281 |
Gossip mechanisms for distributed database systems.January 2007 (has links)
Yam, Shing Chung Jonathan. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (leaves 75-79). / Abstracts in English and Chinese. / Abstract / Acknowledgement / Contents / List of Figures / List of Tables / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation --- p.2 / Chapter 1.2 --- Thesis Organization --- p.5 / Chapter 2 --- Literature Review --- p.7 / Chapter 2.1 --- Data Sharing and Dissemination --- p.7 / Chapter 2.2 --- Data Aggregation --- p.12 / Chapter 2.3 --- Sensor Network Database Systems --- p.13 / Chapter 2.4 --- Data Routing and Networking --- p.23 / Chapter 2.5 --- Other Applications --- p.24 / Chapter 3 --- Preliminaries --- p.25 / Chapter 3.1 --- Probability Distribution and Gossipee-selection Schemes --- p.25 / Chapter 3.2 --- The Network Models --- p.28 / Chapter 3.3 --- Objective and Problem Statement --- p.30 / Chapter 3.4 --- Two-tier Gossip Mechanism --- p.31 / Chapter 3.5 --- Semantic-dependent Gossip Mechanism --- p.32 / Chapter 4 --- Results for Two-tier Gossip Mechanisms --- p.34 / Chapter 4.1 --- Background --- p.34 / Chapter 4.2 --- A Time Bound for Solving the Clustered Destination Problem with T-Theorem 1 --- p.39 / Chapter 4.3 --- Further Results´ؤTheorem 2 --- p.49 / Chapter 4.4 --- Experimental Results for Two-tier and N-tier Gossip Mechanisms --- p.51 / Chapter 4.4.1 --- Performance Evaluation of Two-tier Gossip Mechanisms --- p.52 / Chapter 4.4.2 --- Performance Evaluation of N-tier Gossip Mechanisms --- p.56 / Chapter 4.5 --- Discussion --- p.60 / Chapter 5 --- Results for Semantic-dependent Gossip Mechanisms --- p.62 / Chapter 5.1 --- Background --- p.62 / Chapter 5.2 --- Theory --- p.65 / Chapter 5.3 --- "Detection of Single Moving Heat Source with S max(2c1l,c1h ))" --- p.66 / Chapter 5.4 --- Detection of Multiple Static Heat Sources with Two-tier Gossip mechanism --- p.69 / Chapter 5.5 --- Discussion --- p.72 / Chapter 6 --- Conclusion --- p.73 / Chapter 7 --- References --- p.75 / Appendix Prove of Result 4.3 --- p.80
|
282 |
Performance analysis of a distributed file systemMukhopadhyay, Meenakshi 01 January 1990 (has links)
An important design goal of a distributed file system, a component of many distributed systems, is to provide UNIX file access semantics, e.g., the result of any write system call is visible by all processes as soon as the call completes. In a distributed environment, these semantics are difficult to implement because processes on different machines do not share kernel cache and data structures. Strong data consistency guarantees may be provided only at the expense of performance.
This work investigates the time costs paid by AFS 3.0, which uses a callback mechanism to provide consistency guarantees, and those paid by AFS 4.0 which uses typed tokens for synchronization. AFS 3.0 provides moderately strong consistency guarantees, but they are not like UNIX because data are written back to the server only after a file is closed. AFS 4.0 writes back data to the server whenever there are other clients wanting to access it, the effect being like UNIX file access semantics. Also, AFS 3.0 does not guarantee synchronization of multiple writers, whereas AFS 4.0 does.
|
283 |
Information-Theoretic Control of Multiple Sensor PlatformsGrocholsky, Ben January 2002 (has links)
This thesis is concerned with the development of a consistent, information-theoretic basis for understanding of coordination and cooperation decentralised multi-sensor multi-platform systems. Autonomous systems composed of multiple sensors and multiple platforms potentially have significant importance in applications such as defence, search and rescue mining or intelligent manufacturing. However, the effective use of multiple autonomous systems requires that an understanding be developed of the mechanisms of coordination and cooperation between component systems in pursuit of a common goal. A fundamental, quantitative, understanding of coordination and cooperation between decentralised autonomous systems is the main goal of this thesis. This thesis focuses on the problem of coordination and cooperation for teams of autonomous systems engaged in information gathering and data fusion tasks. While this is a subset of the general cooperative autonomous systems problem, it still encompasses a range of possible applications in picture compilation, navigation, searching and map building problems. The great advantage of restricting the domain of interest in this way is that an underlying mathematical model for coordination and cooperation can be based on the use of information-theoretic models of platform and sensor abilities. The information theoretic approach builds on the established principles and architecture previously developed for decentralised data fusion systems. In the decentralised control problem addressed in this thesis, each platform and sensor system is considered to be a distinct decision maker with an individual information-theoretic utility measure capturing both local objectives and the inter-dependencies among the decisions made by other members of the team. Together these information-theoretic utilities constitute the team objective. The key contributions of this thesis lie in the quantification and study of cooperative control between sensors and platforms using information as a common utility measure. In particular, * The problem of information gathering is formulated as an optimal control problem by identifying formal measures of information with utility or pay-off. * An information-theoretic utility model of coupling and coordination between decentralised decision makers is elucidated. This is used to describe how the information gathering strategies of a team of autonomous systems are coupled. * Static and dynamic information structures for team members are defined. It is shown that the use of static information structures can lead to efficient, although sub-optimal, decentralised control strategies for the team. * Significant examples in decentralised control of a team of sensors are developed. These include the multi-vehicle multi-target bearings-only tracking problem, and the area coverage or exploration problem for multiple vehicles. These examples demonstrate the range of non-trivial problems to which the theory in this thesis can be employed.
|
284 |
The Optimisation of Learning in Science Classrooms from the Perspective of Distributed CognitionXu, Li Hua January 2006 (has links)
In the last few decades, there has been growing attention to situated or distributed perspectives on learning and cognition. The purpose of this study was to examine science learning in classroom settings through the lens of distributed cognition. A particular focus of this study was on the public space of interaction that includes participants' interactions with each other and with artefacts in the environment. / Focusing on the event of student experiment design, two science lessons were videotaped in this study, in which a class of Grade-seven participants was asked to investigate the scientific theme of gravity by designing parachutes and pendulums. The video-stimulated post-lesson interviews with both teacher and student provided complementary data in order to understand their practice in these lessons. / The analysis of two science lessons reveals the different functions of language, gestures, and material objects and their relative significance in the process of student meaning making and knowledge construction. It shows that (1) the language of science is best understood as an artefact employed by the participants to achieve mutual understanding; (2) gestures and other forms of non-verbal acts build the connections between the conceptual and the physical worlds, and provided perceptual resources that foregrounded the salient aspects of their environment; and (3) material objects helped the students to understand each other by disambiguating references to objects, but (4) material objects constrained student sense-making. The analysis also demonstrated that (5) the learning activity was enacted through the participants' deployment of a range of artefacts, and (6) the manipulation of conceptual artefacts was interdependent of the manipulation of material objects. / Building on the theoretical framework of distributed cognition, this study was able to document the students' learning processes by investigating classroom interactions in great detail. The findings and techniques resulting from this study will help teachers and researchers to achieve a better understanding of science learning in classrooms and the role of artefacts in this learning and assist them to improve the learning environments.
|
285 |
Distributed Energy Systems with Wind Power and Energy StorageKorpås, Magnus January 2004 (has links)
<p>The topic of this thesis is the study of energy storage systems operating with wind power plants. The motivation for applying energy storage in this context is that wind power generation is intermittent and generally difficult to predict, and that good wind energy resources are often found in areas with limited grid capacity. Moreover, energy storage in the form of hydrogen makes it possible to provide clean fuel for transportation. The aim of this work has been to evaluate how local energy storage systems should be designed and operated in order to increase the penetration and value of wind power in the power system. Optimization models and sequential and probabilistic simulation models have been developed for this purpose.</p><p>Chapter 3 presents a sequential simulation model of a general windhydrogen energy system. Electrolytic hydrogen is used either as a fuel for transportation or for power generation in a stationary fuel cell. The model is useful for evaluating how hydrogen storage can increase the penetration of wind power in areas with limited or no transmission capacity to the main grid. The simulation model is combined with a cost model in order to study how component sizing and choice of operation strategy influence the performance and economics of the wind-hydrogen system. If the stored hydrogen is not used as a separate product, but merely as electrical energy storage, it should be evaluated against other and more energy efficient storage options such as pumped hydro and redox flow cells. A probabilistic model of a grid-connected wind power plant with a general energy storage unit is presented in chapter 4. The energy storage unit is applied for smoothing wind power fluctuations by providing a firm power output to the grid over a specific period. The method described in the chapter is based on the statistical properties of the wind speed and a general representation of the wind energy conversion system and the energy storage unit. This method allows us to compare different storage solutions.</p><p>In chapter 5, energy storage is evaluated as an alternative for increasing the value of wind power in a market-based power system. A method for optimal short-term scheduling of wind power with energy storage has been developed. The basic model employs a dynamic programming algorithm for the scheduling problem. Moreover, different variants of the scheduling problem based on linear programming are presented. During on-line operation, the energy storage is operated to minimize the deviation between the generation schedule and the actual power output of the wind-storage system. It is shown how stochastic dynamic programming can be applied for the on-line operation problem by explicitly taking into account wind forecast uncertainty. The model presented in chapter 6 extends and improves the linear programming model described in chapter 5. An operation strategy based on model predictive control is developed for effective management of uncertainties. The method is applied in a simulation model of a wind-hydrogen system that supplies the local demand for electricity and hydrogen. Utilization of fuel cell heat and electrolytic oxygen as by-products is also considered. Computer simulations show that the developed operation method is beneficial for grid-connected as well as for isolated systems. For isolated systems, the method makes it possible to minimize the usage of backup power and to ensure a secure supply of hydrogen fuel. For grid-connected wind-hydrogen systems, the method could be applied for maximizing the profit from operating in an electricity market.</p><p>Comprehensive simulation studies of different example systems have been carried out to obtain knowledge about the benefits and limitations of using energy storage in conjunction with wind power. In order to exploit the opportunities for energy storage in electricity markets, it is crucial that the electrical efficiency of the storage is as high as possible. Energy storage combined with wind power prediction tools makes it possible to take advantage of varying electricity prices as well as reduce imbalance costs. Simulation results show that the imbalance costs of wind power and the electricity price variations must be relatively high to justify the installation of a costly energy storage system. Energy storage is beneficial for wind power integration in power systems with high-cost regulating units, as well as in areas with weak grid connection.</p><p>Hydrogen can become an economically viable energy carrier and storage medium for wind energy if hydrogen is introduced into the transportation sector. It is emphasized that seasonal wind speed variations lead to high storage costs if compressed hydrogen tanks are used for long-term storage. Simulation results indicate that reductions in hydrogen storage costs are more important than obtaining low-cost and high-efficient fuel cells and electrolyzers. Furthermore, it will be important to make use of the flexibility that the hydrogen alternative offers regarding sizing, operation and possibly the utilization of oxygen and heat as by-products.</p><p>The main scientific contributions from this thesis are the development of</p><p>- a simulation model for estimating the cost and energy efficiency of wind-hydrogen systems,</p><p>- a probabilistic model for predicting the performance of a gridconnected wind power plant with energy storage,</p><p>- optimization models for increasing the value of wind power in electricity markets by the use of hydrogen storage and other energy storage solutions and the system knowledge about wind energy and energy storage that has been obtained by the use of these models.</p> / Paper 1 is reprinted with kind permission of ACTA Press. Paper 2 is reprinted with kind permission of Elsevier/ Science Direct. http://www.elsevier.com, http://www.sciencedirect.com Paper 3 is reprinted with kind permission of IEEE.
|
286 |
Multithreaded virtual processor on DSMAn, Ho Seok 15 December 1999 (has links)
Modern superscalar processors exploit instruction-level parallelism (ILP) by
issuing multiple instructions in a single cycle because of increasing demand for higher
performance in computing. However, stalls due to cache misses severely degrade the
performance by disturbing the exploitation of ILP. Multiprocessors also greatly
exacerbate the memory latency problem. In SMPs, contention due to the shared bus
located between the processors's L2 cache and the shared memory adds additional delay
to the memory latency. In distributed shared memory (DSM) systems, the memory
latency problem becomes even more severe because a miss on the local memory requires
access to remote memory. This limits the performance because the processor can not
spend its time on useful work until the reply from the remote memory is received.
There are a number of techniques that effectively reduce the memory latency.
Multithreadings has emerged as one of the most promising and exciting techniques to
tolerate memory latency. This thesis aims to realize a simulator that supports software-controlled
multithreadings environment on a Distributed Shared Memory and to show
preliminary simulation results. / Graduation date: 2000
|
287 |
Parallel and Distributed Computation:Numerical MethodsBertsekas, Dimitri P., Tsitsiklis, John N. 21 November 2003 (has links)
No description available.
|
288 |
Simple Bivalency Proofs of the Lower Bounds in Synchronous Consensus ProblemsWang, Xianbing, Teo, Yong Meng, Cao, Jiannong 01 1900 (has links)
A fundamental problem of fault-tolerant distributed computing is for the reliable processes to reach a consensus. For a synchronous distributed system of n processes with up to t crash failures and f failures actually occur, we prove using a straightforward bivalency argument that the lower bound for reaching uniform consensus is (f + 2)-rounds in the case of 0 < f ⤠t â2, and a new lower bound for early-stopping consensus is min (t + 1, f + 2)-rounds where 0 ⤠f ⤠t. Both proofs are simpler and more intuitive than the traditional methods such as backward induction. Our main contribution is that we solve the open problem of proving that bivalency can be applied to show the (f + 2)-rounds lower bound for synchronous uniform consensus. / Singapore-MIT Alliance (SMA)
|
289 |
Leaderless Distributed Hierarchy FormationBeal, Jacob 01 December 2002 (has links)
I present a system for robust leaderless organization of an amorphous network into hierarchical clusters. This system, which assumes that nodes are spatially embedded and can only talk to neighbors within a given radius, scales to networks of arbitrary size and converges rapidly. The amount of data stored at each node is logarithmic in the diameter of the network, and the hierarchical structure produces an addressing scheme such that there is an invertible relation between distance and address for any pair of nodes. The system adapts automatically to stopping failures, network partition, and reorganization.
|
290 |
A Robust Amorphous Hierarchy from Persistent NodesBeal, Jacob 01 May 2003 (has links)
For a very large network deployed in space with only nearby nodes able to talk to each other, we want to do tasks like robust routing and data storage. One way to organize the network is via a hierarchy, but hierarchies often have a few critical nodes whose death can disrupt organization over long distances. I address this with a system of distributed aggregates called Persistent Nodes, such that spatially local failures disrupt the hierarchy in an area proportional to the diameter of the failure. I describe and analyze this system, which has been implemented in simulation.
|
Page generated in 0.0456 seconds