Voici les éléments 1 - 10 sur 142
- PublicationMétadonnées seulementThe GIPSY architectureIntensional Programming involves the programming of expressions placed in an inherent multidimensional context space. It is an emerging and highly dynamic domain of general application. The fast growing computer connectivity allows for more and more efficient implementation of distributed applications. The paradigm of intensionality inherently includes notions of parallelism at different levels. However, the currently available intensional programming software tools are becoming obsolete and do not enable us to further push forward practical investigations on the subject. Experience shows that the theoretical advancement of the field has come to acceptable maturity. Consequently, new powerful tools for intensional programming are required. In this paper, we present the design of a General Intensional Programming System (GIPSY). The design and implementation of the GIPSY reflect three main goals: generality, adaptability and efficiency.
- PublicationMétadonnées seulementSecAdvise: A security mechanism advisorThe proliferation of incompatible e-commerce systems applying different security technologies imposes difficult choices on all the concerned parties. In this context, the purpose of this research is to provide the necessary background to develop a security advisor (SecAdvise), which will make it possible to integrate the security mechanisms and the dynamic selection of the various mechanisms between several parties wishing to conduct business transactions safely. Such an advisor aims multiple goals: overcoming compatibility and interoperability problems, evaluating and reducing technological security risks, and enhancing trust.
- PublicationMétadonnées seulementBALLS: a structured peer-to-peer system with integrated load balancing(2006-12-1)
;Le, Viet Dung ;Babin, GilbertLoad balancing is an important problem for structured peer-to-peer systems. We are particularly interested in the consumption of network bandwidth for routing traffic and in the usage of computer resources for object storage. In this paper, we investigate the possibility to simultaneously balance these two types of load. We present a structured peer-to-peer overlay that efficiently performs such simultaneous load balancing. The overlay is constructed by partitioning the nodes of a de Bruijn graph and by allocating the partitions to the peers. Peers balance network bandwidth consumption by repartitioning the nodes. Balancing of computer resources for storage is enabled by dissociating the actual storage location of an object from the location of its search key. The paper presents and analyzes the protocols required to maintain the overlay structure and perform load balancing. We demonstrate their efficiency by simulation. We also compare our proposed overlay network with other approaches.
- PublicationMétadonnées seulementParallel computing in the 1990s - Attacking the software problem(1991-1-22)
;Boillat, J. E. ;Burkhart, H. ;Decker, K. M.It is today's general wisdom that the productive use of parallel architectures depends crucially on the availability of powerful development tools and run-time environments. In this paper, we systematically discuss the fundamental software problems encountered in programming parallel architectures, in particular those with distributed resources. All these problems need to be solved, if efficient and convenient use of parallel machines is to be guaranteed. We present a five phases model of parallel application program development, which describes the required efforts in parallel programming by means of four transformation steps: problem analysis, algorithm design, implementation, and mapping. The major part of the paper is dedicated to the description of three research projects which focus on the last three transformation steps: SKELETON, a tool for providing improved algorithmic support for the application-oriented programmer, SPADE, an integrated development and run-time environment. and MARC, a tool for automatic mapping of parallel programs.
- PublicationAccès libreMultiagent auctions for multiple items(2001)
;Ben Ameur, Houssein ;Chaib-draaa, BrahimAvailable resources can often be limited with regard to the number of demands. In this paper we propose an approach for solving this problem using the mechanisms of multi-item auctions for allocating the resources to a set of software agents. We consider the resource allocation problem as a market with vendor and buyer agents participating in a multi-item auction. The agents exhibit different acquisition capabilities which let them act differently depending on the current context or situation of the market. We present a model for this approach based on the English auction, and discuss experimental evidence of such a model.
- PublicationAccès libreDynamic Load Sharing in Peer-to-Peer Systems: When Some Peers Are More Equal than OthersIn the past few years, several DHT-based abstractions for peer-to-peer systems have been proposed. The main characteristic is to associate nodes (peers) with keys (objects) and to construct distributed routing structures to support an efficient location. These approaches address the load problem, and load balancing is achieved by moving the keys. However, the problem is still not properly covered. In this paper we present an analysis of structured peer-to-peer systems taking into consideration Zipf-like requests distribution. Based on our analysis, we propose a novel approach for load balancing relying on object popularity. Our approach is based on routing table reorganization in order to balance the lookup traffic load. We have implemented this approach in a Pastry-like system. The obtained results demonstrate a better balance of load, which can lead to improved scalability and performance.
- PublicationMétadonnées seulementA workflow-oriented system architecture for the management of container transportationIn this paper, we introduce a workflow-oriented system architecture for the processing of client requests (CRs) for container transportation. In the context of multi-transfer container transportation, the processing of CRs can be achieved by specific sequences of interdependent activities. These sequences need to be just-in-time created. They also need to be adapted to deal with unexpected events that may occur. Workflow technology is used to model and to manage the processing of CRs. The creation and the adaptation of activity sequences require first, an optimized scheduling of a limited number of resources (by also respecting CRs constraints); and second, a number of special workflow concepts and functionality to correctly manage activity sequences. Optimization models are involved to take care of the resource management and of the activity scheduling. Enhancements of workflow concepts and functionality for workflow management systems are investigated to deal with an activity sequence creation and adaptation. Finally, the proposed architecture includes a rule processing part to reduce the time-consuming manual interaction with the system.
- PublicationMétadonnées seulementSemantic Based Error Avoidance and Correction for Video Streaming
- PublicationMétadonnées seulementDynamic server selection in distributed object computing systems(1998)
;Badidi, Elarbi ;Keller, Rudolf ;Van Dongen, VincentIn this paper, we address the problem of dynamic server selection among a set of objectservers, as the ones defined by CORBA and DCOM, providing the same service type. Theseservers are not necessarily replicas but may have different interfaces and belong to differentservice providers. As a solution, we propose a novel architecture that we call LoDACE. Thisarchitecture has been designed to allow dynamic server selection and load sharing indistributed object computing environments. Specifically, the architecture prevents theoccurrence of major load imbalances that can cause failures in distributed applications. Thearchitecture is based on both the use of a trading service and the monitoring of the servers’load. Our interest in the trader is motivated by the need to discover object serversdynamically. LoDACE allows service requests to be processed by lightly loaded serversselected dynamically. The expected results are better performances in terms of responsivenessand availability of servers.
- PublicationMétadonnées seulementLessons Learned from Applying Big Data Paradigms to a Large Scale Scientific Workflow(: CEUR-WS.org, 2016-11-14)The increasing amount of data related to the execution of scientific workflows has raised awareness of their shift towards parallel data-intensive problems. In this paper, we deliver our experience with combining the traditional high-performance computing and grid-based approaches for scientific workflows, with Big Data analytics paradigms. Our goal was to assess and discuss the suitability of such data-intensive-oriented mechanisms for production-ready workflows, especially in terms of scalability, focusing on a key element in the Big Data ecosystem: the data-centric programming model. Hence, we reproduced the functionality of a MPI-based iterative workflow from the hydrology domain, EnKF-HGS, using the Spark data analysis framework. We conducted experiments on a local cluster, and we relied on our results to discuss promising directions for further research.