Large scale distributed computing systems have been extensively utilized to host critical applications in the fields of national defense, finance, scientific research, commerce, etc. However, applications in distributed systems face the risk of service outages due to inevitable faults. Without proper fault management methods, faults can lead to significant revenue loss and degradation of Quality of Service (QoS). An ideal fault management solution should guarantee fast and accurate fault diagnosis, scalability in distributed systems, portability for a variety of systems, and the versatility of recovering different types of faults. This dissertation presents a model-based fault management structure which automatically recovers computing systems from faults. This structure can recover a system from common faults while minimizing the impact on the system’s QoS. It covers all stages of fault management including fault detection, identification and recovery. It also has the flexibility to incorporate various fault diagnosis methods. When faults occur, the approach identifies fault types and intensity, and it accordingly computes the optimal recovery plan with minimum performance degradation, based on a cost function that defines performance objectives and a predictive control algorithm. The fault management approach has been verified on a centralized Web application testbed and a distributed big data processing testbed with four types of simulated faults: memory leak, network congestion, CPU hog and disk failure. The feasibility of the fault recovery control algorithm is also verified. Simulation results show that our approach enabled effective automatic recovery from faults. Performance evaluation reveals that CPU and memory overhead of the fault management process is negligible. To let domain engineers conveniently apply the proposed fault management structure on their specific systems, a component-based modeling environment is developed. The meta-model of the fault management structure is developed with Unified Modeling Language as an abstract of a general fault recovery solution for computing systems. It defines the fundamental reusable components that comprise such a system, including the connections among them, attributes of each component and constraints. The meta-model can be interpreted into a userriendly graphic modeling environment for creating application models of practical domain specific systems and generating executable codes on them.

Advanced architectures for cluster-based services that have been recently proposed allow for service differentiation, server overload control and high utilization of resources. These systems, however, rely on centralized functions, which limit their ability to scale and to tolerate faults. In addition, they do not have built-in architectural support for automatic reconfiguration in case of failures or addition/removal of system components. Recent research in peer-to-peer systems and distributed management has demonstrated the potential benefits of decentralized over centralized designs: a decentralized design can reduce the configuration complexity of a system and increase its scalability and fault tolerance. This research focuses on introducing self-management capabilities into the design of cluster-based services. Its intended benefits are to make service platforms dynamically adapt to the needs of customers and to environment changes, while giving the service providers the capability to adjust operational policies at run-time. We have developed a decentralized design that efficiently allocates resources among multiple services inside a server cluster. The design combines the advantages of both centralized and decentralized architectures. It allows associating a set of QoS objectives with each service. In case of overload or failures, the quality of service degrades in a controllable manner. We have evaluated the performance of our design through extensive simulations. The results have been compared with performance characteristics of ideal systems. / QC 20101123

No description available.

Video-On-Demand (VOD) has appeared as an important technology for many multimedia applications such as news on demand, digital libraries, home entertainment, and distance learning. In its simplest form, delivery of a video stream requires a dedicated channel for each video session. This scheme is very expensive and non-scalable. To preserve server bandwidth, many users can share a channel using multicast. Two types of multicast have been considered. In a non-periodic multicast setting, users make video requests to the server; and it serves them according to some scheduling policy. In a periodic broadcast environment, the server does not wait for service requests. It broadcasts a video cyclically, e.g., a new stream of the same video is started every t seconds. Although, this type of approach does not guarantee true VOD, the worst service latency experienced by any client is less than t seconds. A distinct advantage of this approach is that it can serve a very large community of users using minimal server bandwidth. In VOD System it is desirable to provide the user with the video-cassette-recorder-like (VCR) capabilities such as fast-forwarding a video or jumping to a specific frame. This issue in the broadcast framework is addressed, where each video and its interactive version are broadcast repeatedly on the network. Existing techniques rely on data prefetching as the mechanism to provide this functionality. This approach provides limited usability since the prefetching rate cannot keep up with typical fast-forward speeds. In the same environment, end users might have access to different bandwidth capabilities at different times. Current periodic broadcast schemes, do not take advantage of high-bandwidth capabilities, nor do they adapt to the low-bandwidth limitation of the receivers. A heterogeneous technique is presented that can adapt to a range of receiving bandwidth capability. Given a server bandwidth and a range of different client bandwidths, users employing the proposed technique will choose either to use their full reception bandwidth capability and therefore accessing the video at a very short time, or using part or enough reception bandwidth at the expense of a longer access latency.

With the emergence of various applications that have different Quality of Service (QoS) requirements, the capability of a network to support QoS becomes more and more important and necessary. This dissertation explores QoS in Cognitive Packet Networks (CPN) by using adaptive routing, flow and congestion control. We present a detailed description and analysis of our proposed routing algorithms based on single and multiple QoS constraints. An online estimation of packet loss rate over a path is introduced. We implement and evaluate the adaptive routing scheme in an experimental CPN test-bed. Our experiments support our claims that the users can achieve their desired best-effort QoS through this routing scheme. We also propose a QoS-based flow and congestion control scheme that is built in the transport layer and specially designed to work with CPN to support users' QoS while remaining friendly to TCP. Theoretical models and experimental analysis are presented. Finally we experimentally demonstrate that the proposed flow and congestion control scheme can effectively control the input flows, react to the congestion and work with our proposed adaptive routing scheme to achieve users' QoS.

Wireless ad hoc network consists of inexpensive nodes that form a mobile communication network. Due to limitations of the transmission range, the nodes rely on each other to forward packets such that messages can be delivered across the network. The selection of the path along which a packet is forwarded from the source node to the destination node is done by the routing algorithm. Most commonly used routing algorithms, though effective for non-real time applications, cannot handle real-time applications that require strict delay bounds on packet delivery. In this thesis, we propose a routing protocol that ensures timely delivery of real time data packets. The idea is to route packets in such a way that irrespective of factors like traffic load and node density, the average delay remains within acceptable bounds. This is done by carefully accessing the resources available to a route before a session is admitted along that route. Each link in the route is checked for sufficient bandwidth not only for the new session to be admitted but also for the sessions that are already using that link. The new session is admitted only if the admission does not violate the delay bounds of any on-going sessions. This method of route selection coupled with per-hop link reservations allows us to provide bounds on the delay performance. Extensive simulation experiments have been conducted that demonstrate the performance of the proposed routing protocol in terms of throughput, session blocking probability, packet drop probability, average path length, and delay.

This thesis describes an architecture for policy-based quality of service (QoS) for fixed broadband wireless systems. An implementation of the proposed architecture for the Local Multipoint Distribution Service (LMDS) wireless network in Blacksburg, Virginia is described in detail. The focus of the research work was to enable simpler management of the LMDS system and to design and enable network QoS. The thesis examines various means to provide QoS in the network. It highlights issues related to enabling QoS in the VT-LMDS network, like prioritized access, resource management, service differentiation, and lack of predictability in network performance. Quality of service assumes a definition based on the context and application of interest. This research focuses on enabling service differentiation and intelligent resource management based on network conditions and link utilization. A software application that serves as a model of the described architecture was developed using the C++ programming language. The tool uses the Simple Network Management Protocol (SNMP) for the network management operations. The design, implementation issues and the advantages and shortcomings of the tool are outlined and a short primer on the use of the tool is provided. Finally, possibilities for future work in this area especially towards enabling the tool to work with other vendor-specific LMDS systems and non-LMDS fixed broadband wireless systems are examined and the issues in implementing one such system are described. / Master of Science

Data stream systems have to deal with massive data volumes. To perform several queries in parallel or to perform even a single query, resources must be planned carefully and the resulting quality-of-service (QoS) is lower than the best one. Typical QoS measures are the output delay and the amount of data in the stream used for the processing. In this paper, we introduce a model which allows to describe stream operators and the streams between the operators of an operator graph belonging to a stream query. The model allows us to calculate the resources consumed by a query graph given a certain result quality. Furthermore, it can be used to determine in advance if the quality-of-service requirement of a given query can be met with the actual available system resources. This model is the basis for building QoS-guaranteeing systems.

No description available.

Quality of Service (QoS) routing considered as one of the major components of the QoS framework in communication networks. The concept of QoS routing has emerged from the fact that routers direct traffic from source to destination, depending on data types, network constraints and requirements to achieve network performance efficiency. It has been introduced to administer, monitor and improve the performance of computer networks. Many QoS routing algorithms are used to maximize network performance by balancing traffic distributed over multiple paths. Its major components include bandwidth, delay, jitter, cost, and loss probability in order to measure the end users¿ requirements, optimize network resource usage and balance traffic load. The majority of existing QoS algorithms require the maintenance of the global network state information and use it to make routing decisions. The global QoS network state needs to be exchanged periodically among routers since the efficiency of a routing algorithm depends on the accuracy of link-state information. However, most of QoS routing algorithms suffer from scalability problems, because of the high communication overhead and the high computation effort associated with marinating and distributing the global state information to each node in the network.The goal of this thesis is to contribute to enhancing the scalability of QoS routing algorithms. Motivated by this, the thesis is focused on localized QoS routing that is proposed to achieve QoS guarantees and overcome the problems of using global network state information such as high communication overhead caused by frequent state information updates, inaccuracy of link-state information for large QoS state update intervals and the route oscillating due to the view of state information. Using such an approach, the source node makes its own routing decisions based on the information that is local to each node in the path. Localized QoS routing does not need the global network state to be exchanged among network nodes because it infers the network state and avoids all the problems associated with it, like high communication and processing overheads and oscillating behaviour. In localized QoS routing each source node is required to first determine a set of candidate paths to each possible destination. In this thesis we have developed localized QoS routing algorithms that select a path based on its quality to satisfy the connection requirements. In the first part of the thesis a localized routing algorithm has been developed that relies on the average residual bandwidth that each path can support to make routing decisions. In the second part of the thesis, we have developed a localized delay-based QoS routing (DBR) algorithm which relies on a delay constraint that each path satisfies to make routing decisions. We also modify credit-based routing (CBR) so that this uses delay instead of bandwidth. Finally, we have developed a localized QoS routing algorithm for routing in two levels of a hierarchal network and this relies on residual bandwidth to make routing decisions in a hierarchical network like the internet. We have compared the performance of the proposed localized routing algorithms with other localized and global QoS routing algorithms under different ranges of workloads, system parameters and network topologies. Simulation results have indicated that the proposed algorithms indeed outperform algorithms that use the basics of schemes that currently operate on the internet, even for a small update interval of link state. The proposed algorithms have also reduced the routing overhead significantly and utilize network resources efficiently.