this paper presents a compile-time placement method of mobile relational operators MROs in a large scale environment. MROs are self adaptive to changing run-time conditions by deciding their execution place if they di...
ISBN:
(纸本)9780769530499
this paper presents a compile-time placement method of mobile relational operators MROs in a large scale environment. MROs are self adaptive to changing run-time conditions by deciding their execution place if they discover compile-time estimation errors. Proposed placement methods tend to have a main drawback with MROs running over a large scale environment: their focus is on finding optimal performance depending on single-point estimation at compile-time, instead of optimal performance over an estimation interval. We propose: (i) to determine the migration space of a MRO including the sites on which the MRO is allowed to migrate during its execution, and (ii) to find the robust site which will allow acceptable response time in an estimation interval. Performance study shows that, with a risk of loosing around 6% in response time, it is possible to gain tip to 300% withthe proposed robust placement.
When datasets are distributed on different sources, finding out their intersection while preserving the privacy of the datasets is a widely required task. In this paper we address the Privacy Preserving Set Intersecti...
详细信息
ISBN:
(纸本)9780769530499
When datasets are distributed on different sources, finding out their intersection while preserving the privacy of the datasets is a widely required task. In this paper we address the Privacy Preserving Set Intersection (PPSI) problem, in which each of the N parties learns no elements other than the intersection of their N private datasets. We propose an efficient protocol in the malicious model, where the adversary may control arbitrary number of parties and execute the protocol for its own benefit. A related work in [12] has a correctness probability of (N-1/N)(N) (N is the size of the encryption scheme's plaintext space), a computation complexity of O(N(2)S(2)lgN) (S is the size of each party's data set). Our PPSI protocol in the malicious model has a correctness probability of (N-1/N)(N-1), and achieves a computation cost of O(c(2)S(2)lgN) (c is the number of malicious parties and c <= N-1).
In the past decade, the number of mobile devices has increased significantly. these devices are in turn showing more computational capabilities. It is therefore possible to envision a near future where client applicat...
详细信息
In the past decade, the number of mobile devices has increased significantly. these devices are in turn showing more computational capabilities. It is therefore possible to envision a near future where client applications may be deployed on these devices. there are, however, constraints that hinder this deployment, especially the limited communication bandwidth and storage space available. this paper describes the Efficient XML Data Exchange Manager (EXEM) that combines context-dependent lossy and lossless compression mechanisms used to support lightweight exchange of objects in XML format between server and client applications. the lossy compression mechanism reduces the size of XML messages by using known information about the application. the lossless compression mechanism decouples data and metadata (compression dictionary) content. We illustrate the use of EXEM with a prototype implementation of the lossless compression mechanism that shows the optimization of the available resources on the server and the mobile client. these experimental results demonstrate the efficiency of the EXEM approach for XML data exchange in the context of mobile application development.
Given a set of tasks with certain characteristics, e.g., data size, estimated execution time and a set Of processing nodes withtheir own parameters, the goal of task scheduling is to allocate tasks at nodes so that t...
详细信息
ISBN:
(纸本)9780769530499
Given a set of tasks with certain characteristics, e.g., data size, estimated execution time and a set Of processing nodes withtheir own parameters, the goal of task scheduling is to allocate tasks at nodes so that the total makespan is minimized. the problem has been studied under various assumptions concerning task and node parameters withthe resulting problem statements usually being NP-complete. List scheduling (LS) heuristics such as MaxMin and MinMin together with genetic algorithms (GAs) were applied in the past to find solutions. In this paper we investigate new heuristics for boththe LS and the GA paradigm withthe specific aim of improving the performance of the standard algorithms when task computations involve large data transfers. Experimental results under various environment assumptions illustrate the merits of the new algorithms.
MPI is commonly used standard in development of scientific applications. It focuses on interlanguage operability and is not very well object oriented. the paper proposes a general pattern enabling design of distribute...
详细信息
ISBN:
(纸本)9783540739395
MPI is commonly used standard in development of scientific applications. It focuses on interlanguage operability and is not very well object oriented. the paper proposes a general pattern enabling design of distributed and object oriented applications. It also presents its sample implementations and performance tests.
Withthe development of internet technologies, internet has been more complexly consisted of a large amount of Web documents, science technology documents, data-base and etc. distributed retrieval system is more requi...
详细信息
ISBN:
(纸本)9780769530499
Withthe development of internet technologies, internet has been more complexly consisted of a large amount of Web documents, science technology documents, data-base and etc. distributed retrieval system is more required to support effective retrieval and management about a large amount of Web documents, science technology documents and etc. distributed retrieval system has to support for user to search quickly and exactly. A distributed retrieval system has to support for DB manager to manage easily. So we have developed the distributed retrieval system called dKRISTAL(1) which finds indexing files and manages database system in real time. We have developed new dKRISTAL system which can support searching and managing database. We measured the integrated search speed of distributed retrieval system. Also this system effectively manages documents at real-time. this paper made an experiment using a large mount of science technology information system and Web documents using dKRISTAL. this paper analyzed the result of experiment.
In this paper we address the critical issues of efficient resource management and high-performance paralleldistributedcomputing on the Grid by introducing a new hierarchical approach that combines a user-level job s...
详细信息
ISBN:
(纸本)9783540739395
In this paper we address the critical issues of efficient resource management and high-performance paralleldistributedcomputing on the Grid by introducing a new hierarchical approach that combines a user-level job scheduling with a dynamic load balancing technique that automatically adapts a black-box distributed or parallel application to the heterogeneous resources. the algorithm developed dynamically selects the resources best suited for a particular task or parallel process of the executed application, and optimizes the load balance based on the dynamically measured resource parameters and estimated requirements of the application. We describe the proposed algorithm for automated load balancing, paying attention to the influence of resource heterogeneity metrics, demonstrate the speedup achieved withthis technique for different types of applications and resources, and propose a way to extend the approach to a wider class of applications.
the scope of the peer-to-peer (P2P) paradigm has expanded beyond the research arena and has become ubiquitous in commercial, industrial and military applications. this ubiquity, however, comes at the cost of significa...
详细信息
ISBN:
(纸本)9780889867048
the scope of the peer-to-peer (P2P) paradigm has expanded beyond the research arena and has become ubiquitous in commercial, industrial and military applications. this ubiquity, however, comes at the cost of significant handicap in design and development of large-scale, reliable, complex realtime applications, as they do not fit into readily available optimized P2P solutions, such as file distribution, grid computing, or Pub/Sub message-passing networks. Rather, these applications necessitate custom development, a high-risk, time consuming and expensive process. We approach this gap by categorizing the problem space into an application taxonomy, and identifying a new class, which we call Extreme P2P applications. Extreme applications are characterized by cross-cutting dimensions of severe QoS requirements, variable resource constraints, evolution during deployment, inherent human participation during operation, and small market share - to name a few. Such characteristics contribute to their development being a significant challenge. We address this challenge by first, proposing a novel architecture for Extreme applications, and second, by introducing a newly re-architected, comprehensive middleware, Cougaar, as a suitable platform for its implementation. We demonstrate the suitability via an architectural mapping, and show how the novel two-tier Cougaar architecture addresses the contextual domain of many such applications by being backward compatible with existing distributed and P2P systems.
the proceedings contain 63 papers. the topics discussed include: looking for a definition of dynamic distributed system;adaptive workflow nets for grid computing;a stochastic semantics for BioAmbients;a categorical ob...
详细信息
ISBN:
(纸本)9783540739395
the proceedings contain 63 papers. the topics discussed include: looking for a definition of dynamic distributed system;adaptive workflow nets for grid computing;a stochastic semantics for BioAmbients;a categorical observation of timed testing equivalence;from unreliable objects to reliable objects: the case of atomic registers and consensus;towards a computing model for open distributed systems;enhancing online computer games for open distributed systems;enhancing online computer games for grids;optimized parallel approach for 3D modelling of forest fire behaviour;a high-level toolkit for development of distributed scientific applications;orthogonal organized finite state machine application to sensor acquired information;parallel broadband finite element time domain algorithm implemented to dispersive electromagnetic problem;and strategies for development of a parallel program for protoplanetary disc simulation.
Increase in intensive applications with different computational requirements, coupled withthe unification of remote and diverse resources thanks to advances in the wide-area network technologies and the low cost of c...
详细信息
ISBN:
(纸本)9780769527840
Increase in intensive applications with different computational requirements, coupled withthe unification of remote and diverse resources thanks to advances in the wide-area network technologies and the low cost of components, have-encouraged the development of grid computing. To exploit the promising potentials of geographically distributed resources, effective and efficient mapping algorithms are fundamental. Since the problem of optimally mapping is NP-complete, the development of evolutionary techniques to find near-optimal solutions is welcome. In this paper a distributed system based on Differential Evolution is designed and implemented to face the mapping problem in a gild environment aiming at reducing the degree of use of the grid resources. this system is tested on some different resource allocation scenarios.
暂无评论