Combining State and Model-based approaches for Mobile Agent Load Balancing Georgousopoulos Christos Omer F. Rana

Slides:



Advertisements
Similar presentations
Mobile Agents Mouse House Creative Technologies Mike OBrien.
Advertisements

Kerberos 1 Public domain image of Heracles and Cerberus. From an Attic bilingual amphora, 530–520 BC. From Italy (?).
Performance-sensitive Service Provision in Active Digital Libraries Georgousopoulos Christos Omer F. Rana
System Area Network Abhiram Shandilya 12/06/01. Overview Introduction to System Area Networks SAN Design and Examples SAN Applications.
Study of Hurricane and Tornado Operating Systems By Shubhanan Bakre.
What’s the Problem Web Server 1 Web Server N Web system played an essential role in Proving and Retrieve information. Cause Overloaded Status and Longer.
Using DSVM to Implement a Distributed File System Ramon Lawrence Dept. of Computer Science
Agent Caching in APHIDS CPSC 527 Computer Communication Protocols Project Presentation Presented By: Jake Wires and Abhishek Gupta.
Context-based Information Sharing and Authorization in Mobile Ad Hoc Networks Incorporating QoS Constraints Sanjay Madria, Missouri University of Science.
Progress Report Wireless Routing By Edward Mulimba.
Web Caching Schemes1 A Survey of Web Caching Schemes for the Internet Jia Wang.
Dept. of Computer Science & Engineering, CUHK1 Trust- and Clustering-Based Authentication Services in Mobile Ad Hoc Networks Edith Ngai and Michael R.
© nCode 2000 Title of Presentation goes here - go to Master Slide to edit - Slide 1 Reliable Communication for Highly Mobile Agents ECE 7995: Term Paper.
Quality of Service in IN-home digital networks Alina Albu 23 October 2003.
Improving Robustness in Distributed Systems Jeremy Russell Software Engineering Honours Project.
An Authentication Service Against Dishonest Users in Mobile Ad Hoc Networks Edith Ngai, Michael R. Lyu, and Roland T. Chin IEEE Aerospace Conference, Big.
EEC-681/781 Distributed Computing Systems Lecture 3 Wenbing Zhao Department of Electrical and Computer Engineering Cleveland State University
Application-Layer Anycasting: A Server Selection Architecture and Use in a Replicated Web Service IEEE/ACM Transactions on Networking Vol.8, No. 4, August.
1 Introduction to Load Balancing: l Definition of Distributed systems. Collection of independent loosely coupled computing resources. l Load Balancing.
RETSINA: A Distributed Multi-Agent Infrastructure for Information Gathering and Decision Support The Robotics Institute Carnegie Mellon University PI:
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,
Wide Web Load Balancing Algorithm Design Yingfang Zhang.
Course Instructor: Aisha Azeem
Client-Server Processing and Distributed Databases
Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung Google∗
COGNITIVE RADIO FOR NEXT-GENERATION WIRELESS NETWORKS: AN APPROACH TO OPPORTUNISTIC CHANNEL SELECTION IN IEEE BASED WIRELESS MESH Dusit Niyato,
1 Choosing a Load Balancing Scheme for Agent-Based Digital Libraries Christos Georgousopoulos and Omer Rana Cardiff University.
SensIT PI Meeting, January 15-17, Self-Organizing Sensor Networks: Efficient Distributed Mechanisms Alvin S. Lim Computer Science and Software Engineering.
1 CMPT 275 High Level Design Phase Architecture. Janice Regan, Objectives of Design  The design phase takes the results of the requirements analysis.
Mobile Agent Technology for the Management of Distributed Systems - a Case Study Claudia Raibulet& Claudio Demartini Politecnico di Torino, Dipartimento.
CH2 System models.
Master Thesis Defense Jan Fiedler 04/17/98
Higashino Lab. Maximizing User Gain in Multi-flow Multicast Streaming on Overlay Networks Y.Nakamura, H.Yamaguchi and T.Higashino Graduate School of Information.
Autonomic SLA-driven Provisioning for Cloud Applications Nicolas Bonvin, Thanasis Papaioannou, Karl Aberer Presented by Ismail Alan.
Unit – I CLIENT / SERVER ARCHITECTURE. Unit Structure  Evolution of Client/Server Architecture  Client/Server Model  Characteristics of Client/Server.
Distributed Session Announcement Agents for Real-time Streaming Applications Keio University, Graduate School of Media and Governance Kazuhiro Mishima.
Trust- and Clustering-Based Authentication Service in Mobile Ad Hoc Networks Presented by Edith Ngai 28 October 2003.
Introduction to the Adapter Server Rob Mace June, 2008.
Locating Mobile Agents in Distributed Computing Environment.
Broadband Access Solutions via Satellite Sergey Eleferov Russian Satellite Communications Company Satellite Communications Centre “DUBNA”
Mobile Agent Migration Problem Yingyue Xu. Energy efficiency requirement of sensor networks Mobile agent computing paradigm Data fusion, distributed processing.
Supporting FIPA Interoperability for Legacy Multi-Agent Systems Christos Georgousopoulos 1 Omer F. Rana 1 ( ) 2.
Experiment Management System CSE 423 Aaron Kloc Jordan Harstad Robert Sorensen Robert Trevino Nicolas Tjioe Status Report Presentation Industry Mentor:
Dr. Sudharman K. Jayaweera and Amila Kariyapperuma ECE Department University of New Mexico Ankur Sharma Department of ECE Indian Institute of Technology,
Multiuser Receiver Aware Multicast in CDMA-based Multihop Wireless Ad-hoc Networks Parmesh Ramanathan Department of ECE University of Wisconsin-Madison.
Multimedia Information System Lab. Network Architecture Res. Group Cooperative Video Streaming Mechanisms with Video Quality Adjustment Naoki Wakamiya.
Algorithmic, Game-theoretic and Logical Foundations
An Efficient Wireless Mesh Network A New Architecture 指導教授:許子衡 教授 學生:王志嘉.
1 Object Oriented Logic Programming as an Agent Building Infrastructure Oct 12, 2002 Copyright © 2002, Paul Tarau Paul Tarau University of North Texas.
University of Pennsylvania 7/15/98 Asymmetric Bandwidth Channel (ABC) Architecture Insup Lee University of Pennsylvania July 25, 1998.
Distributed and hierarchical deadlock detection, deadlock resolution
Distributed Computing Systems CSCI 4780/6780. Scalability ConceptExample Centralized servicesA single server for all users Centralized dataA single on-line.
CS 6401 Overlay Networks Outline Overlay networks overview Routing overlays Resilient Overlay Networks Content Distribution Networks.
1 Reforming Software Delivery Using P2P Technology Purvi Shah Advisor: Jehan-François Pâris Department of Computer Science University of Houston Jeffrey.
1 Καστοριά Μάρτιος 13, 2009 Efficient Service Task Assignment in Grid Computing Environments Dr Angelos Michalas Technological Educational Institute of.
Hierarchical Load Balancing for Large Scale Supercomputers Gengbin Zheng Charm++ Workshop 2010 Parallel Programming Lab, UIUC 1Charm++ Workshop 2010.
Achieving All the Time, Everywhere Access in Next- Generation Mobile Networks by Marcello Cinque, Domenico Cotroneo and Stefano Russo Presented by Ashok.
System Architecture CS 560. Project Design The requirements describe the function of a system as seen by the client. The software team must design a system.
The Concept of Universal Service
Presented by Edith Ngai MPhil Term 3 Presentation
Authors: Jiang Xie, Ian F. Akyildiz
Introduction to Load Balancing:
Network Load Balancing
Switching Techniques In large networks there might be multiple paths linking sender and receiver. Information may be switched as it travels through various.
Mobile Agents.
Switching Techniques.
High Performance Computing
Gengbin Zheng, Esteban Meneses, Abhinav Bhatele and Laxmikant V. Kale
Software Agent.
Presentation transcript:

Combining State and Model-based approaches for Mobile Agent Load Balancing Georgousopoulos Christos Omer F. Rana

Load balancing overview Load balance mobilestatic state model Market mechanism Specialized agents gather System state information Aim: improve the average utilization and performance of tasks on available servers Kinds of Load Balance (LB): Keren & Barak: mobile LB has a 30-40% improvement over the static placement scheme only a price sophistiated auction protocols a pricing mechanism without any negotiation roam through the network bid for resources

Our approach on LB  Provide a LB mechanism to evenly distribute agent tasks among the available servers (i.e. equitably server the agents, there are no priorities between agents based on the time needed for their task to be accomplished)  We propose a LB mechanism based on a combination of the model-based and state-based approaches (i.e. decisions on LB are based upon a model which adapts due to the information gathered from the state-based approach)  We demonstrate this approach for a MAS operating on an active digital library composed of multi-spectral images of the Earth as part of the Synthetic Aperture Radar Atlas (SARA)

The SARA LB mechanism  State-based approach  Model-based approach (4/4) Communication between management agents (1/4) The management agents in the SARA architecture (3/4) Information maintained by management agents (2/4) Distribution of information among the management agents (1/1) LB decision model

The SARA architecture

(1/4) The management agents in the SARA architecture Info. server  LMA (Local Management Agent) web server  UMA (Universal Management Agent) i) optimize mobile agents’ itinerary ii) avoid unnecessary migrations iii) identification & comparison of agent task i) inform mobile agents for updates  A management agent exists for every server  Their common objective: optimize system performance  Why multiple management agents ? i) no central point of failure ii) over a centralized scheme: as the number of agents increase, the network load is increased (state-based approach)  LB decisions are supported through the management agents

 Minimization of information transmitted over the network  Minimization of the mobile agent’s size  System optimization Advantages of having management agents control over LB decisions (i.e. only 2 messages are exchanged between a mobile agent and a management agent: the agent’s requirements & the agent’s itinerary ) (i.e. the decision support algorithm is within the management agents. Alternatively mobile agents would have to carry it during their migration) Information used for LB decisions may also be reused for: i) undertaking similarity analysis between agent requests i.e. tasks ii) cache techniques are possible to be applied iii) lay the foundations for an efficient monitoring system

(2/4) Distribution of information among the management agents  distributed scheme :information is distributed among the servers  centralized scheme :a global database is used to hold all information for each server ii) map of the surrounding area i) global network map iii) neighbor map - agent interactions - information: - in a case of a failure stored in one location network overload increases - impose agents to have a kind of intelligence - each server has all the information: replication (for integrity) no central point of failure network overload decreases (provides all information for each server) (provides information for the local server but information is reduced more and more for servers which are not in the local region) (provides information for the local server and its neighbor servers only) (state-based approach)

(3/4) Information maintained by management agents (state-based approach) LMA’s information acquired by Local: resources: software: status of voyager server, available analysis algorithms hardware: database server: status, processing power compute server: status, processing power, average data filtered per sec., maximum data filtered per sec. local LAA number of agent: active, persistent general (concerning database server): average completion task time, average server’s utilisation LMA itself Remote: servers’ resources:… LMAs servers’ bandwidths: server x with server ysender agent UMA’s information acquired by Local agent’s info: agent id: general: request, time of request local UAA (upon URA’s creation) time of request accomplished, status of the task location of results: server’s IP, physical location path, file-space acquired resources used: software: analysis algorithm (AA) used, size of custom AA hardware: database/file archives used, engagement time (from-to), server’s utilization (before-after), compute server used, engagement time (from-to) local UAA (before URA’s death) Remote agents’ info: server x,y: agent id, request, status of the task UMAs LMAs’ info: server x, y: …LMAs SARA LB uses the global network map for decentralized information distribution with a slight variation …

(4/4) Communication between management agents (state-based approach) Management agents’ interaction EventInteraction (sender – recipient) Information exchangeType of mes. on the initialization of the systemLMA-LMAs/UMAscontents in row 1,2 of table 1multicast upon URA’s creationUAA-local UMAcontents in row 1 of table 2direct UMA-UMAsinformation in bold of table 2multicast before URA’s deathUAA-local UMAcontents in row 2 of table 2direct UMA-UMAsinformation in bold, in row 2 of table 2multicast URA’s migration failureURA-local LMA/UMA Voyager server is down (row 1, table 1)direct LMA/UMA- LMAs/UMAs multicast database connection failureLRA-local LMAdatabase is unavailable (row 1, table 1)direct LMA-LMAs/UMAsmulticast sever will be unavailable until a specified time LMA-LMAs/UMAsthe time the server will become available (row 1, table 1) multicast need for further information about an agent’s task UMA-UMAselected information of row 1,2 of table 2 based on the recipient UMA needs direct change on information-server’s (LMA’s) status/resources LAA-local LMAcontents in row 1 of table 1direct LMA-LMAs/UMAscontents in row 1,2 of table 1multicast change on UMA’s information (concerning URA personal details) UMA-UMAscontents in row 3 of table 2multicast

LB decision model (model-based approach) i) agents’ tasks ii) servers’ utilization (performance load) iii) availability of resources iv) network efficiency  LB decisions are based on a model which accepts as: input: an agent’s requirements & System state information output: the appropriate server where an agent should migrate to  The model is a function of:

LB decision model (model-based approach) The model may be better expressed with reference to the agents’ task…

LB decision model (model-based approach) case 3: Agent’s task  Similar (cashed)  Exactly the same  Need filtering  Custom filter case 5: Agent’s task  Not similar (not chased)  Do not need filtering where: T av = the average time an agent needs to complete a task (regarding all servers) U av = the average utilization of all servers U s = the utilization of a server S a.code = the file-size of an agent’s code. B 2 = the bandwidth between 2 information servers Τ s = time needed for a server to became available utilization of a server where: a = the number of agents on that server μ = the average task time of the agents L = the processing power of the server examples of different agents’ tasks… +Ts+Ts

Parametersserver 1server 2server 3server 4server 5server 6server 7server 8server 9server 10 Agents (α) = Av.Task.T (μ) = Proc.Power (L) = Utiliz.Server (Us) = AgentCode (Sa.code)=7148 Bandwidth Sx-Sy (B2)= Av.Util.allServ (Uav) =19.6 Av.Task (Tav) =20.1 x = LB decision model (model-based approach) Agent’s task  Not similar (not chased)  Do not need filtering Mathematica simulation of Case 5 ( L= x* ops ) ( Sa = Kbytes/sec ) ( B2 = Kbytes/sec )

Advantages of the proposed LB technique  LB decisions are supported by the management agents  Distribution of information between the management agents  More accurate LB decisions (the variation of the global network map decentralized information distribution implies reduction of information replication) (LB model uses the state-based information)

Conclusion – Future work were specialized stationary agents are used to gather system state information and make decisions on the distribution of mobile agents among the servers, based on a model of probabilistic estimations in relation with the information provided by the stationary agents  we demonstrated a combination of the state and model-based approaches for mobile agent load balancing  implement the proposed LB technique…  … to optimize the intelligence of the management agents

The End The End