexibles Design können Behandlungsräume in kosteneffizienter Weise um Möglichkeiten der Bewegungskompensation ergänzt werden. Darüber hinaus werden aktuelle Behandlungsmethoden wie intensitätsmodulierte Strahlentherapie oder Volumetric Modulated Arc Therapy in keiner Weise eingeschränkt. Aufgrund der Unterstützung verschiedener Kompensationsmodi kann das System auf alle beweglichen Tumore angewendet werden, unabhängig davon ob die Bewegungen vorhersagbar (Lungentumore) oder nicht vorhersagbar (Prostatatumore) sind. Durch Integration von geeigneten Methoden zur Tumorpositionsbestimmung kann das System auf einfache Weise zur Kompensation von anderen Tumoren erweitert werden. N2 - Radiation therapy today, on account of improvements in treatment procedures over the last 60 years, allows precise treatment of static tumors inside the human body. However, irradiation of moving tumors is still a challenging task as moving tumors often leave the treatment beam and the radiation dose delivered to the tumor reduces simultaneously increasing that on healthy tissue. This research work aims to push the frontiers of radiation therapy in order to enable precise treatment of moving tumors with focus on research and development of a unique real-time system enabling active motion compensation through robotic means to compensate tumor motion. During treatment, patients lie on a treatment couch which is normally used for static position corrections of patient set-up errors prior to radiation treatment. The treatment couch used, called HexaPOD, is a parallel manipulator with six degrees of freedom which can precisely position heavy loads inside a small region. Despite the HexaPOD not initially built with dynamics in mind, it is used in this work for sustained motion compensation by moving patients such that tumors stay precisely located at the center of the treatment beam during the complete course of treatment. In order to realize real-time tumor motion compensation by means of the HexaPOD, several challanges need to be addressed. Real-time aspects are covered by the adoption of a hard real-time operation system in combination with measurement and estimation of latencies of all physical quantities in the compensation system such as tumor or breathing position measurements. Accurate timing information is respected consistently in the whole system and all software-induced latencies are adaptively compensated for. This requires knowledge of future tumor positions from predictors. Several predictors for breathing and tumor motion predictions are proposed and evaluated in terms of a variety of different performance metrics. Extensions to prediction algorithms are introduced fusing both breathing and tumor position information to allow for predictions without the need of an explicit correlation model. Predictions determine the future motion path of the HexaPOD in order to compensate for tumor motion. Several control schemes are developed to enable reference tracking for the HexaPOD. Based on linear and non-linear dynamic modelling of the HexaPOD with system identification methods, a first controller is derived in the form of a model predictive controller. A second controller is proposed based on an assumption of the working principle of the HexaPOD's internal controller. Finally, a third controller is derived as combination of the first and second one. For each of these controllers, comparative results with real hardware experiments and humans in the loop as well as choices of free parameters are presented and discussed. Apart from precise tracking, emphasis is placed on patient comfort which is of crucial importance for acceptance of the system. It is demonstrated that smooth trajectories can be realized by the controllers to guarantee that patients feel comfortable while their tumor motion is compensated at sub-millimeter accuracies. Overall errors of the system are analyzed by relating them to tracking and prediction errors. By exploiting the properties of different predictors, it is shown that the startup time until tracking is reached can be reduced to only a few seconds, even in the case of an initially at-rest HexaPOD and with no initial knowledge of tumor motion. This makes the system especially suitable for the relatively short-fractionated treatment sessions for lung tumors. The tumor motion compensation system has been developed solely based on standard clinical hardware, found in most treatment rooms. With a simple and flexible design, existing treatment can be updated in a cost-efficient way to introduce motion compensation capabilities. Simultaneously, the system does not impose any constraints on state-of-the-art treatment types such as intensity modulated radiotherapy or volumetric modulated arc therapy. Supporting different compensation modes, the system can be applied to any moving tumor whether its motion is predictable (lung tumors) or unpredictable (prostate tumors). By integration of adequate tumor position determination methods, the system can be easily extended to other tumors as well. T3 - Forschungsberichte in der Robotik = Research Notes in Robotics - 7 KW - Robotik KW - Bewegungskompensation KW - Regelung KW - Strahlentherapie KW - Vorhersage KW - Tumorbewegung KW - Echzeit KW - Prediction KW - Tumor motion KW - Real-time Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-79045 SN - 978-3-923959-88-4 ER - TY - THES A1 - Lehrieder, Frank T1 - Performance Evaluation and Optimization of Content Distribution using Overlay Networks T1 - Leistungsbewertung und Optimierung von Overlay Netzwerken zum Verteilen großer Datenmengen N2 - The work presents a performance evaluation and optimization of so-called overlay networks for content distribution in the Internet. Chapter 1 describes the importance which have such networks in today's Internet, for example, for the transmission of video content. The focus of this work is on overlay networks based on the peer-to-peer principle. These are characterized by the fact that users who download content, also contribute to the distribution process by sharing parts of the data to other users. This enables efficient content distribution because each user not only consumes resources in the system, but also provides its own resources. Chapter 2 of the monograph contains a detailed description of the functionality of today's most popular overlay network BitTorrent. It explains the various components and their interaction. This is followed by an illustration of why such overlay networks for Internet service providers (ISPs) are problematic. The reason lies in the large amount of inter-ISP traffic that is produced by these overlay networks. Since this inter-ISP traffic leads to high costs for ISPs, they try to reduce it by improved mechanisms for overlay networks. One optimization approach is the use of topology awareness within the overlay networks. It provides users of the overlay networks with information about the underlying physical network topology. This allows them to avoid inter-ISP traffic by exchanging data preferrentially with other users that are connected to the same ISP. Another approach to save inter-ISP traffic is caching. In this case the ISP provides additional computers in its network, called caches, which store copies of popular content. The users of this ISP can then obtain such content from the cache. This prevents that the content must be retrieved from locations outside of the ISP's network, and saves costly inter-ISP traffic in this way. In the third chapter of the thesis, the results of a comprehensive measurement study of overlay networks, which can be found in today's Internet, are presented. After a short description of the measurement methodology, the results of the measurements are described. These results contain data on a variety of characteristics of current P2P overlay networks in the Internet. These include the popularity of content, i.e., how many users are interested in specific content, the evolution of the popularity and the size of the files. The distribution of users within the Internet is investigated in detail. Special attention is given to the number of users that exchange a particular file within the same ISP. On the basis of these measurement results, an estimation of the traffic savings that can achieved by topology awareness is derived. This new estimation is of scientific and practical importance, since it is not limited to individual ISPs and files, but considers the whole Internet and the total amount of data exchanged in overlay networks. Finally, the characteristics of regional content are considered, in which the popularity is limited to certain parts of the Internet. This is for example the case of videos in German, Italian or French language. Chapter 4 of the thesis is devoted to the optimization of overlay networks for content distribution through caching. It presents a deterministic flow model that describes the influence of caches. On the basis of this model, it derives an estimate of the inter-ISP traffic that is generated by an overlay network, and which part can be saved by caches. The results show that the influence of the cache depends on the structure of the overlay networks, and that caches can also lead to an increase in inter-ISP traffic under certain circumstances. The described model is thus an important tool for ISPs to decide for which overlay networks caches are useful and to dimension them. Chapter 5 summarizes the content of the work and emphasizes the importance of the findings. In addition, it explains how the findings can be applied to the optimization of future overlay networks. Special attention is given to the growing importance of video-on-demand and real-time video transmissions. N2 - Die Arbeit beschäftigt sich mit der Leistungsbewertung und Optimierung von sogenannten Overlay-Netzwerken zum Verteilen von großen Datenmengen im Internet. Im Kapitel 1 der Arbeit wird die große Bedeutung erläutert, die solche Netzwerke im heutigen Internet haben, beispielsweise für die Übertragung von Video-Inhalten. Im Fokus der Arbeit liegen Overlay-Netzwerke, die auf dem Peer-to-peer Prinzip basieren. Diese zeichnen sich dadurch aus, dass Nutzer, die Inhalte herunterladen, auch gleichzeitig an dem Verteilprozess teilnehmen, indem sie Teile der Daten an andere Nutzer weitergeben. Dies ermöglicht eine effiziente Verteilung der Daten, weil jeder Nutzer nicht nur Ressourcen im System belegt, sondern auch eigene Ressourcen einbringt. Kapitel 2 der Arbeit enthält eine detaillierte Beschreibung der Funktionsweise des heute populärsten Overlay-Netzwerks BitTorrent. Es werden die einzelnen Komponenten erläutert und deren Zusammenspiel erklärt. Darauf folgt eine Darstellung, warum solche Overlay-Netzwerke für Internet-Anbieter (Internet service provider, ISP) problematisch sind. Der Grund dafür liegt in der großen Menge an Inter-ISP Verkehr, den diese Overlays erzeugen. Da solcher Inter-ISP Verkehr zu hohen Kosten für ISPs führt, versuchen diese den Inter-ISP Verkehr zu reduzieren, indem sie die Mechanismen der Overlay-Netzwerke optimieren. Ein Ansatz zur Optimierung ist die Verwendung von Topologiebewusstsein innerhalb der Overlay-Netzwerke. Dabei erhalten die Nutzer der Overlay-Netzwerke Informationen über die zugrunde liegende, physikalische Netzwerktopologie. Diese ermöglichen es ihnen, Inter-ISP Verkehr zu vermeiden, indem sie Daten bevorzugt mit anderen Nutzern austauschen, die mit dem gleichen ISP verbunden sind. Ein weiterer Ansatz, um Inter-ISP Verkehr einzusparen, ist Caching. Dabei stellt der ISP zusätzliche Rechner, sogenannte Caches, in seinem Netzwerk zur Verfügung, die Kopien populärer Inhalte zwischenspeichern. Die Nutzer dieses ISP können solche Inhalte nun von den Caches beziehen. Dies verhindert, dass populäre Inhalte mehrfach von außerhalb des betrachteten ISPs bezogen werden müssen, und spart so kostenintensiven Inter-ISP Verkehr ein. Im dritten Kapitel der Arbeit werden Ergebnisse einer umfassenden Messung von Overlay-Netzwerken vorgestellt, wie sie heute im Internet anzutreffen sind. Nach einer kurzen Darstellung der bei der Messung verwendeten Methodik werden die Resultate der Messungen beschrieben. Diese Ergebnisse enthalten Daten über eine Vielzahl von Eigenschaften von heutigen P2P-basierten Overlay-Netzwerken im Internet. Dazu zählen die Popularität von Inhalten, d.h., wie viele Nutzer an bestimmten Inhalten interessiert sind, die zeitliche Entwicklung der Popularität und die Größe der Daten. Im Detail wird auch die Verteilung der Nutzer über das Internet analysiert. Ein besonderes Augenmerk liegt dabei auf der Anzahl der Nutzer, die gleichzeitig und im Netz desselben ISP eine bestimmte Datei tauschen. Auf der Basis dieser Messergebnisse wird eine Abschätzung durchgeführt, welches Einsparpotential die Optimierung von Overlay-Netzwerken durch Topologiebewusstsein bietet. Diese neuartige Abschätzung ist von wissenschaftlicher und praktischer Bedeutung, da sie sich nicht auf einzelne ISPs und Dateien beschränkt, sondern des gesamte Internet und die Menge aller in Overlay-Netzwerken verfügbaren Dateien umfasst. Schließlich werden die Besonderheiten von regionalen Inhalten betrachtet, bei denen sich die Popularität auf bestimmte Teile des Internets beschränkt. Dies ist beispielsweise bei Videos in deutscher, italienischer oder französischer Sprache der Fall. Kapitel 4 der Arbeit widmet sich der Optimierung von Overlay-Netzwerken zum Verteilen großer Datenmengen durch Caching. Es wird ein deterministisches Flussmodel entwickelt, das den Einfluss von Caches beschreibt. Auf der Basis dieses Modells leitet er eine Abschätzung des Inter-ISP Verkehrs ab, der von einem Overlay-Netzwerk erzeugt wird, und welcher Teil davon durch Caches eingespart werden kann. Die Ergebnisse zeigen, dass der Einfluss von Caches von der Struktur der Overlay-Netzwerke abhängt und dass Caches unter bestimmten Umständen auch zu einem erhöhten Inter-ISP Verkehr führen können. Das beschriebene Modell ist somit ein wichtiges Hilfsmittel für ISPs um zu entscheiden, für welche Overlay-Netzwerke Caches sinnvoll sind, und um diese anschließend richtig zu dimensionieren. Kapitel 5 fasst den Inhalt der Arbeit zusammen und stellt die Bedeutung der gewonnenen Erkenntnisse heraus. Abschließend wird erläutert, in welcher Weise die in der Arbeit beschriebenen Ergebnisse wichtige Grundlagen für die Optimierung von zukünftigen Overlay-Netzwerken darstellen werden. Dabei wird besonders auf die wachsende Bedeutung von Video-On-Demand und Echt-Zeit Video-Übertragungen eingegangen. T3 - Würzburger Beiträge zur Leistungsbewertung Verteilter Systeme - 01/13 KW - Leistungsbewertung KW - Verteiltes System KW - Overlay-Netz KW - Overlay Netzwerke KW - Overlay networks Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-76018 ER -