Context : Big Data and Cloud Computing nowadays require large amounts of storage that are accessible by many servers. The Energy consumed by these servers as well as that consumed by hosts providing the storage has been growing rapidly over the recent years. There are various approaches to save energy both at the hardware and software level, respectively. In the context of software, this challenge requires identification of new development methodologies that can help reduce the energy footprint of the Distributed Storage System. Until recently, reducing the energy footprint of Distributed Storage Systems is a challenge because there is no new methodology implemented to reduce the energy footprint of the Distributed Storage Systems. To tackle this challenge, we evaluate the energy consumption of Distributed Storage Systems by using a Power Application Programming Interface (PowerAPI) that monitors, in real-time, the energy consumed at the granularity of a system process. Objectives : In this study we investigate the Energy Consumption of distributed storage system. We also attempt to understand the effect on energy consumption for various patters of video streams. Also we have observed different measurement approaches for energy performance. Methods : The method is to use a power measuring software library while a synthetic load generator generates the load i.e., video data streams. The Tool which generates the workload is Standard Performance Evaluation Corporation Solution File Server (SPECsfs 2014) and PowerAPI is the software power monitoring library to evaluate the energy consumption of distributed storage systems of GlusterFS and Compuverde. Results : The mean and median values of power samples in mill watts for Compuverde higher than Gluster. For Compuverde the mean and median values until the load increment of three streams was around a 400 milliwatt value. The values of mean and median for the Gluster system were gradually increasing. Conclusions : The results show Compuverde having a higher consumption of energy than Gluster as it has a higher number of running processes that implement additional features that do not exist in Gluster. Also we have concluded that the conpuverde performed better for higher values of Load i.e., video data streams. / <p>Topic : Evaluating Energy Consumption of Distributed Storage Systems</p><p>Advisor: Dr. Dragos Ilie, Senior Lecturer, BTH</p><p>External Advisor: Stefan Bernbo,CEO, Compuverde AB</p><p>Student: Samuel Sushanth Kolli</p><p>The report gives a clear description of Distributed Storage Sytems and their Energy consumption with Performance Evaluation.</p><p>The report also includes the complete description and working of SpecSFS 2014 and PowerAPI Tool.</p> / Performance Evaluation of Distributed Storage Systems

Desde sus inicios, los juegos se caracterizaban por ser un sistema de entretenimiento dedicado a ofrecer momentos de relajación y diversión para una o más personas. En un primer momento, el reto de los video-juegos era desarrollado por el propio sistema del juego. Es decir, la gente elegía el nivel de dificultad con el que quería jugar y, de esa manera, el juego adaptaba el nivel de sus retos. Eso ha empezado a pasar a un segundo plano. A partir de las década de 1990, los juegos han empezado a desarrollar juegos que cuenten con la posibilidad de enfrentar a usuarios de diversas partes del mundo a través de Internet. Uno de estos tantos juegos es el que se está presentando en cuestión para la investigación: Dota 2. No suficiente con eso, en la actualidad, juegos como Dota 2, que resaltan por la manera en que han desarrollado la competencia en línea, empiezan a ser disfrutados por sus usuarios no solo al momento de jugar. La observación de partidas ajenas se muestra como un disfrute para muchos jugadores. Lo que la gente está haciendo es aprovechar esta situación y empieza a transmitir en vivo sus juegos, lo cual pasa a convertirse en una especie de programa audiovisual para los seguidores del juego. / Tesis

The current data-intensive world is continuously producing huge volumes of live streaming data through various kinds of electronic devices, such as sensor networks, smart phones, GPS and RFID systems. To understand these data sources and thus better leverage them to serve human society, the demands for mining complex patterns from these high speed data streams have significantly increased in a broad range of application domains, such as financial analysis, social network analysis, credit fraud detection, and moving object monitoring. In this dissertation, we present a framework to tackle the mining and management problem for the family of neighbor-based patterns in data streams, which covers a broad range of popular pattern types, including clusters, outliers, k-nearest neighbors and others. First, we study the problem of efficiently executing single neighbor-based pattern mining queries. We propose a general optimization principle for incremental pattern maintenance in data streams, called "Predicted Views". This general optimization principle exploits the "predictability" of sliding window semantics to eliminate both the computational and storage effort needed for handling the expiration of stream objects, which usually constitutes the most expensive operations for incremental pattern maintenance. Second, the problem of multiple query optimization for neighbor-based pattern mining queries is analyzed, which aims to efficiently execute a heavy workload of neighbor-based pattern mining queries using shared execution strategies. We present an integrated pattern maintenance strategy to represent and incrementally maintain the patterns identified by queries with different query parameters within a single compact structure. Our solution realizes fully shared execution of multiple queries with arbitrary parameter settings. Third, the problem of summarization and matching for neighbor-based patterns is examined. To solve this problem, we first propose a summarization format for each pattern type. Then, we present computation strategies, which efficiently summarize the neighbor-based patterns either during or after the online pattern extraction process. Lastly, to compare patterns extracted on different time horizon of the stream, we design an efficient matching mechanism to identify similar patterns in the stream history for any given pattern of interest to an analyst. Our comprehensive experimental studies, using both synthetic as well as real data from domains of stock trades and moving object monitoring, demonstrate superiority of our proposed strategies over alternate methods in both effectiveness and efficiency.

Many modern applications, including online financial feeds, tag-based mass transit systems and RFID-based supply chain management systems transmit real-time data streams. There is a need for event stream processing technology to analyze this vast amount of sequential data to enable online operational decision making. This dissertation focuses on innovating several techniques at the core of a scalable E-Analytic system to achieve efficient, scalable and robust methods for in-memory multi-dimensional nested pattern analysis over high-speed event streams. First, I address the problem of processing flat pattern queries on event streams with out-of-order data arrival. I design two alternate solutions: aggressive and conservative strategies respectively. The aggressive strategy produces maximal output under the optimistic assumption that out-of-order event arrival is rare. The conservative method works under the assumption that out-of-order data may be common, and thus produces output only when its correctness can be guaranteed. Second, I design the integration of CEP and OLAP techniques (ECube model) for efficient multi-dimensional event pattern analysis at different abstraction levels. Strategies of drill-down (refinement from abstract to specific patterns) and of roll-up (generalization from specific to abstract patterns) are developed for the efficient workload evaluation. I design a cost-driven adaptive optimizer called Chase that exploits reuse strategies for optimal E-Cube hierarchy execution. Then, I explore novel optimization techniques to support the high- performance processing of powerful nested CEP patterns. A CEP query language called NEEL, is designed to express nested CEP pattern queries composed of sequence, negation, AND and OR operators. To allow flexible execution ordering, I devise a normalization procedure that employs rewriting rules for flattening a nested complex event expression. To conserve CPU and memory consumption, I propose several strategies for efficient shared processing of groups of normalized NEEL subexpressions. Our comprehensive experimental studies, using both synthetic as well as real data streams demonstrate superiority of our proposed strategies over alternate methods in the literature in both effectiveness and efficiency.

With the steady increase in the bandwidth available to end users and Web sites hosting user generated content, there appears to be more multimedia content on the Web than ever before. Studies to quantify media stored on the Web done in 1997 and 2003 are now dated since the nature, size and number of streaming media objects on the Web have changed considerably. Although there have been more recent studies characterizing specific streaming media sites like YouTube, there are only a few studies that focus on characterizing the media stored on the Web as a whole. We build customized tools to crawl the Web, identify streaming media content and extract the characteristics of the streaming media found. We choose 16 different starting points and crawled 1.25 million Web pages from each starting point. Using the custom built tools, the media objects are identified and analyzed to determine attributes including media type, media length, codecs used for encoding, encoded bitrate, resolution, and aspect ratio. A little over half the media clips we encountered are video. MP3 and AAC are the most prevalent audio codecs whereas H.264 and FLV are the most common video codecs. The median size and encoded bitrates of stored media have increased since the last study. Information on the characteristics of stored multimedia and their trends over time can help system designers. The results can also be useful for empirical Internet measurements studies that attempt to mimic the behavior of streaming media traffic over the Internet.

Drones can be used for several civil applications including search and rescue, coverage, and aerial imaging. Newer applications like construction and delivery of goods are also emerging. Performing tasks as a team of drones is often beneficial but requires coordination through communication. In this thesis, the communication requirements of video streaming drone applications based on existing works are studied. The existing communication technologies are then analyzed to understand if the communication requirements posed by these drone applications can be met by the available technologies. The shortcomings of existing technologies with respect to drone applications are identified and potential requirements for future technologies are suggested. The existing communication and routing protocols including ad-hoc on-demand distance vector (AODV), location-aided routing (LAR), and greedy perimeter stateless routing (GPSR) protocols are studied to identify their limitations in context to the drone networks. An application scenario where a team of drones covers multiple areas of interest is considered, where the drones follow known trajectories and transmit continuous streams of sensed traffic (images or video) to a ground station. A route switching (RS) algorithm is proposed that utilizes both the location and the trajectory information of the drones to schedule and update routes to overcome route discovery and route error overhead. Simulation results show that the RS scheme outperforms LAR and AODV by achieving higher network performance in terms of throughput and delay. Video streaming drone applications such as search and rescue, surveillance, and disaster management, benefit from multicast wireless video streaming to transmit identical data to multiple users. Video multicast streaming using IEEE 802.11 poses challenges of reliability, performance, and fairness under tight delay bounds. Because of the mobility of the video sources and the high data-rate of the videos, the transmission rate should be adapted based on receivers' link conditions. Rate-adaptive video multicast streaming in IEEE 802.11 requires wireless link estimation as well as frequent feedback from multiple receivers. A contribution to this thesis is an application-layer rate-adaptive video multicast streaming framework using an 802.11 ad-hoc network that is applicable when both the sender and the receiver nodes are mobile. The receiver nodes of a multicast group are assigned with roles dynamically based on their link conditions. An application layer video multicast gateway (ALVM-GW) adapts the transmission rate and the video encoding rate based on the received feedback. Role switching between multiple receiver nodes (designated nodes) cater for mobility and rate adaptation addresses the challenges of performance and fairness. The reliability challenge is addressed through re-transmission of lost packets while delays under given bounds are achieved through video encoding rate adaptation. Emulation and experimental results show that the proposed approach outperforms legacy multicast in terms of packet loss and video quality.

Kong Chun Wai. / Thesis submitted in: July 2003. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 53-54). / Abstracts in English and Chinese. / Contents / acknowledgement --- p.I / Abstract --- p.II / 摘要 --- p.III / Chapter Chapter 1 --- Introduction --- p.1 / Chapter Chapter 2 --- Related Works --- p.4 / Chapter 2.1 --- Previous Work --- p.4 / Chapter 2.2 --- Comparison --- p.5 / Chapter Chapter 3 --- System Architecture --- p.7 / Chapter 3.1 --- Transmission Scheduling --- p.7 / Chapter 3.2 --- Admission Control --- p.9 / Chapter 3.3 --- Challenges in Supporting VBR-encoded Video --- p.10 / Chapter Chapter 4 --- Priority Scheduling --- p.12 / Chapter 4.1 --- Static Channel Priority (SCP) --- p.13 / Chapter 4.2 --- Dynamic Channel Priority (DCP) --- p.16 / Chapter Chapter 5 --- Turbo-Slice-and-Patch --- p.19 / Chapter 5.1 --- Video Pre-processing --- p.19 / Chapter 5.2 --- Bandwidth Allocation --- p.22 / Chapter 5.3 --- Three-Phase Patching --- p.23 / Chapter 5.4 --- Client Buffer Requirement --- p.27 / Chapter Chapter 6 --- Playback Continuity --- p.30 / Chapter Chapter 7 --- Performance Evaluation --- p.39 / Chapter 7.1 --- Average Latency --- p.40 / Chapter 7.2 --- Client Buffer Requirement --- p.43 / Chapter 7.3 --- Choice of Parameter Rcut --- p.44 / Chapter 7.4 --- Latency versus Arrival Rate --- p.46 / Chapter 7.5 --- Server Bandwidth Comparison --- p.48 / Chapter 7.6 --- Bandwidth Partitioning --- p.50 / Chapter Chapter 8 --- Conclusions --- p.52 / Bibliography --- p.53

Wong Ying Wai. / Thesis submitted in: December 2003. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 64-66). / Abstracts in English and Chinese. / Acknowledgement --- p.I / Abstract --- p.II / 摘要 --- p.III / Chapter Part I - --- Recursive Patching --- p.1 / Chapter Chapter 1 --- Introduction --- p.2 / Chapter Chapter 2 --- Transition Patching --- p.5 / Chapter Chapter 3 --- Recursive Patching --- p.9 / Chapter Chapter 4 --- Stream Assignment --- p.12 / Chapter 4.1 --- The Equal-Split Stream Assignment Scheme --- p.12 / Chapter 4.2 --- A Hierarchical Equal-Split Stream Assignment Scheme --- p.14 / Chapter Chapter 5 --- Performance Evaluation --- p.16 / Chapter Chapter 6 --- Conclusion --- p.18 / Bibliography --- p.19 / Chapter Part II - --- Interactive Multicast Video Streaming --- p.21 / Chapter Chapter 1 --- Introduction --- p.22 / Chapter Chapter 2 --- Background --- p.25 / Chapter 2.1 --- Multicast Streaming Algorithms --- p.25 / Chapter 2.2 --- Interactive Playback Support --- p.30 / Chapter Chapter 3 --- Interactive Multicast Streaming --- p.34 / Chapter 3.1 --- Interactivity Model --- p.34 / Chapter 3.2 --- Request Scheduling --- p.36 / Chapter 3.3 --- Client Buffer Management --- p.37 / Chapter 3.4 --- Performance Impact --- p.39 / Chapter Chapter 4 --- Static Full Stream Scheduling --- p.45 / Chapter Chapter 5 --- Adaptive Full Stream Scheduling --- p.48 / Chapter Chapter 6 --- Performance Evaluation --- p.52 / Chapter 6.1 --- Optimization of the Full Stream Threshold --- p.52 / Chapter 6.2 --- Latencies Comparisons --- p.57 / Chapter 6.3 --- Effect of Client Buffer Constraint --- p.58 / Chapter 6.4 --- Just-in-Time Simulation --- p.60 / Chapter Chapter 7 --- Conclusion --- p.63 / Bibliography --- p.64

Seminario para optar al titulo de Ingeniero Comercial, mención Administración / En el mundo digital del siglo 21, hemos alcanzado la instantaneidad, accediendo a servicios, contenido y entretenimiento de manera expedita. Conveniencia que sólo el mundo digital y su codificación nos permite articular, en un mundo cada día más actualizado/conectado. Al punto que podemos disfrutar el último episodio de nuestra serie favorita, donde queramos y cuando queramos, gracias a servicios como Netflix. Tomar un taxi a cualquier hora del día gracias a Uber. O encontrar acomodación para un viaje de negocios, gracias a servicios como Airbnb. Así mismo. Existen tecnologías en la industria de la música que nos permite escuchar a nuestros favoritos al alcance de un dispositivo, accediendo a una biblioteca prácticamente inconmensurable, al momento que deseemos. ¡Parece ser demasiado bueno para ser cierto! Sin duda, este tipo de plataforma de negocios debe ser sustentado por varías aristas que nos gustaría analizar en este trabajo, para esclarecer el deparar de los artistas quienes proveen a estos servicios de “streaming” de su contenido y el negocio que se monta a fin de cuentas Cabe destacar que la instauración de estos servicios no sólo han traído nuevas oportunidades para los músicos contemporáneos como alcanzar una exposición prácticamente global. Sino además desafíos que la conveniencia digital conlleva consigo misma. Vale decir, los “royalties” por derechos de autor han ido constantemente hacia la baja, creando un hoyo en el reditúo de los artistas por el uso de sus obras. Actualmente se vive ese escenario en el mundo del “streaming” digital, ese trade-­‐off entre exposición de marca el cual es asegurado por el servicio de “streaming”, a cambio de los “royalties” asociados a dichos trabajos. De primera impresión, esto parece ser altamente desfavorable para los artistas (creadores de contenido), no obstante este trabajo pretende encontrar puntos de inflexión donde esta condición pueda ser explotada de manera redituable por parte de los artistas.

L'augmentation de l'utilisation de l'Internet et des services de données motive l'évolution des réseaux cellulaires de troisième. Dans ce contexte, HSDPA (High Speed Downlink Packet Access) a été développé dans les releases 5 et 6 au sein de 3GPP pour poursuivre l'évolution du mode "paquet" de l'UMTS. Ce système utilise de nouvelles technologies telles que le Hybrid-ARQ (Automatic Repeat Request), la modulation adaptative et l'ordonnancement rapide (fast Scheduling) pour permettre de véhiculer des débits plus élevés sur l'interface radio et d'augmenter la capacité. Cette thèse se focalise sur l'analyse et la modélisation des interactions entre la couche MAC-hs de HSDPA et les autres couches (physique, transport). L'objectif est de trouver la configuration optimale de cette entité MAC-hs afin de réduire les interactions "négatives" entre-couches et optimiser les performances de HSDPA. Par conséquent, cette thèse fournit des études et des modélisations analytiques couvrant les aspects suivants: -Analyse et modélisation de l'impact du canal radio (shadowing, fast fading) sur les performances du système HSDPA dans le cas où plusieurs "schedulers" sont utilisés -Analyse et modélisation de l'effect des services "Circuit" de l'UMTS R99 sur les performances de HSDPA. -Modélisation de l'interaction entre le protocole TCP et l'entité MAC-hs. Une nouvelle stratégie d'ordonnancement est proposée afin d'améliorer les performances du système -Charactérisation de l'interaction entre MAc-hs et les services streaming. Une nouveau "scheduler" est proposé afin de garantir les contraintes sévères de QoS des services streaming sans trop perdre de capacité cellulaire.