Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Robert Schaefer, AGH University of Science and Technology,

Slides:



Advertisements
Similar presentations
A Workflow Engine with Multi-Level Parallelism Supports Qifeng Huang and Yan Huang School of Computer Science Cardiff University
Advertisements

Interaction model of grid services in mobile grid environment Ladislav Pesicka University of West Bohemia.
Grid Communication Simulator Boro Jakimovski Marjan Gusev Institute of Informatics Faculty of Natural Sciences and Mathematics University of Sts. Cyril.
Using Parallel Genetic Algorithm in a Predictive Job Scheduling
Requirements on the Execution of Kahn Process Networks Marc Geilen and Twan Basten 11 April 2003 /e.
Dinker Batra CLUSTERING Categories of Clusters. Dinker Batra Introduction A computer cluster is a group of linked computers, working together closely.
Summary Background –Why do we need parallel processing? Applications Introduction in algorithms and applications –Methodology to develop efficient parallel.
A Grid Parallel Application Framework Jeremy Villalobos PhD student Department of Computer Science University of North Carolina Charlotte.
Agent Mediated Grid Services in e-Learning Chun Yan, Miao School of Computer Engineering Nanyang Technological University (NTU) Singapore April,
Computer Science Department 1 Load Balancing and Grid Computing David Finkel Computer Science Department Worcester Polytechnic Institute.
Parallel Programming Models and Paradigms
1 Introduction to Load Balancing: l Definition of Distributed systems. Collection of independent loosely coupled computing resources. l Load Balancing.
Inferring the Topology and Traffic Load of Parallel Programs in a VM environment Ashish Gupta Peter Dinda Department of Computer Science Northwestern University.
Mapping Techniques for Load Balancing
07/14/08. 2 Points Introduction. Cluster and Supercomputers. Cluster Types and Advantages. Our Cluster. Cluster Performance. Cluster Computer for Basic.
MATE-EC2: A Middleware for Processing Data with Amazon Web Services Tekin Bicer David Chiu* and Gagan Agrawal Department of Compute Science and Engineering.
Parallelization: Conway’s Game of Life. Cellular automata: Important for science Biology – Mapping brain tumor growth Ecology – Interactions of species.
Design and Implementation of a Single System Image Operating System for High Performance Computing on Clusters Christine MORIN PARIS project-team, IRISA/INRIA.
A.V. Bogdanov Private cloud vs personal supercomputer.
Word Wide Cache Distributed Caching for the Distributed Enterprise.
Parallel Processing LAB NO 1.
Lecture 4: Parallel Programming Models. Parallel Programming Models Parallel Programming Models: Data parallelism / Task parallelism Explicit parallelism.
RUNNING PARALLEL APPLICATIONS BEYOND EP WORKLOADS IN DISTRIBUTED COMPUTING ENVIRONMENTS Zholudev Yury.
Research Achievements Kenji Kaneda. Agenda Research background and goal Research background and goal Overview of my research achievements Overview of.
Optimized Java computing as an application for Desktop Grid Olejnik Richard 1, Bernard Toursel 1, Marek Tudruj 2, Eryk Laskowski 2 1 Université des Sciences.
Heterogeneous Parallelization for RNA Structure Comparison Eric Snow, Eric Aubanel, and Patricia Evans University of New Brunswick Faculty of Computer.
Neural and Evolutionary Computing - Lecture 10 1 Parallel and Distributed Models in Evolutionary Computing  Motivation  Parallelization models  Distributed.
DISTRIBUTED COMPUTING
Active Monitoring in GRID environments using Mobile Agent technology Orazio Tomarchio Andrea Calvagna Dipartimento di Ingegneria Informatica e delle Telecomunicazioni.
Service Architecture of Grid Faults Diagnosis Expert System Based on Web Service Wang Mingzan, Zhang ziye Northeastern University, Shenyang, China.
Young Suk Moon Chair: Dr. Hans-Peter Bischof Reader: Dr. Gregor von Laszewski Observer: Dr. Minseok Kwon 1.
Performance Model & Tools Summary Hung-Hsun Su UPC Group, HCS lab 2/5/2004.
Computer Science and Engineering Parallel and Distributed Processing CSE 8380 March 01, 2005 Session 14.
Cracow Grid Workshop, October 27 – 29, 2003 Institute of Computer Science AGH Design of Distributed Grid Workflow Composition System Marian Bubak, Tomasz.
Evaluation of Agent Teamwork High Performance Distributed Computing Middleware. Solomon Lane Agent Teamwork Research Assistant October 2006 – March 2007.
April 26, CSE8380 Parallel and Distributed Processing Presentation Hong Yue Department of Computer Science & Engineering Southern Methodist University.
BOF: Megajobs Gracie: Grid Resource Virtualization and Customization Infrastructure How to execute hundreds of thousands tasks concurrently on distributed.
Cloud Age Time to change the programming paradigm?
Mobile Agent Migration Problem Yingyue Xu. Energy efficiency requirement of sensor networks Mobile agent computing paradigm Data fusion, distributed processing.
Summary Background –Why do we need parallel processing? Moore’s law. Applications. Introduction in algorithms and applications –Methodology to develop.
1 Job Scheduling for Grid Computing on Metacomputers Keqin Li Proceedings of the 19th IEEE International Parallel and Distributed Procession Symposium.
Service-oriented Resource Broker for QoS-Guaranteed in Grid Computing System Yichao Yang, Jin Wu, Lei Lang, Yanbo Zhou and Zhili Sun Centre for communication.
Enabling the Future Service-Oriented Internet (EFSOI 2008) Supporting end-to-end resource virtualization for Web 2.0 applications using Service Oriented.
Mobile Agents For Mobile Computing Department Of Computer Science – Dartmouth College Robert Gray David Kotz Saurab Nog Daniela Rus George Cybenko.
Department of Computer Science MapReduce for the Cell B. E. Architecture Marc de Kruijf University of Wisconsin−Madison Advised by Professor Sankaralingam.
ProActive components and legacy code Matthieu MOREL.
CS- 492 : Distributed system & Parallel Processing Lecture 7: Sun: 15/5/1435 Foundations of designing parallel algorithms and shared memory models Lecturer/
A Grid-enabled Multi-server Network Game Architecture Tianqi Wang, Cho-Li Wang, Francis C.M.Lau Department of Computer Science and Information Systems.
Static Process Scheduling
An Overview of Scientific Workflows: Domains & Applications Laboratoire Lorrain de Recherche en Informatique et ses Applications Presented by Khaled Gaaloul.
A System Performance Model Distributed Process Scheduling.
Parallelization Strategies Laxmikant Kale. Overview OpenMP Strategies Need for adaptive strategies –Object migration based dynamic load balancing –Minimal.
I MAGIS is a joint project of CNRS - INPG - INRIA - UJF iMAGIS-GRAVIR / IMAG Efficient Parallel Refinement for Hierarchical Radiosity on a DSM computer.
DS-Grid: Large Scale Distributed Simulation on the Grid Georgios Theodoropoulos Midlands e-Science Centre University of Birmingham, UK Stephen John Turner,
NGS computation services: APIs and.
Parallelizing Functional Tests for Computer Systems Using Distributed Graph Exploration Alexey Demakov, Alexander Kamkin, and Alexander Sortov
Computer Science and Engineering Parallel and Distributed Processing CSE 8380 April 28, 2005 Session 29.
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
SYSTEM MODELS FOR ADVANCED COMPUTING Jhashuva. U 1 Asst. Prof CSE
Dynamic Mobile Cloud Computing: Ad Hoc and Opportunistic Job Sharing.
INTRODUCTION TO HIGH PERFORMANCE COMPUTING AND TERMINOLOGY.
Introduction to Parallel Computing: MPI, OpenMP and Hybrid Programming
Dynamic Deployment of VO Specific Condor Scheduler using GT4
Parallel Programming By J. H. Wang May 2, 2017.
Liang Chen Advisor: Gagan Agrawal Computer Science & Engineering
Ch > 28.4.
AGENT OS.
Towards Next Generation Panel at SAINT 2002
Summary Background Introduction in algorithms and applications
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Robert Schaefer, AGH University of Science and Technology, Kraków, Poland The Group Members: Maciej Smołka Jagiellonian University, Kraków, Poland Piotr Uhruski, Marek Grochowski AGH University of Science and Technology, Kraków, Poland

Motivation Distributed computation paradigms Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics  message passing libraries PVM Parallel Virtual Machine (1990), MPI Message-Passing Interface (1992)  SOA (Service Oriented Architecture) CORBA (1996), SOAP (1998)  GRID Condor (1997), Globus (1998), OGSI/OGSA (2002) Some drawbacks :  partially manual resources allocation  time consuming deployment and maintenance of the system  usually assuming static resources

Motivation Computation + Agent logic Agents environment Middleware Application Network Heterogeneous Operating Systems Distributed computing using MAS technology Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Sample task implementations Smart Solid Connections Overview of the OCTOPUS architecture Middleware Application Diffusion scheduling in multiagent computing system Java CORBA Octopus... Java CORBA Octopus Java CORBA Octopus Agents (scheduling, grain control) Agent SDK Virtual Topology VCN MotivationArchitectureAlgorithmsExamplesDynamics

Diffusion scheduling in multiagent computing system Architecture OCTOPUS Key Tasks  Execute Agents  Distributed Communication  Environment Information  Migration  Virtual Network Topology  Virtual Computation Node (VCN)  Agent’s Construction Kit Agents environment MotivationArchitectureAlgorithmsExamplesDynamics

Algorithms  Analogy to molecular diffusion phenomena  Local scheduling method – every agent is autonomously searching and allocating resources at neighbouring node  We hope to obtain the asymptotically balanced load Diffusion scheduling idea Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Diffusion schduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Diffusion scheduling – main parameters

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Diffusion scheduling algorithm

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Binding energy formulas under consideration (2) (1)

Algorithms  Internal job is a dynamic structure of atomic jobs  Sequential computation of contained atomic jobs  New agent creation when the number of contained jobs exceeds the capacity of the agent Controlling the computation grain – Container agent Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Algorithms „Weak” synchronization strategy – „Leo the Professional” agent (J. Momot, K. Kossacki – 2004)  Migrates through the network and gathers information about computing agents  Responsible for removing redundancy  Allows to avoid total synchronization of the local system Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Tests Speedup vs. grain in CAE computation Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Tests Overhead of the Agent Oriented technology (the case of HGS computation) Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Tests Speedup of the Diffusion Scheduling (the case of HGS computation) Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Communication dependent rules „LAN” case „WAN” emulation

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Experiments in the local area network (1)(2)

Diffusion scheduling in multiagent computing system MotivationArchitectureAlgorithmsExamplesDynamics Experiments in the wide area network (2)(1)

Conclusions MotivationArchitectureAlgorithmsExamplesDynamics Diffusion scheduling in multiagent computing system Preliminaries

Conclusions MotivationArchitectureAlgorithmsExamplesDynamics Diffusion scheduling in multiagent computing system State equations

Conclusions MotivationArchitectureAlgorithmsExamplesDynamics Diffusion scheduling in multiagent computing system Optimal scheduling problem

Conclusions Diffusion scheduling is an effective tool of managing large-scale distributed systems. It is achieved by the low complexity of local scheduling rules and only local communication. It ensures proper agent location in the dynamic network environment. Introduced formal description provides the discrete equation of evolution and the characterization of admissible controls as well as the cost functional for computing MAS. The optimal scheduling problem posses the unique solution in the class of stationary strategies. Total overhead is low in comparison with the computation time (~ 5%). No significant requirements imposed over applications. Diffusion scheduling in multiagent computing system

Thank you for your patience! Diffusion scheduling in multiagent computing system

Publications