Distributed Multi-Agent Management in a parallel-programming simulation and analysis environment: diffusion, guarded migration, merger and termination.

Slides:



Advertisements
Similar presentations
An Overview Of Virtual Machine Architectures Ross Rosemark.
Advertisements

Chap 4 Multithreaded Programming. Thread A thread is a basic unit of CPU utilization It comprises a thread ID, a program counter, a register set and a.
Threads. Objectives To introduce the notion of a thread — a fundamental unit of CPU utilization that forms the basis of multithreaded computer systems.
Silberschatz, Galvin and Gagne ©2009Operating System Concepts – 8 th Edition Chapter 4: Threads.
1 Chapter 5 Threads 2 Contents  Overview  Benefits  User and Kernel Threads  Multithreading Models  Solaris 2 Threads  Java Threads.
Development of Parallel Simulator for Wireless WCDMA Network Hong Zhang Communication lab of HUT.
Oracle Database Architectures Are Extremely Complex, And Very Expensive. All of Their Complexity Goes Away ! The Snippet Engine Network Architectures Are.
Modified from Silberschatz, Galvin and Gagne ©2009 Lecture 7 Chapter 4: Threads (cont)
© David Kirk/NVIDIA and Wen-mei W. Hwu, ECE 498AL, University of Illinois, Urbana-Champaign 1 Structuring Parallel Algorithms.
Based on Silberschatz, Galvin and Gagne  2009 Threads Definition and motivation Multithreading Models Threading Issues Examples.
4.7.1 Thread Signal Delivery Two types of signals –Synchronous: Occur as a direct result of program execution Should be delivered to currently executing.
Company LOGO Development of Resource/Commander Agents For AgentTeamwork Grid Computing Middleware Funded By Prepared By Enoch Mak Spring 2005.
Chris Rouse CSS Cooperative Education Faculty Research Internship Winter / Spring 2014.
Inter-cluster Job Deployment by AgentTeamwork Sentinel Agents Emory Horvath CSS497 Spring 2006 Advisor: Dr. Munehiro Fukuda.
Silberschatz, Galvin and Gagne ©2009Operating System Concepts – 8 th Edition Chapter 4: Threads.
C++ Agents Implementation Chris Rouse CSS 497. Outline  Finish Agent Implementation  Involves changes to the following classes:  Agents_base.h/.cpp.
Parallel NetCDF Library Development Formerly “Sensor Cloud Integration” Kelsey Weingartner.
CSS Cooperative Education Faculty Research Internship Spring / Summer 2013 Richard Romanus 08/23/2013 Developing and Extending the MASS Library (Java)
SensIT PI Meeting, January 15-17, Self-Organizing Sensor Networks: Efficient Distributed Mechanisms Alvin S. Lim Computer Science and Software Engineering.
@2011 Mihail L. Sichitiu1 Android Introduction Platform Overview.
Silberschatz, Galvin and Gagne ©2011Operating System Concepts Essentials – 8 th Edition Chapter 4: Threads.
Silberschatz, Galvin and Gagne ©2009Operating System Concepts – 8 th Edition Chapter 4: Threads.
ICOM 5995: Performance Instrumentation and Visualization for High Performance Computer Systems Lecture 7 October 16, 2002 Nayda G. Santiago.
Chapter 6 Operating System Support. This chapter describes how middleware is supported by the operating system facilities at the nodes of a distributed.
Managing a Cloud For Multi Agent System By, Pruthvi Pydimarri, Jaya Chandra Kumar Batchu.
Threads, Thread management & Resource Management.
Computational Design of the CCSM Next Generation Coupler Tom Bettge Tony Craig Brian Kauffman National Center for Atmospheric Research Boulder, Colorado.
Multi-Threaded Application CSNB534 Asma Shakil. Overview Software applications employ a strategy called multi- threaded programming to split tasks into.
Copyright © George Coulouris, Jean Dollimore, Tim Kindberg This material is made available for private study and for direct.
ESC499 – A TMD-MPI/MPE B ASED H ETEROGENEOUS V IDEO S YSTEM Tony Zhou, Prof. Paul Chow April 6 th, 2010.
Comparison of Distributed Operating Systems. Systems Discussed ◦Plan 9 ◦AgentOS ◦Clouds ◦E1 ◦MOSIX.
Advanced Spectrum Management in Multicell OFDMA Networks enabling Cognitive Radio Usage F. Bernardo, J. Pérez-Romero, O. Sallent, R. Agustí Radio Communications.
Issues Autonomic operation (fault tolerance) Minimize interference to applications Hardware support for new operating systems Resource management (global.
April 23, 2013Research in Progress Seminar MASS: A Multi-Agent Spatial Simulation Library Munehiro Fukuda, Ph.D. School of Science, Technology, Engineering,
Mobile Agent Migration Problem Yingyue Xu. Energy efficiency requirement of sensor networks Mobile agent computing paradigm Data fusion, distributed processing.
ABone Architecture and Operation ABCd — ABone Control Daemon Server for remote EE management On-demand EE initiation and termination Automatic EE restart.
Hwajung Lee.  Interprocess Communication (IPC) is at the heart of distributed computing.  Processes and Threads  Process is the execution of a program.
CSS 700: MASS CUDA Parallel‐Computing Library for Multi‐Agent Spatial Simulation Fall Quarter 2014 Nathaniel Hart UW Bothell Computing & Software Systems.
A Software Framework for Distributed Services Michael M. McKerns and Michael A.G. Aivazis California Institute of Technology, Pasadena, CA Introduction.
Distributed mega-scale Agent Management in MASS: diffusion, guarded migration, merger and termination Cherie Wasous CSS_700 Thesis – Winter 2014 (Feb.
ATLAS Grid Requirements A First Draft Rich Baker Brookhaven National Laboratory.
CUDA Basics. Overview What is CUDA? Data Parallelism Host-Device model Thread execution Matrix-multiplication.
Lecture 3 Threads Erick Pranata © Sekolah Tinggi Teknik Surabaya 1.
7. Grid Computing Systems and Resource Management
SensorWare: Distributed Services for Sensor Networks Rockwell Science Center and UCLA.
Parallel processing
© David Kirk/NVIDIA and Wen-mei W. Hwu, ECE 498AL, University of Illinois, Urbana-Champaign 1 ECE 498AL Spring 2010 Programming Massively Parallel.
McGraw-Hill©The McGraw-Hill Companies, Inc., 2000 OS 1.
EEL 5937 Mobile agents EEL 5937 Multi Agent Systems Lotzi Bölöni.
Silberschatz, Galvin and Gagne ©2013 Operating System Concepts – 9 th Edition Chapter 4: Threads.
Page 1 2P13 Week 1. Page 2 Page 3 Page 4 Page 5.
Next Generation of Apache Hadoop MapReduce Owen
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
Distributed mega-scale Agent Management in MASS: diffusion, guarded migration, merger and termination Cherie Wasous CSS_700 Thesis – Winter 2014 (Jan.
Real-Time Systems Laboratory Seolyoung, Jeong JADE (Java Agent DEvelopment framework )
Silberschatz, Galvin and Gagne ©2009Operating System Concepts – 8 th Edition Chapter 4: Threads.
Hongbin Li 11/13/2014 A Debugger of Parallel Mutli- Agent Spatial Simulation.
MASS C++ Updates JENNIFER KOWALSKY, What is MASS? Multi-Agent Spatial Simulation A library for parallelizing simulations and data analysis Uses.
INTRODUCTION TO HIGH PERFORMANCE COMPUTING AND TERMINOLOGY.
Application of Design Patterns to Geometric Decompositions V. Balaji, Thomas L. Clune, Robert W. Numrich and Brice T. Womack.
Chapter 4: Multithreaded Programming
Thank you, chairman for the kind introduction. And hello, everyone.
Enterprise Computing Collaboration System Example
Parallel NetCDF + MASS Development
MASS CUDA Performance Analysis and Improvement
Chapter 4: Threads.
Mobile Agents.
Modified by H. Schulzrinne 02/15/10 Chapter 4: Threads.
CHAPTER 4:THreads Bashair Al-harthi OPERATING SYSTEM
Chapter 4: Threads & Concurrency
Presentation transcript:

Distributed Multi-Agent Management in a parallel-programming simulation and analysis environment: diffusion, guarded migration, merger and termination Cherie Wasous CSS_700 Thesis Research – Autumn 2013

“parallel-programming simulation and analysis environment”

MASS (Multi-Agent Spatial Simulation ) parallel computing software library from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” “parallel-programming simulation and analysis environment”

MASS (Multi-Agent Spatial Simulation ) parallel computing software library Simplifies the task of creating and running parallel applications across multiple computers and CPU cores. from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” “parallel-programming simulation and analysis environment”

MASS (Multi-Agent Spatial Simulation ) parallel computing software library Simplifies the task of creating and running parallel applications across multiple computers and CPU cores. from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” “parallel-programming simulation and analysis environment”

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS v.1 enables two primary types of simulations: 1.A Stand-alone Grid of Stationary Locations Example: A map and its grid of sub-locations

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS v.1 enables two primary types of simulations: 1.A Stand-alone Grid of Stationary Locations Example: A map and its grid of sub-locations 2.A Grid of Stationary Locations with Mobile Units Example: A map, its grid of sub-locations, and mobile units

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS Library 1. Stand-alone Grid of Stationary Locations Composed of: The Grid of Locations referred to as Places in MASS contains the grid of stationary locations

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS Library 1. Stand-alone Grid of Stationary Locations Composed of: The Grid of Locations referred to as Places in MASS contains the grid of stationary locations Single Stationary Location referred to as a Place object in MASS contains basic information about the local place Example: local Temperature

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS Library 2. Grid of Stationary Locations with Mobile Units Composed of: Collection of Mobile Units referred to as “Bag of” Agents in MASS each Place location has a “Bag of” Agents contains the mobile units for the Place location

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” MASS Library 2. Grid of Stationary Locations with Mobile Units Composed of: Collection of Mobile Units referred to as “Bag of” Agents in MASS each Place location has a “Bag of” Agents contains the mobile units for the Place location Mobile Unit referred to as Agent in MASS contains basic information about the mobile unit Example: Amount of sugar an ant (agent) has consumed

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” Overall MASS Framework Places Maintain & manages the Place locations Manages exchange between the Place locations callAll( ) callSome( ) exchangeAll( ) exchangeBoundary( )

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” Overall MASS Framework Places Maintain & manages the Place locations Manages exchange between the Place locations Place Maintains Place location data Provides a user software interface callAll( ) callSome( ) exchangeAll( ) exchangeBoundary( ) callMethod( ) {User created functions}

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” Overall MASS Framework Places Maintain & Manages the Place locations Manages exchange between the Place locations Place Maintains Place location data Provides a user software interface Agents Maintains & Manages the Agent units Manages the exchange and migration of Agent units callAll( ) callSome( ) exchangeAll( ) exchangeBoundary( ) callMethod( ) {User created functions} callAll( ) manageAll( ) migrate( ) spawn( ) kill( )

from: Romanus, css497 summer2013, “Developing and Extending the MASS Library (Java) Places.exchangeBoundary( )” Overall MASS Framework Places Maintain & Manages the Place locations Manages exchange between the Place locations Place Maintains Place location data Provides a user software interface Agents Maintains & Manages the Agent units Manages the exchange and migration of Agent units Agent Maintains the Agent data Provides a user software interface callAll( ) callSome( ) exchangeAll( ) exchangeBoundary( ) callMethod( ) {User created functions} callAll( ) manageAll( ) migrate( ) spawn( ) kill( ) callMethod( ) {User created functions}

MASS execution model from: Chuang, MS Thesis, “Design and Qualitative/Quantative Analysis of Multi-Agent Spatial Simulation Library”

from: Fukuda, et al, NSF proposal Fall 2013, “Multi-Agent-Based Parallelization of Scientific Data Analysis and Simulation” MASS v.2 Supports NetCDF in Parallel. Facilitates big-data analysis.

MASS v.future Enhance Multi-Agent Management. Eases adoption and improves performance for scientific data analysis and simulation.

“diffusion, guarded migration, merger, and termination” Diffusion MASS currently can: Create an agent at every place element Create an agent at specified place elements Create a large number of agents and spread across the place elements

“diffusion, guarded migration, merger, and termination” Diffusion MASS currently can: Create an agent at every place element Create an agent at specified place elements Create a large number of agents and spread across the place elements MASS future enhancements: Improve efficiency of creation more local ; reducing communication between nodes and between threads “Diffusion” option – where a few agents are spread across the place elements at each thread, and they efficiently clone themselves locally to all adjacent place elements ; leaving a footprint where visited

“diffusion, guarded migration, merger, and termination” Diffusion MASS currently can: Create an agent at every place element Create an agent at specified place elements Create a large number of agents and spread across the place elements MASS future enhancements: Improve efficiency of creation more local ; reducing communication between nodes and between threads “Diffusion” option – where a few agents are spread across the place elements at each thread, and they efficiently clone themselves locally to all adjacent place elements ; leaving a footprint where visited Continue Focus on User Interface: Keep it Simple, Powerful and Efficient.

“diffusion, guarded migration, merger, and termination” Guarded Migration MASS currently does not limit the number of agents migrating into a single place element. However, Traffic Simulation – limit just one car in a space Epidemic Simulations – limit each household to X number of people

“diffusion, guarded migration, merger, and termination” Guarded Migration MASS currently does not limit the number of agents migrating into a single place element. However, Traffic Simulation – limit just one car in a space Epidemic Simulations – limit each household to X number of people MASS future enhancements: Allow user to specify maximum agents per single place element Guarded Migration – using a fair, deterministic, distributed arbitration technique

“diffusion, guarded migration, merger, and termination” Guarded Migration MASS currently does not limit the number of agents migrating into a single place element. However, Traffic Simulation – limit just one car in a space Epidemic Simulations – limit each household to X number of people MASS future enhancements: Allow user to specify maximum agents per single place element Guarded Migration – using a fair, deterministic, distributed arbitration technique Continue Focus on User Interface: Keep it Simple, Powerful and Efficient.

“diffusion, guarded migration, merger, and termination” Merger, and Termination MASS currently does not support agent merge command. Cumbersome for user to write code for this. MASS currently only supports kill command for single agent. Cumbersome and inefficient for user to kill each agent.

“diffusion, guarded migration, merger, and termination” Merger, and Termination MASS currently does not support agent merge command. Cumbersome for user to write code for this. MASS currently only supports kill command for single agent. Cumbersome and inefficient for user to kill each agent. Continue Focus on User Interface: Keep it Simple, Powerful and Efficient.

Questions ???