Search

Your search keyword '"Académie des sciences de Pologne"' showing total 15 results
Start Over Author "Académie des sciences de Pologne"
15 results on '"Académie des sciences de Pologne"'

1. Ontologies, Agents and the Grid: An Overview

Author

Pavel Telegin, Mehrdad Senobari, Maria Ganzha, Michal Drozdowicz, Ivan Lirkov, Marcin Paprzycki, Richard Olejnik, Systems Research Institute [Warsaw] (IBS PAN), Polska Akademia Nauk = Polish Academy of Sciences (PAN), Contributions of the Data parallelism to real time (DART), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institute for Parallel Processing (IPP BAS), Bulgarian Academy of Sciences (BAS), SuperComputing Center of Russian Academy of Sciences, Russian Academy of Sciences [Moscow] (RAS), Tarbiat Modares University [Tehran], PICS CNRS/Académie des Sciences de Pologne, Saxe-Coburg Publications, Stirlingshire, UK, and CNRS/Académie des Sciences de Pologne

Subjects
Information management, Knowledge management, Computer science, software agents, 02 engineering and technology, Ontology (information science), grid, 0202 electrical engineering, electronic engineering, information engineering, Information system, resource brokering and management, IDEF5, ontology, business.industry, [INFO.INFO-WB]Computer Science [cs]/Web, 020207 software engineering, Grid, Data science, Semantic grid, Software agent, [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], Middleware, semantic information processing, 020201 artificial intelligence & image processing, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], business
Abstract

23 pages; One of the important claims that permeate the current view of information management is that ontological demarcation of data and semantic information processing are going to allow us to infuse "intelligence" into information systems. Separately, it is claimed that software agents, combined with ontologies will be the foundation ofWeb 4.0. In our work we are developing an agent-team-based resource management and brokering infrastructure for computational grids. The proposed meta-level middleware is to utilize both software agents and ontologies. In this context, the aim of this chapter is twofold. First, we present an overview of found efforts to develop ontologies to be used in grid and agent-grid computing. Second, we analyze which one of them, if any, should be the base ontology for the system under development.

Published
2009
Full Text
View/download PDF

2. Species delimitation, global phylogeny and historical biogeography of the parasitoid wasp genus Spathius (Braconidae: Doryctinae) reveal multiple Oligocene-Miocene intercontinental dispersal events

Author

Alejandro Zaldívar-Riverón, Sergey A Belokobylskij, Rubi Meza-Lázaro, Carlos Pedraza-Lara, Mario García-París, Andrea S Meseguer, Universidad Nacional Autónoma de México (UNAM), Musée de l'évolution de l'Académie des Sciences de Pologne, Partenaires INRAE, University Skaya Naberezhnaya, Consejo Superior de Investigaciones Científicas [Madrid] (CSIC), Centre de Biologie pour la Gestion des Populations (UMR CBGP), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Institut National de la Recherche Agronomique (INRA)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Université de Montpellier (UM)-Institut de Recherche pour le Développement (IRD [France-Sud])-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro), US National Science Foundation : DEB0205982, Consejo Nacional de Ciencia y Tecnologia (CONACyT) : 220454, Proyecto Cooperacion Bilateral CONACyT-CONICET : 207072, MINECO/FEDER : CGL2015-66571-P, Russian Foundation for Basic Research : 15-29-02466, 16-04-00197, Russian State Research Project : AAAA-A17-117030310210-3, Museo Nacional de Ciencias Naturales (MNCN-CSIC), Madrid, Spain (DGAPA-PASPA), Universidad Nacional Autónoma de México, Ministerio de Economía y Competitividad (España), Consejo Nacional de Ciencia y Tecnología (México), European Commission, and Russian Foundation for Basic Research

Subjects
0106 biological sciences, 0301 basic medicine, species delineation, [SDV]Life Sciences [q-bio], Dispersal, Molecular phylogeny, 15. Life on land, 010603 evolutionary biology, 01 natural sciences, 03 medical and health sciences, 030104 developmental biology, COI mtDNA, [SDE]Environmental Sciences, Species delineation, Animal Science and Zoology, dispersal, Ecology, Evolution, Behavior and Systematics, molecular phylogeny
Abstract

Phylogenetic studies of globally distributed taxa are crucial to estimate the mode and tempo of common intercontinental biogeographic processes. However, few of these studies have focused on invertebrates, mainly because their taxonomy and species richness generally are highly neglected. Here we performed a morphological and mtDNA sequence-based species delineation analysis for 111 specimens of the cosmopolitan, speciose parasitoid wasp genus Spathius (Braconidae) and assessed its phylogenetic relationships and historical biogeography adding two nuclear markers. Seventy-one species of Spathius were delimited. Neither the monophyly of Spathiini, Spathius, nor its species groups were recovered. Based on the relaxed molecular clock and ancestral area reconstruction analyses, the Oriental appears as the most plausible region of origin for Spathius, whereas various intercontinental dispersal events probably played an important role in its species diversification. At least three and two dispersal events from the Oriental to the Ethiopian and Australian regions, respectively, were estimated to occur during the late Oligocene to mid-Miocene, c. 25–15 Mya. Dispersal to the Palaearctic and Nearctic from the Ethiopian region probably occurred during the early Miocene, c. 20 Mya. Our results overall reflect that the worldwide distribution of Spathius was acquired early in the evolutionary history of the lineage., This study was funded by grants given by the Consejo Nacional de Ciencia y Tecnología (CONACyT; Proyecto Ciencia Básica No. 220454; Proyecto Cooperación Bilateral CONACyT-CONICET No. 207072; Red Temática del Código de Barras de la Vida) and PAPIIT-DGAPA-UNAM (Convocatoria 2016) to A.Z.-R.; by the grant CGL2015-66571-P (MINECO/FEDER) to M.G.-P.; and by grants given by the Russian Foundation for Basic Research (projects nos 15-29-02466 and 16-04-00197) and the Russian State Research Project No. AAAA-A17-117030310210-3 to S.A.B. A.Z.-R. is thankful to the DGAPA-UNAM for the financial support received during his sabbatical stay at the Museo Nacional de Ciencias Naturales (MNCN-CSIC), Madrid, Spain (DGAPA-PASPA, Convocatoria 2015).

Published
2018
Full Text
View/download PDF

3. On the local geometry of definably stratified sets

Author

Trotman, David, Valette, Guillaume, Institut de Mathématiques de Marseille (I2M), Aix Marseille Université (AMU)-École Centrale de Marseille (ECM)-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques, Académie des Sciences de Pologne, and Trotman, David

Subjects
[MATH.MATH-AC] Mathematics [math]/Commutative Algebra [math.AC], [MATH.MATH-GT]Mathematics [math]/Geometric Topology [math.GT], [MATH.MATH-AC]Mathematics [math]/Commutative Algebra [math.AC], [MATH.MATH-AG] Mathematics [math]/Algebraic Geometry [math.AG], [MATH.MATH-AG]Mathematics [math]/Algebraic Geometry [math.AG], ComputingMilieux_MISCELLANEOUS, [MATH.MATH-GT] Mathematics [math]/Geometric Topology [math.GT]
Abstract

International audience

Published
2017

4. Detecting asymptotic non-regular values by polar curves

Author

Zbigniew Jelonek, Mihai Tibăr, Institut de Mathématiques, Académie des Sciences de Pologne, Laboratoire Paul Painlevé - UMR 8524 (LPP), Université de Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies, and Laboratoire Paul Painlevé (LPP)

Subjects
Polynomial, Pure mathematics, Series (mathematics), General Mathematics, 010102 general mathematics, [MATH.MATH-CV]Mathematics [math]/Complex Variables [math.CV], 0102 computer and information sciences, Function (mathematics), 01 natural sciences, Effective algorithm, Mathematics - Algebraic Geometry, Mathematics::Algebraic Geometry, 010201 computation theory & mathematics, FOS: Mathematics, [MATH.MATH-AG]Mathematics [math]/Algebraic Geometry [math.AG], Affine transformation, 0101 mathematics, Algebraic Geometry (math.AG), ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract

We locate the Malgrange non-regular values of a given polynomial function $f:\bC^n \to \bC$ by using a series of affine polar curves. We moreover show that all non-trivial Malgrange non-regular values of $f$ are indicated by a single "super-polar curve" which we introduce here, providing also an effective algorithm of detection.

Published
2015
Full Text
View/download PDF

5. L’irénisme et l’idée de tolérance à la Renaissance

Author

Pierre, Benoist, Centre d'études supérieures de la Renaissance UMR 7323 (CESR), Ministère de la Culture et de la Communication (MCC)-Université de Tours (UT)-Centre National de la Recherche Scientifique (CNRS), Académie des sciences de Pologne, and Pierre, Benoist

Subjects
Europe, Conflits religieux, [SHS.HIST] Humanities and Social Sciences/History, Renaissance 1450-1600, Tolérance, Histoire religieuse, Histoire européenne, [SHS.HIST]Humanities and Social Sciences/History, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2015

6. Bifurcation locus and branches at infinity of a polynomial f : C2 -> C

Author

Tibar, Mihai, Jelonek, Zbigniew, Laboratoire Paul Painlevé - UMR 8524 (LPP), Université de Lille-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques, Académie des Sciences de Pologne, Labex CEMPI, and Laboratoire Paul Painlevé (LPP)

Subjects
Mathematics - Algebraic Geometry, [MATH.MATH-CV]Mathematics [math]/Complex Variables [math.CV], [MATH.MATH-AG]Mathematics [math]/Algebraic Geometry [math.AG]
Abstract

International audience; We show that the number of bifurcation points at infinity of a polynomial function f : C2 -> C is at most the number of branches at infinity of a generic fiber of f and that this upper bound can be diminished by one in certain cases.

Published
2015

7. Extremal Optimization Applied to Task Scheduling of Distributed Java Programs

Author

Ernesto Tarantino, Marek Tudruj, Richard Olejnik, Umberto Scafuri, Eryk Laskowski, Ivanoe De Falco, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Institute of High Performance Computing and Networking, CNR, Naples, Italy, Institute of High Performance Computing and Networking (ICAR), Consiglio Nazionale delle Ricerche [Roma] (CNR)-Consiglio Nazionale delle Ricerche [Roma] (CNR), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Consiglio Nazionale delle Ricerche [Roma] (CNR), Polish-Japanese Institute of Information Technology (PJIIT), PICS CNRS/Académie des Sciences de Pologne, Springer-Verlag Berlin Heidelberg, CNR, Italie, National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)-National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), and National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)

Subjects
Rate-monotonic scheduling, Extremal optimization, distributed systems, 020203 distributed computing, Java, Computer science, Evolutionary algorithm, 02 engineering and technology, Dynamic priority scheduling, Parallel computing, Fair-share scheduling, LNCS, Scheduling (computing), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, scheduling, evolutionary algorithms, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], Cluster analysis, computer, computer.programming_language
Abstract

International audience; The paper presents new Java programs scheduling algorithms for execution on clusters of Java Virtual Machines (JVMs), which involve extremal optimization (EO) combined with task clustering. Two new scheduling algorithms are presented and compared. The first employs task clustering to reduce an initial program graph and then applies extremal optimization to schedule the reduced program graph to system resources. The second algorithm applies task clustering only to find an initial solution which is next improved by the EO algorithm working on the initial program graph. Both algorithms are also compared to an EO algorithm which does not use the clustering approach.

Published
2013
Full Text
View/download PDF

8. Load Balancing in Distributed Applications Based on Extremal Optimization

Author

Marek Tudruj, Ivanoe De Falco, Richard Olejnik, Eryk Laskowski, Umberto Scafuri, Ernesto Tarantino, Institute of High Performance Computing and Networking, CNR, Naples, Italy, Institute of High Performance Computing and Networking (ICAR), Consiglio Nazionale delle Ricerche [Roma] (CNR)-Consiglio Nazionale delle Ricerche [Roma] (CNR), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Consiglio Nazionale delle Ricerche [Roma] (CNR), Polish-Japanese Institute of Information Technology (PJIIT), PICS CNRS, Springer Verlag, Académie des Sciences de Pologne, CNR Italie, National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)-National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), and National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)

Subjects
Extremal optimization, 020203 distributed computing, Multi-core processor, Computer science, Distributed computing, Computation, Message passing, distributed program design, load balancing, 02 engineering and technology, Parallel computing, Load balancing (computing), LNCS, extremal optimization, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]
Abstract

10 pages; International audience; he paper shows how to use Extremal Optimization in load balancing of distributed applications executed in clusters of multicore processors interconnected by a message passing network. Composed of iterative optimization phases which improve program task placement on processors, the proposed load balancing method discovers dynamically the candidates for migration with the use of an Extremal Optimization algorithm and a special quality model which takes into account the computation and communication parameters of the constituent parallel tasks. Assessed by experiments with simulated load balancing of distributed program graphs, a comparison of the proposed Extremal Optimization approach against a deterministic approach based on a similar load balancing theoretical model is provided.

Published
2013
Full Text
View/download PDF

9. Ontology for Contract Negotiations in an Agent-based Grid Resource Management System

Author

Michal Drozdowicz, Ivan Lirkov, Maria Ganzha, Marcin Paprzycki, Dana Petcu, Costin Badica, Richard Olejnik, Katarzyna Wasielewska, Naoual Attaoui, Systems Research Institute [Warsaw] (IBS PAN), Polska Akademia Nauk = Polish Academy of Sciences (PAN), Université Abdelmalek Essaâdi (UAE), Institute for Parallel Processing (IPP BAS), Bulgarian Academy of Sciences (BAS), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Western University of Technologie of Timisoara (UVT), Western University of Technologie of Timisoara, University of Craiova, Romania, PICS CNRS, P. Iványi, B.H.V. Topping, and CNRS/Académie des Sciences de Pologne

Subjects
Knowledge management, software agents, business.industry, Quality of service, media_common.quotation_subject, 020206 networking & telecommunications, 02 engineering and technology, semantic information processing, Grid, grid, Service-level agreement, Negotiation, Work (electrical), [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], Software agent, resource brokering and management, 0202 electrical engineering, electronic engineering, information engineering, Ontology, 020201 artificial intelligence & image processing, Economic model, ontology, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], business, media_common
Abstract

International audience; Our research (the Agents in Grid; AiG project) concerns the development of an agent-based Grid middleware, in which (a) agents work in teams (each team is to be managed by the LMaster agent), (b) all meta-information is ontologically demarcated and semantically processed (with all team information stored in and managed by the Client Information Center; CIC infrastructure represented by the CIC agent), and (c) an economic model is to be based on autonomic Service Level Agreement (SLA) negotiations and Quality of Service (QoS) monitoring.

Published
2011
Full Text
View/download PDF

10. Negotiations in an Agent-based Grid Resource Brokering System

Author

Michal Drozdowicz, Marcin Paprzycki, Ivan Lirkov, Costin Badica, Dana Petcu, Richard Olejnik, Maria Ganzha, Katarzyna Wasielewska, Naoual Attaoui, Systems Research Institute [Warsaw] (IBS PAN), Polska Akademia Nauk = Polish Academy of Sciences (PAN), West University of Timișoara [Roumanie] (WUT), University of Craiova, Université Abdelmalek Essaâdi (UAE), Institute for Parallel Processing (IPP BAS), Bulgarian Academy of Sciences (BAS), Contributions of the Data parallelism to real time (DART), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), PICS CNRS, P. Iványi, B.H.V. Topping, and CNRS/Académie des Sciences de Pologne

Subjects
Knowledge management, Process management, software agents, media_common.quotation_subject, service level agreement, 02 engineering and technology, Ontology (information science), grid, negotiations, Service-level agreement, 0202 electrical engineering, electronic engineering, information engineering, resource brokering and management, Grid resources, ontology, media_common, Conceptualization, business.industry, European research, 020206 networking & telecommunications, Grid, Negotiation, Software agent, [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], 020201 artificial intelligence & image processing, Business, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]
Abstract

International audience; The aim of this chapter is to present an overview of issues concerning autonomous (possibly agent-based) \textit{Service Level Agreement} negotiations. To achieve this goal, first five European research projects are discussed that represent different approaches to the problem of integration of business and grid architectures, as well as various methods of establishing the SLA between grid users. Second, the experience gained from these projects is used as a foundation of conceptualization of the SLA negotiations in the AiG project.

Published
2011
Full Text
View/download PDF

11. Extremal Optimization Approach Applied to Initial Mapping of Distributed Java Programs

Author

Umberto Scafuri, Ernesto Tarantino, Richard Olejnik, Marek Tudruj, Ivanoe De Falco, Eryk Laskowski, Institute of High Performance Computing and Networking (ICAR), Consiglio Nazionale delle Ricerche [Roma] (CNR), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Polish-Japanese Institute of Information Technology (PJIIT), CNRS/Académie des Sciences de Pologne, CNR Italie, and National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)

Subjects
Extremal optimization, Extremal Optimization, Java, Computer science, Distributed computing, Evolutionary algorithm, 0102 computer and information sciences, 02 engineering and technology, Thread (computing), Software_PROGRAMMINGTECHNIQUES, 01 natural sciences, program optimization, 0202 electrical engineering, electronic engineering, information engineering, mapping, evolutionary algorithms, Cluster analysis, computer.programming_language, distributed systems, Multi-core processor, strictfp, distributed programs, Program optimization, Java concurrency, 010201 computation theory & mathematics, ACM: D.: Software/D.2: SOFTWARE ENGINEERING, 020201 artificial intelligence & image processing, Software_PROGRAMMINGLANGUAGES, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], computer
Abstract

International audience; An extremal optimization algorithm for initial Java program placement on clusters of Java Virtual Machines (JVMs) is presented. JVMs are implemented on multicore processors working under the ProActive Java execution framework. Java programs are represented as Directed Acyclic Graphs in which tasks correspond to methods of distributed active Java objects that communicate using a RMI mechanism. The presented probabilistic extremal optimization approach is based on the local fitness function composed of two sub-functions in which elimination of delays of task execution after reception of required data and the imbalance of tasks execution in processors are used as heuristics for improvements of extremal optimization solutions. The evolution of an extremal optimization solution is governed by task clustering supported by identification of the dominant path in the graph. The applied task mapping is based on dynamic measurements of current loads of JVMs and inter-JVM communication link bandwidth. The JVM loads are approximated by observation of the average idle time that threads report to the OS. The current link bandwidth is determined by observation of the performed average number of RMI calls per second.

Published
2010
Full Text
View/download PDF

12. Distributed Java Programs Initial Mapping Based on Extremal Optimization

Author

Eryk Laskowski, Ivanoe De Falco, Umberto Scafuri, Ernesto Tarantino, Richard Olejnik, Marek Tudruj, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institute of High Performance Computing and Networking, CNR, Naples, Italy, Institute of High Performance Computing and Networking (ICAR), Consiglio Nazionale delle Ricerche [Roma] (CNR)-Consiglio Nazionale delle Ricerche [Roma] (CNR), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Consiglio Nazionale delle Ricerche [Roma] (CNR), Polish-Japanese Institute of Information Technology (PJIIT), PICS CNRS, Springer-Verlag Berlin Heidelberg, Académie des Sciences de Pologne, CNRS Italie, National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)-National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR), and National Research Council of Italy | Consiglio Nazionale delle Ricerche (CNR)

Subjects
Extremal optimization, Theoretical computer science, Java, Computer science, Evolutionary algorithm, 0102 computer and information sciences, 02 engineering and technology, Thread (computing), Software_PROGRAMMINGTECHNIQUES, 01 natural sciences, LNCS, Scheduling (computing), program optimization, 0202 electrical engineering, electronic engineering, information engineering, Cluster analysis, computer.programming_language, distributed systems, 020203 distributed computing, Fitness function, evolutionary algorithm, Program optimization, 010201 computation theory & mathematics, evolutionary algorithms, scheduling, Software_PROGRAMMINGLANGUAGES, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], Heuristics, computer
Abstract

11 pages; International audience; An extremal optimization algorithm for initial Java program placement on clusters of Java Virtual Machines (JVMs) is presented. JVMs are implemented on multicore processors working under the ProActive Java execution framework. Java programs are represented as Directed Acyclic Graphs in which tasks correspond to methods of distributed active Java objects that communicate using a RMI mechanism. The presented probabilistic extremal optimization approach is based on the local fitness function composed of two sub-functions in which elimination of delays of task execution after reception of required data and the imbalance of tasks execution in processors are used as heuristics for improvements of extremal optimization solutions. The evolution of an extremal optimization solution is governed by task clustering supported by identification of the dominant path in the graph. The applied task mapping is based on dynamic measurements of current loads of JVMs and inter-JVM communication link bandwidth. The JVM loads are approximated by observation of the average idle time that threads report to the OS. The current link bandwidth is determined by observation of the performed average number of RMI calls per second.

Published
2010
Full Text
View/download PDF

13. Load Balancing Metrics for the SOAJA Framework

Author

Olejnik, R., Alshabani, I., Toursel, B., Laskowski, E., Marek Tudruj, LIFL - DART/Émeraude, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Polish-Japanese Institute of Information Technology (PJIIT), and CNRS/Académie des Sciences de Pologne

Subjects
distributed computing, service-oriented architecture, load balancing, ACM: D.: Software/D.2: SOFTWARE ENGINEERING, adaptive software, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], grid computing
Abstract

International audience; The paper describes system and program metrics used for load balancing algorithms for Java program execution in the SOAJA (Service Oriented Adaptative Java Applications) executive environment. This environment aims in maintaining design and execution of large scale computing tasks in complex networked Grid environments. SOAJA services provide means for static and dynamic load balancing with the use of special metrics obtained by Java object observation. SOAJA comprises mechanisms and algorithms for automatic placement and adaptation of application objects, in response to evolution of resource availability. Under control of SOAJA, parallel Java objects can be optimally allocated to Grid nodes before execution and next migrated at runtime to less loaded nodes to maintain the balance of loads of constituent JVMs. SOAJA mechanisms employ computation power metrics based on measurements of the idle time of processor nodes and communication bandwidth metrics for network resources based on statistical assessment of the existing traffic. Due to these mechanisms the granularity of computing and distribution of the application elements on the Grid platform can be optimally controlled.

Published
2009

14. Resource Management in Grids: Overview and a discussion of a possible approach for an Agent-Based Middleware

Author

Maria Ganzha, Nasrollah Moghadam Charkari, Pavel Telegin, Marcin Paprzycki, Michal Drozdowicz, Ivan Lirkov, Mehrdad Senobari, Richard Olejnik, Tarbiat Modares University [Tehran], Systems Research Institute [Warsaw] (IBS PAN), Polska Akademia Nauk = Polish Academy of Sciences (PAN), Contributions of the Data parallelism to real time (DART), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institute for Parallel Processing (IPP BAS), Bulgarian Academy of Sciences (BAS), SuperComputing Center of Russian Academy of Sciences, Russian Academy of Sciences [Moscow] (RAS), PICS CNRS, Saxe-Coburg Publications, Stirlingshire, UK, and CNRS - Académie des Sciences de Pologne

Subjects
Job scheduler, Process management, metaschedulers, agent-based resource management, Distributed computing, 020206 networking & telecommunications, 02 engineering and technology, Grid, computer.software_genre, grid computing, Resource (project management), Grid computing, Software agent, [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], Middleware, 0202 electrical engineering, electronic engineering, information engineering, Resource allocation, 020201 artificial intelligence & image processing, Resource management, resource management, Business, job scheduling, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], computer
Abstract

14 pages; International audience; Resource management and job scheduling are important research issues in computational grids. When software agents are used as resource managers and brokers in the Grid a number of additional issues and possible approaches materialize. The aim of this chapter is twofold. First, we discuss traditional job scheduling in grids, and when agents are utilized as grid middleware. Second, we use this as a context for discussion of how job scheduling can be done in the agent-based system under development.

Published
2009
Full Text
View/download PDF

15. Data Mining on Desktop Grid Platforms

Author

Fiolet, Valerie, Olejnik, Richard, Laskowski, Eryk, Masko, Łukasz, Tudruj, Marek, Toursel, Bernard, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Institute of Computer Science [Mons], University of Mons [Belgium] (UMONS), LIFL - DART/Émeraude, Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Contributions of the Data parallelism to real time (DART), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), Institute of Computer Science [Warszawa], Polska Akademia Nauk = Polish Academy of Sciences (PAN), Institue of Computer Science [Pologne], Polish-Japanese Institute of Information Technology (PJIIT), and Collaboration CNRS/Académie des Sciences de Pologne

Subjects
ACM: E.: Data/E.0: GENERAL, ACM: D.: Software/D.2: SOFTWARE ENGINEERING, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], Computer Science::Distributed, Parallel, and Cluster Computing
Abstract

International audience; Very large data volumes and high computation costs in data mining applications justify the use for them of Grid-level massive parallelism. The paper concerns Grid-oriented implementation of the DisDaMin (Distributed Data Mining) project, which proposes distributed knowledge discovery through parallelization of data mining tasks. DisDaMin solves data mining problems by using new distributed algorithms based on special clusterized data decomposition and asynchronous task processing, which match the Grid computing features. The DisDaMin algorithms are embedded inside the DG-ADAJ (Desktop-Grid Adaptative Application in Java) system, which is a middleware platform for Desktop Grid. It provides adaptive control of distributed applications written in Java for Grid or Desktop Grid. It allows an optimized distribution of applications on clusters of Java Virtual Machines, monitoring of application execution and dynamic on-line balancing of processing and communication. Simulations were performed to prove the efficiency of the proposed mechanisms. They were carried on using the French national project Grid'5000 (part of the CoreGrid project) and the DG-ADAJ.

Published
2008
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results