PANTS (PANTS Application Node Transparency System) is a suite of programs designed to add transparent load balancing to a Beowulf cluster so that processes are transfered among the nodes of the cluster to improve performance. PANTS provides the option of using one of several different load balancing policies, each having a different approach. This paper studies the scalability and performance of these policies on large clusters and under various workloads. We measure the performance of our policies on our current cluster, and use that performance data to build simulations to test the performance of the policies in larger clusters and under differing workloads. Two policies, one deterministic and one non-deterministic, are presented which offer optimal steady-state performance. We also present best practices and discuss the major challenges of load balancing policy design.

"Distributed systems are clusters of computers working together on one task. The sharing of information across different architectures, and the timely and efficient use of the network resources for communication among computers are some of the problems involved in the implementation of a distributed system. In the case of a low latency system, the network utilization and the responsiveness of the communication mechanism are even more critical. This thesis introduces a new approach for the distribution of messages to computers in the system, in which, the Common Object Request Broker Architecture (CORBA) is used in conjunction with IP multicast to implement a fault-tolerant, low latency distributed system. Fault tolerance is achieved by replication of the current state of the system across several hosts. An update of the current state is initiated by a client application that contacts one of the state object replicas. The new information needs to be distributed to all the members of the distributed system (the object replicas). This state update is accomplished by using a two-phase commit protocol, which is implemented using a binary tree structure along with IP multicast to reduce the amount of network utilization, distribute the computation load associated with state propagation, and to achieve faster communication among the members of the distributed system. The use of IP multicast enhances the speed of message distribution, while the two-phase commit protocol encapsulates IP multicast to produce a reliable multicast service that is suitable for fault tolerant, distributed low latency applications. The binary tree structure, finally, is essential for the load sharing of the state commit response collection processing. "

"Recently the Internet has been increasingly used for multi-party applications like video-conferencing, video-on-demand and shared white-boards. Multicast extensions to IP to support multi-party applications are best effort, often resulting in packet loss within the network. Since some multicast applications can not tolerate packet loss, most of the existing reliable multicast schemes recover each and every lost packet. However, multimedia applications can tolerate a certain amount of packet loss and are sensitive to long recovery delays. We propose a new loss recovery technique that selectively repairs lost packets based upon the amount of packet loss and delay expected for the repair. Our technique sends a special WAIT message down the multicast tree in the event a loss is detected in order to reduce the number of retransmission requests. We also propose an efficient sender initiated multicast trace-route mechanism for determining the multicast topology and a mechanism to deliver the topology information to the multicast session participants. We evaluate our proposed technique using an event driven network simulator, comparing it with two popular reliable multicast protocols, SRM and PGM. We conclude that our proposed WAIT protocol can reduce the overhead on a multicast session as well as improve the average end-to-end latency of the session."

Typescript (photocopy). / Digitized by Kansas Correctional Industries

Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1980. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Bibliography: leaves 88-89. / by Richard P. Hughes. / M.S.

Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1979. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Includes bibliographical references. / by Daniel U. Friedman. / M.S.

Cheng Ho Ting. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 90-93). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Overview of Wireless Cooperative Communications --- p.1 / Chapter 1.2 --- Motivation --- p.2 / Chapter 1.3 --- Distributed Space-Time Block Coding --- p.4 / Chapter 1.4 --- Imperfect Channel Estimation --- p.4 / Chapter 1.5 --- Time-Varying Channels --- p.4 / Chapter 1.6 --- Outline of the thesis --- p.5 / Chapter 2 --- Background Study --- p.6 / Chapter 3 --- Distributed Space-Time Block Coding --- p.13 / Chapter 3.1 --- Introduction --- p.13 / Chapter 3.2 --- System Model --- p.13 / Chapter 3.3 --- BER Analysis by Characteristic Equations --- p.16 / Chapter 3.4 --- BER Analysis by Error Terms --- p.18 / Chapter 3.4.1 --- Non-fading R→D link --- p.19 / Chapter 3.4.2 --- Fading R→D link --- p.19 / Chapter 3.5 --- Performance --- p.20 / Chapter 3.5.1 --- Accuracy of Analytical Expressions --- p.20 / Chapter 3.5.2 --- Observation of Second-order Diversity --- p.21 / Chapter 3.6 --- Summary --- p.22 / Chapter 4 --- Distributed Space-Time Block Coding with Imperfect Channel Estimation --- p.31 / Chapter 4.1 --- Introduction --- p.31 / Chapter 4.2 --- System Model --- p.32 / Chapter 4.3 --- BER Analysis --- p.32 / Chapter 4.3.1 --- Non-fading R→D link --- p.33 / Chapter 4.3.2 --- Fading R→D link --- p.34 / Chapter 4.4 --- Numerical Results --- p.34 / Chapter 4.5 --- Summary --- p.36 / Chapter 5 --- Distributed Space-Time Block Coding with Time-Varying Channels --- p.43 / Chapter 5.1 --- Introduction --- p.43 / Chapter 5.2 --- System Model --- p.44 / Chapter 5.3 --- Pilot Symbol Assisted Modulation (PSAM) for DSTBC --- p.45 / Chapter 5.4 --- Reception Methods --- p.48 / Chapter 5.4.1 --- Maximum-Likelihood Detection (ML) in [29] --- p.48 / Chapter 5.4.2 --- Cooperative Maximum-Likelihood Detection (CML) --- p.50 / Chapter 5.4.3 --- Alamouti's Receiver (AR) --- p.51 / Chapter 5.4.4 --- Zero-forcing Linear Detection (ZF) --- p.51 / Chapter 5.4.5 --- Decision-feedback Detection (DF) --- p.52 / Chapter 5.5 --- BER Analysis for Time-varying Channels --- p.53 / Chapter 5.5.1 --- Quasi-Static Channels (p = 1) --- p.53 / Chapter 5.5.2 --- ZF: Uncorrelated Channel (p = 0) --- p.54 / Chapter 5.5.3 --- ZF: General Channel --- p.55 / Chapter 5.5.4 --- DF: General Channel --- p.56 / Chapter 5.6 --- Numerical Results --- p.57 / Chapter 5.7 --- Summary --- p.60 / Chapter 6 --- Conclusion and Future Work --- p.74 / Chapter 6.1 --- Conclusion --- p.74 / Chapter 6.2 --- Future Work --- p.76 / Chapter 6.2.1 --- Design of Code Matrix --- p.76 / Chapter 6.2.2 --- Adaptive Protocols --- p.77 / Chapter A --- Derivation of (3.23) --- p.79 / Chapter B --- Derivation of (3.30) and (3.32) --- p.83 / Chapter C --- Derivation of (4.9) and (4.13) --- p.85 / Chapter D --- Derivation of (5.68) --- p.88 / Bibliography --- p.90

In this thesis, we first propose a distributed QoS evaluation framework for Web services, named WS-DREAM. Inspired by the recent success of Web 2.0, our evaluation framework employs the concept of user-collaboration. In our framework, users in different geographic locations collaborative with each other to evaluate the target Web services and share their observed Web service QoS information. Based on our Web service evaluation framework, several large-scale distributed evaluations are conducted on 5,825 real-world Web services and the detailed evaluation results are publicly released for future research. / The predicted Web service QoS values can be employed to build fault-tolerant service-oriented systems. In the area of service computing, the cost for developing multiple redundant components is greatly reduced, since the functionally equivalent Web services are provided by different organizations and are accessible via Internet. Hence, based on the predicted QoS values, we propose two methods for building fault tolerance Web services. Firstly, we propose an adaptive fault tolerance strategy for Web services. Then, we present an optimal fault tolerance strategy selection framework for Web services. / Web service evaluation is time and resource consuming. Moreover, in some scenarios, Web service evaluation may not be possible (e.g., the Web service invocation is charged, too many service candidate, etc.). Therefore, Web service QoS prediction approaches are becoming more and more attractive. In order to prediction the Web service QoS as accurate as possible, we propose three prediction methods. The first prediction method employs the information of neighborhoods for making missing value prediction. The second method engages matrix factorization techniques to enhance the prediction accuracy. The third method predicts the ranking of the target Web services instead of QoS values. / Web service is becoming a major technique for building loosely-coupled distributed systems. Service-oriented architecture (SOA) has been widely employed in e-business, e-government, automotive systems, multimedia services, process control, finance, and a lot of other domains. Quality-of-Service (QoS) is usually employed for describing the non-functional characteristics of Web services and employed as an important differentiating point of different Web services. With the prevalence of Web services on the Internet, Web service QoS management is becoming more and more important. / Zheng, Zibin. / Adviser: Michael R. Lyu. / Source: Dissertation Abstracts International, Volume: 73-04, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2011. / Includes bibliographical references (leaves 184-198). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [201-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.

For the macroscopic traceback problem, we propose an algorithm, which leverages the well-known Chandy-Lamport's distributed snapshot algorithm, so that a set of border routers of the ISPs can correctly gather statistics in a coordinated fashion. The victim site can then deduce the local traffic intensities of all the participating routers. Given the collected statistics, we provide a method for the victim site to locate the attackers who sent out dominating flows of packets. Our finding shows that the proposed methodology can pinpoint the location of the attackers in a short period of time. / In the second part of the thesis, we study a well-known technique against the microscopic traceback problem. The probabilistic packet marking (PPM for short) algorithm by Savage et al. has attracted the most attention in contributing the idea of IP traceback. The most interesting point of this IP traceback approach is that it allows routers to encode certain information on the attack packets based on a pre-determined probability. Upon receiving a sufficient number of marked packets, the victim (or a data collection node) can construct the set of paths the attack packets traversed (or the attack graph), and hence the victim can obtain the locations of the attackers. In this thesis, we present a discrete-time Markov chain model that calculates the precise number of marked packets required to construct the attack graph. / The denial-of-service attack has been a pressing problem in recent years. Denial-of-service defense research has blossomed into one of the main streams in network security. Various techniques such as the pushback message, the ICMP traceback, and the packet filtering techniques are the remarkable results from this active field of research. / The focus of this thesis is to study and devise efficient and practical algorithms to tackle the flood-based distributed denial-of-service attacks (flood-based DDoS attack for short), and we aim to trace every location of the attacker. In this thesis, we propose a revolutionary, divide-and-conquer trace-back methodology. Tracing back the attackers on a global scale is always a difficult and tedious task. Alternatively, we suggest that one should first identify Internet service providers (ISPs) that contribute to the flood-based DDoS attack by using a macroscopic traceback approach . After the concerned ISPs have been found, one can narrow the traceback problem down, and then the attackers can be located by using a microscopic traceback approach. / Though the PPM algorithm is a desirable algorithm that tackles the microscopic traceback problem, the PPM algorithm is not perfect as its termination condition is not well-defined in the literature. More importantly, without a proper termination condition, the traceback results could be wrong. In this thesis, we provide a precise termination condition for the PPM algorithm. Based on the precise termination condition, we devise a new algorithm named the rectified probabilistic packet marking algorithm (RPPM algorithm for short). The most significant merit of the RPPM algorithm is that when the algorithm terminates, it guarantees that the constructed attack graph is correct with a specified level of confidence. Our finding shows that the RPPM algorithm can guarantee the correctness of the constructed attack graph under different probabilities that the routers mark the attack packets and different structures of the network graphs. The RPPM algorithm provides an autonomous way for the original PPM algorithm to determine its termination, and it is a promising means to enhance the reliability of the PPM algorithm. / Wong Tsz Yeung. / "September 2007." / Adviser: Man Hon Wong. / Source: Dissertation Abstracts International, Volume: 69-08, Section: B, page: 4867. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (p. 176-185). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in English and Chinese. / School code: 1307.

Kin Kwong Leung. / "August 15, 2003." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2003. / Includes bibliographical references (p. 77-[82]). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.