A Lightweight Platform for Integration of Mobile Devices into Pervasive Grids Stavros Isaiadis, Vladimir Getov University of Westminster, London {s.isaiadis,

Slides:



Advertisements
Similar presentations
Large-Scale, Adaptive Fabric Configuration for Grid Computing Peter Toft HP Labs, Bristol June 2003 (v1.03) Localised for UK English.
Advertisements

1 Towards an Open Service Framework for Cloud-based Knowledge Discovery Domenico Talia ICAR-CNR & UNIVERSITY OF CALABRIA, Italy Cloud.
OMV Ontology Metadata Vocabulary April 10, 2008 Peter Haase.
…to Ontology Repositories Mathieu dAquin Knowledge Media Institute, The Open University From…
CSF4 Meta-Scheduler Tutorial 1st PRAGMA Institute Zhaohui Ding or
ASYCUDA Overview … a summary of the objectives of ASYCUDA implementation projects and features of the software for the Customs computer system.
Designing Services for Grid-based Knowledge Discovery A. Congiusta, A. Pugliese, Domenico Talia, P. Trunfio DEIS University of Calabria ITALY
CPSCG: Constructive Platform for Specialized Computing Grid Institute of High Performance Computing Department of Computer Science Tsinghua University.
Abstraction Layers Why do we need them? –Protection against change Where in the hourglass do we put them? –Computer Scientist perspective Expose low-level.
Dynasoar Dynamic Deployment of Web Services on a Grid or the Internet or Why its good to be Jobless Paul Watson School of Computing Science.
The National Grid Service and OGSA-DAI Mike Mineter
Current status of grids: the need for standards Mike Mineter TOE-NeSC, Edinburgh.
OMII-UK Steven Newhouse, Director. © 2 OMII-UK aims to provide software and support to enable a sustained future for the UK e-Science community and its.
Auto-scaling Axis2 Web Services on Amazon EC2 By Afkham Azeez.
Multi-level SLA Management for Service-Oriented Infrastructures Wolfgang Theilmann, Ramin Yahyapour, Joe Butler, Patrik Spiess consortium / SAP.
Application Server Based on SoftSwitch
1 Towards Building Generic Grid Services Platform A component oriented approach Jeyarajan Thiyagalingam Stavros Isaiadis, Vladimir Getov Distributed and.
Distributed Processing, Client/Server and Clusters
IONA Technologies Position Paper Constraints and Capabilities for Web Services
Database System Concepts and Architecture
Executional Architecture
Global Analysis and Distributed Systems Software Architecture Lecture # 5-6.
1 Chapter 11: Data Centre Administration Objectives Data Centre Structure Data Centre Structure Data Centre Administration Data Centre Administration Data.
Mobile Agents: A Key for Effective Pervasive Computing Roberto Speicys Cardoso & Fabio Kon University of São Paulo - Brazil.
Managing Agent Platforms with the Simple Network Management Protocol Brian Remick Thesis Defense June 26, 2015.
McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 17 Client-Server Processing, Parallel Database Processing,
Institute of Computer Science AGH Performance Monitoring of Java Web Service-based Applications Włodzimierz Funika, Piotr Handzlik Lechosław Trębacz Institute.
Adaptive Server Farms for the Data Center Contact: Ron Sheen Fujitsu Siemens Computers, Inc Sever Blade Summit, Getting the.
Sergey Belov, Tatiana Goloskokova, Vladimir Korenkov, Nikolay Kutovskiy, Danila Oleynik, Artem Petrosyan, Roman Semenov, Alexander Uzhinskiy LIT JINR The.
Data Management Kelly Clynes Caitlin Minteer. Agenda Globus Toolkit Basic Data Management Systems Overview of Data Management Data Movement Grid FTP Reliable.
Mobile Agent Technology for the Management of Distributed Systems - a Case Study Claudia Raibulet& Claudio Demartini Politecnico di Torino, Dipartimento.
A Lightweight Platform for Integration of Resource Limited Devices into Pervasive Grids Stavros Isaiadis and Vladimir Getov University of Westminster
Software Architecture Framework for Ubiquitous Computing Divya ChanneGowda Athrey Joshi.
Active Monitoring in GRID environments using Mobile Agent technology Orazio Tomarchio Andrea Calvagna Dipartimento di Ingegneria Informatica e delle Telecomunicazioni.
Ramiro Voicu December Design Considerations  Act as a true dynamic service and provide the necessary functionally to be used by any other services.
Grid Resource Allocation and Management (GRAM) Execution management Execution management –Deployment, scheduling and monitoring Community Scheduler Framework.
Semantic Interoperability Berlin, 25 March 2008 Semantically Enhanced Resource Allocator Marc de Palol Jorge Ejarque, Iñigo Goiri, Ferran Julià, Jordi.
Grid Technologies  Slide text. What is Grid?  The World Wide Web provides seamless access to information that is stored in many millions of different.
The Grid System Design Liu Xiangrui Beijing Institute of Technology.
GEM Portal and SERVOGrid for Earthquake Science PTLIU Laboratory for Community Grids Geoffrey Fox, Marlon Pierce Computer Science, Informatics, Physics.
1 4/23/2007 Introduction to Grid computing Sunil Avutu Graduate Student Dept.of Computer Science.
Enabling Peer-to-Peer SDP in an Agent Environment University of Maryland Baltimore County USA.
Tool Integration with Data and Computation Grid GWE - “Grid Wizard Enterprise”
Middleware for Grid Computing and the relationship to Middleware at large ECE 1770 : Middleware Systems By: Sepehr (Sep) Seyedi Date: Thurs. January 23,
NA-MIC National Alliance for Medical Image Computing UCSD: Engineering Core 2 Portal and Grid Infrastructure.
Cracow Grid Workshop ‘06 17 October 2006 Execution Management and SLA Enforcement in Akogrimo Antonios Litke Antonios Litke, Kleopatra Konstanteli, Vassiliki.
Grid programming with components: an advanced COMPonent platform for an effective invisible grid © 2006 GridCOMP Grids Programming with components. An.
What is SAM-Grid? Job Handling Data Handling Monitoring and Information.
6/23/2005 R. GARDNER OSG Baseline Services 1 OSG Baseline Services In my talk I’d like to discuss two questions:  What capabilities are we aiming for.
Dynamic Service Aggregation in Heterogeneous Grids Stavros Isaiadis and Vladimir Getov University of Westminster Heraklion, Crete, 13 th June 2007
Internet of Things. IoT Novel paradigm – Rapidly gaining ground in the wireless scenario Basic idea – Pervasive presence around us a variety of things.
International Symposium on Grid Computing (ISGC-07), Taipei - March 26-29, 2007 Of 16 1 A Novel Grid Resource Broker Cum Meta Scheduler - Asvija B System.
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
Development of e-Science Application Portal on GAP WeiLong Ueng Academia Sinica Grid Computing
Aneka Cloud ApplicationPlatform. Introduction Aneka consists of a scalable cloud middleware that can be deployed on top of heterogeneous computing resources.
Testing and integrating the WLCG/EGEE middleware in the LHC computing Simone Campana, Alessandro Di Girolamo, Elisa Lanciotti, Nicolò Magini, Patricia.
GRID ANATOMY Advanced Computing Concepts – Dr. Emmanuel Pilli.
Tool Integration with Data and Computation Grid “Grid Wizard 2”
DIRAC Project A.Tsaregorodtsev (CPPM) on behalf of the LHCb DIRAC team A Community Grid Solution The DIRAC (Distributed Infrastructure with Remote Agent.
Gaia An Infrastructure for Active Spaces Prof. Klara Nahrstedt Prof. David Kriegman Prof. Dennis Mickunas
Grid Execution Management for Legacy Code Architecture Exposing legacy applications as Grid services: the GEMLCA approach Centre.
SAM architecture EGEE 07 Service Availability Monitor for the LHC experiments Simone Campana, Alessandro Di Girolamo, Nicolò Magini, Patricia Mendez Lorenzo,
Spark on Entropy : A Reliable & Efficient Scheduler for Low-latency Parallel Jobs in Heterogeneous Cloud Huankai Chen PhD Student at University of Kent.
1 Grid2003 Monitoring, Metrics, and Grid Cataloging System Leigh GRUNDHOEFER, Robert QUICK, John HICKS (Indiana University) Robert GARDNER, Marco MAMBELLI,
Introduction to Distributed Platforms
The Open Grid Service Architecture (OGSA) Standard for Grid Computing
GGF15 – Grids and Network Virtualization
SDM workshop Strawman report History and Progress and Goal.
MWCN`03 Singapore 28 October 2003
Presentation transcript:

A Lightweight Platform for Integration of Mobile Devices into Pervasive Grids Stavros Isaiadis, Vladimir Getov University of Westminster, London {s.isaiadis, HPCC 2005, Sorrento, Italy

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 2 Outline Overview & Motivation Platform Architecture Current Implementation Status Future Plans Conclusion & Questions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 3 Overview - Goals A proxy-based architecture that will allow the integration of mobile/limited devices into Grid systems in an efficient way A lightweight components-based platform that can be deployed in limited devices without draining resources A set of middleware components built on top of the core platform, including (among other): –A lightweight monitoring framework –Failure resilience components that will provide a virtually reliable environment –Parallelization components to support automatic task extraction and distribution (assuming suitable parallel/distributed programming model)

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 4 Motivation Future Grid systems should be truly pervasive and ubiquitous While access to the Grid and job submission from mobile/limited devices is generally supported (e.g. through portals), contribution of resources is very difficult Resource constraints make installation of Grid middleware prohibiting Mobile and pervasive computing attract a big part of current research and industry funds and hold a big share of the market pie Small and/or mobile devices increasingly offer functionality not available in traditional Grid nodes –multimedia equipment, sensors, global positioning systems etc.

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 5 Outline Overview & Motivation Platform Architecture Current Implementation Status Future Plans Conclusion & Questions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 6 Integration Problems: Dynamicity & Limited Resources Dynamicity of small devices may penalize overall Grid performance and is not acceptable in complex and heavily loaded Grid systems Solution: –Hide devices behind a proxy and delegate finer control (scheduling, monitoring, recovery etc) to a local community system Resource limitations make contribution of resources difficult and inefficient Solution: –Similar services are aggregated and published through a single interface at the proxy –A single consistent interface to all aggregated resources is presented regardless of the internal state of the cluster –Devices now form a virtual cluster and are presented as a single entity to the Grid.

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 7 Service Aggregation SERVICE A Virtual cluster PROXY The Grid SERVICE A Aggregation CLIENT Service invocation Forward request (single, parallel or mirrored)

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 8 Providing a Virtually Stable and Flexible Environment When aggregating services that provide controlled access to raw resources (like CPU cycles, memory, storage etc.), we dont present the total aggregate but only a fraction This way we can mask internal failures by reallocating resources from within the cluster without notifying (and thus placing extra burden on) higher level Grid components A monitoring and failure recovery framework based on agents, heartbeats and an orchestrating gateway will help predict, detect, diagnose and recover from failures Forecasting components to support the community scheduling system providing recommendations on the best possible resource usage plans

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 9 COMPONENT IMPLEMENTED Platform Architecture VIRTUALIZATION LAYER (AGGREGATOR SERVICE INTERFACES) PLATFORM KERNEL COMPONENT NOT IMPLEMENTED YET MONITORING FAILURE RESILIENCE RESOURCE MANAGEMENT INDEXING REGISTRATION PARALLEL PROGRAMMING MODEL HIGHER LEVEL SERVICES LAYER MIDDLEWARE SERVICES LAYER CORE LAYER

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 10 Virtual Clustering VIRTUALIZATION LAYER (AGGREGATOR SERVICE INTERFACES) PLATFORM KERNEL MONITORING FAILURE RESILIENCE RESOURCE MANAGEMENT INDEXING REGISTRATION PARALLEL PROGRAMMING MODEL Proxy Virtual Cluster The Grid

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 11 Outline Overview & Motivation Platform Architecture Current Implementation Status Future Plans Conclusion & Questions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 12 Implementation Status Pure Java implementation to ensure a high degree of interoperability Currently following a service-based approach –Both Grid and Web Services are supported A CCA compliant version is under way as a more lightweight alternative to the current service-based implementation Currently implemented components: –Registration/aggregation –Indexing –Resource management (partially) Registration and Indexing components are available both as Web Services and as Active RMI Objects registered in the proxy

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 13 HOSTING DEVICE Aggregation Operational Overview Aggregator WSDL Generator WSDL Parser Aggregator Service Generator Deploy Descriptors Generator Service Archive Generator Service Deployer WEB/GRID SERVICE CONTAINER SERVICE AGGREGATION SERVICE SERVICE WSDLMETA- DATA 1.Service provider sends the WSDL description of the service. Static meta data is automatically collected and forwarded. 2.The WSDL Parser extracts all necessary service parameters INFO 3.These are then fed to a WSDL generator that will generate the WSDL description for the aggregator service INFO WSDL 4.From the WSDL we generate the actual Java interface and implementation classes. We also add our own interfaces for mirrored or parallel execution and for administering the service and querying for meta-data INTF WSDD IMPL 5.All the resulting classes along with the deployment descriptors are used in order to create the service archive JAR/ GAR Deploy 6.The service archive is then deployed to the Web/Grid service container of choice META- DATA MAP Update 7.Finally, the indexing components are updated to include the new hosting device meta-data and the new aggregator-to-original service mappings INDEXING SERVICE Resource Meta-data Repository Aggregation Map Dynamic Index

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 14 Invocation Operational Overview SERVICE BSERVICE A SERVICE DSERVICE C WEB/GRID SERVICE CONTAINER SERVICE CLIENT SERVICE INDEXING SERVICE Resource Meta-data Repository Aggregation Map Dynamic Index MONITORING COMPONENTS Availability Forecasting Job Meta- Data Repository Monitoring Gateway AGGREGATOR SERVICE IMPLEMENTATION 1. A 2. C 3. … Virtual Cluster Proxy The Grid Service request 1.A client forwards a request to the aggregator service. Get available services 2.The aggregator service will query the index service and get back a prioritized list of services that match the requirements Execute 3.The aggregator will forward the request to the highest prioritized service )or services in the case of mirrored or parallel execution) Updates The index is updated in a push fashion from the monitoring framework components

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 15 Outline Overview & Motivation Platform Architecture Current Implementation Status Future Plans Conclusion & Questions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 16 Future Plans Design and implement a lightweight monitoring framework –Small monitoring agents in the cluster devices –Monitoring gateway to collect information and orchestrate actions –Forecasting facilities to provide recommendations on the best resource usage plan, based on monitoring information statistics like usage and failure history Support for roaming between Virtual Clusters Design and implement a failure recovery framework Adopt a suitable parallel/distributed programming model –Provide suitable interfaces for parallelization parameters, selection requirements and querying executing jobs

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 17 Outline Overview & Motivation Platform Architecture Current Implementation Status Future Plans Conclusion & Questions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 18 Conclusion The Virtual Cluster architecture will allow the efficient integration of mobile and limited devices into the Grid The aggregation technique coupled with a suitable parallel programming model can provide the foundation for enhanced performance The monitoring and failure recovery framework can provide a virtually stable and reliable environment, along with relatively high service availability

Questions? …or comments, suggestions, ideas… Contact: You can find this presentation here: