TY  - BOOK
AU  - Bouvry,Pascal
TI  - Intelligent Decision Systems in Large-Scale Distributed Environments
SN  - 9783642212710
U1  - 004 
KW  - Engineering
KW  - Artificial Intelligence
KW  - Computational Intelligence
KW  - Artificial Intelligence (incl. Robotics)
N1  - 1 Task Allocation Oriented Users Decisions in Computational Grid
Joanna Kolodziej, Fatos Xhafa
1.1 Introduction
1.2 Users' Layers in the Und Arcnitecture
1.3 Grid Users Relations in Grid Scheduling
1.3.1 Hierarchic Grid Infrastructure
1.3.2 Users' Requirements, Relations and Strategies in Job
Scheduling
1.4 Game-Theoretic Models for Scheduling and Resource
Management
1.5 Solving the Grid Users' Games
1.5.1 GA-Based Hybrid Approach
1.6 A Case Study: Non-cooperative Asymmetric Stackelberg Game
of the Grid Users in Independent Batch Scheduling
1.6.1 Players' Cost Functions .
1.6.2 Experiments Setting
1.6.3 Computational Results
1.7 Other Approaches
1.7.1 Computational Economy
1.7.2 Neural Networks and Markov Decision Processes ,
1.8 Conclusions and Future Work
2 Efficient Hierarchical Task Scheduling on GRIDS Accounting for
Computation and Communications
Johnatan E. Pecero, Frederic Pinel, Bemabe Dorronsoro,
Gr^goire Danoy, Pascal Bouvry, Albert Y. Zomaya
2.1 Introduction
2.2 Models
2.2.1 System Model
2.2.2 Application Model
2.2.3 Scheduling Model
2.3 Resource Management System and Grid Scheduling
2.3.1 Resource Management System
2.3.2 Workflow Scheduling on the Grid: A Brief
Taxonomy
2.4 Proposed Approach: The Hierarchical Scheduler with
Cooperative Local Schedulers
2.4.1 Recursive Convex Clustering Algorithm
2.4.2 DAG Partitioning Problem
2.4.3 Local Scheduler
2.5 Results
2.6 Conclusion
Multi-objective Cooperative Coevolutionary Evolutionary
Algorithms for Continuous and Combinatorial Optimization
Bemabe Dorronsoro, Grdgoire Danoy, Pascal Bouvry,
Antonio J. Nebro
3.1 Introduction
3.2 Related Work
3.3 Base Algorithms
3.4 The Proposed Cooperative Coevolutionary Evolutionary
Algorithms
3.4.1 Cooperative Coevolutionary Evolutionary
Algorithms
3.4.2 Multi-objective Cooperative Coevolutionary
Evolutionary Algorithms
3.4.3 Parallel Multi-objective Cooperative Coevolutionary
Evolutionary Algorithms
3.5 Problems
3.5.1 Continuous Problems
3.5;2 Real-World Combinatorial Problem
3.6 Experiments
3.6.1 Configuration of Algorithms
3.6.2 Methodology for the Comparisons .
3.6.3 Results
3.7 Conclusion and Future Work
Parallel Evolutionary Algorithms for Energy Aware Scheduling
Yacine Kessaci, Mohand Mezmaz, Nouredine Melab,
El-Ghazali Taibi, Daniel Tuyttens
4.1 Introduction
4.2 Energy Aware Approaches
4.3 Optimization Approaches
4.3.1 Aggregation Approach
4.3.2 Lexicographic Approach
4.3.3 Pareto Approach
4.4 System-Level Approaches
4.4.1 Hardware-Level Approaches
4.4.2 Software-Level Approaches
4.5 Approaches According to Targeted Execution System
4.5.1 Embedded Systems
4.5.2 Computing Systems
4.6 Problem Modeling
4.6.1 System Model
4.6.2 Application Model .
4.6.3 Energy Model
4.6.4 Scheduling Model
4.7 A Case Study: A Parallel Evolutionary Algorithm
4.7.1 Hybrid Approach
4.7.2 Insular Approach
4.7.3 Multi-start Approach
4.8 Experiments and Results
4.8.1 Experimental Settings
4.8.2 Hybrid Approach
4.8.3 Insular Approach
4.8.4 Multi-start Approach
4.9 Conclusions
Biologically-Inspired Methods and Game Theory in
Multi-criterion Decision Processes
Pawel Jarosz, Tadeusz Burczynski
5.1 Introduction
5.2 Multi-criteria Decision Making and Multiobjective
Optimization
5.2.1 No-Preference Methods
5.2.2 Posteriori Methods
5.2.3 Priori Methods
5.2.4 Interactive Methods
5.2.5 Multiobjective Optimization
5.3 Methods for Multiobjective Optimization
5.3.1 Evolutionary Algorithms
5.3.2 Artificial Immune Systems
5.3.3 Game Theory
5.3.4 Hybrid Evolutionary-uame Algorithm
5.3.5 Immune Game Theory Multiobjective Algorithm
IMGAMO
5.4 Numerical Tests
5.4.1 The ZDT2 Problem
5.4.2 The ZDT3 Problem
5.4.3 The ZDT6 Problem
5.5 Concluding Remarks
Advanced Planning in Vertically Integrated Supply Chains
Maksud Ibrahimov, Arvind Mohais, Sven Schellenberg,
Zbigniew Michalewicz
6.1 Introduction
6.2 Literature Review
6.2.1 Supply Chain Management
6.2.2 Time-Vaiying Constraints
6.2.3 Computational Intelligence
6.3 Wine Supply Chain
6.3.1 Maturity Models
6.3.2 Vintage Intake Planning
6.3.3 Crushing
6.3.4 Tank Farm
6.3.5 Bottling
6.3.6 Environmental Factors
6.3.7 Summary
6.4 Advanced Planning in Mining
6.4.1 Problem Statement
6.4.2 Constraints and Business Rules
6.4.3 Functionality
6.5 Conclusion and Future Works
7 Efficient Data Sharing over Large-Scale Distributed
Communities
Juan Li, Samee Ullah Khan, Qingrui Li, Nasir Ghani,
Nasro Min-Allah, Pascal Bouvry, Weiyi Zhang
7.1 Introduction
7.2 Related Work
7.3 System Overview
7.3.1 Problem Description
7.3.2 A Multilayered Semantic Sharing Scheme
7.3.3 From Schema to Ontology
7.3.4 Semantic Similarity
7.4 Semantics-Based Self-clustering .
7.4.1 Joining the Right Semantic Cluster
7.4.2 Dynamic Self-adjusting
7.5 Query Evaluation
7.5.1 Problems of Query Evaluation
7.5.2 Semantics-Based Forwarding
7.5.3 Containment-Based Caching.
7.6 Experiment
7.7 Conclusion
Hierarchical Multi-Agent System for Heterogeneous Data
Integration
Aleksander Byrski, Marek Kisiel-Dorohinicki, Jacek Dajda,
Grzegorz Dobrowolski, Edward Nawarecki
8.1 Introduction
8.2 AgE - Agent-Based Computation Framework
8.3 Panorama of Systems for Integration of Heterogeneous
Information
8.4 Basic Model of Data Transformation
8.5 Hierarchical Data Integration and Processing
8.5.1 System Environment and User Interaction
8.5.2 Agent-Based Data Integration Workflow Model
8.5.3 Multi-Agent System Structure
8.5.4 Tasks, Objects and Data Types
8.5.5 Tree of Agents .
8.5.6 Roles of Agents
8.5.7 Actions of Agents
8.5.8 Resources of the System
8.6 Searching for Personal Profile of a Scientist - An Example
8.6.1 Construction of Scientist's Profile
8.6.2 Example Data Flow
8.6.3 Set of Types
8.6.4 System Environment and Structure
8.6.5 Agents, Their Actions and Their Goais
8.6.6 System Resources
8.7 Conclusions
Emerging Cooperation in the Spatial IPD with Reinforcement
Learning and Coalitions
Ana Peleteiro, Juan C. Burguillo, Ana L. Bazzan
9.1 Introduction
9.2 Related Work
9.3 Prisoner's Dilemma
9.4 The Game
9.4.1 Spatial Distribution
9.4.2 Basic Game Rules
9.4.3 Agent Roles
9.4.4 Scenarios and Agent Actions
9.5 Reinforcement Learning Algorithms
9.5.1 Q-Leaming (QL)
9.5.2 Leeiming Automata (LA)
9.5.3 Action Selection and States
9.6 Scenarios
9.7 Results Using the Coordination Game
9.7.1 Scenario without Coalitions
9.7.2 Scenario with Coalitions
9.8 Results Using a Prisoner's Dilemma Approach
9.8.1 Scenario without Coalitions .
9.8.2 Scenario with Coalitions
9.9 Conclusions and Future Work
10 Evolutionary and Economic Agents in Complex Decision
Systems
Stephan Otto, Christoph Niemann
10.1 Introduction
10.2 Environments and Complex Decision Systems
10.2.1 Environments
10.2.2 Decision Systems
10.3 Complex Decision Systems
10.3.1 Software Agents
10.3.2 Economic and Market-Based Models .
10.3.3 Evolutionary Computation and Agents
10.4 Case Studies.
10.4.1 Hybrid Decision Systems
10.4.2 Evolutionary Agents Optimize Supply Chain Structures
10.4.3 Evolutionary Agents Optimize the p-median
Problem
10.5 Conclusion and Future Work
11 On Reconfiguring Embedded Application Placement on Smart
Sensing and Actuating Environments
Nikos Tziritas, Samee Ullah Khan, Thanasis Loukopoulos
11.1 Introduction
11.1.1 Application Model
11.1.2 Motivation
11.1.3 Related Work and Contributions
11.2 Problem Definition
11.2.1 System Model
11.2.2 Problem Formulation
11.3 Algorithms
11.3.1 The APR Problem with 2 Nodes
11.3.2 The Agent Exchange Algorithm
11.3.3 Extending to N Nodes
11.3.4 Greedy Algorithmic Approach .
11.4 Experiments
11.4.1 Experimental Setup
11.4.2 Comparison against the Optimal
11.4.3 Experiments with a Larger Network
11.4.4 Discussion
11.5 Conclusions
12 A Game Theoretic Approach to Dynamic Network Formation in
Market-Oriented Resource Providing Networks
Yutaka Okaie, Tadashi Nakano
12.1 Introduction
12.2 Network Formation Game Example
12.3 The Model
12.3.1 Agents
12.3.2 Platforms
12.4 Simulation Experiments
12.4.1 Simulation Algorithms
12.4.2 Default Simulation Configurations
12.4.3 Simulation Results: Simple Scenario
12.4.4 Simulation Results: Realistic Scenario
12.5 Theoretical Analysis
12.5.1 Edgeless Topologies
12.5.2 Fully Connected Topologies
12.5.3 i/-Regular Topologies
12.5.4 Hub Topologies
12.5.5 Summary of Theoretical Analysis
12.6 Related Work
12.7 Conclusion
I
13 Distributed Evolutionary Algorithm Using the MapReduce
Paradigm - A Case Study for Data Compaction Problem
Doina Logofatu, Manfred Gruber, Dumitru (Dan) Dumitrescu
13.1 Introduction
13.2 Problem Description
13 3 Recent Work
13.4 Parallel Evolutionary Algorithm Using MapReduce
11.3 Algorithms
11.3.1 The APR Problem with 2 Nodes
11.3.2 The Agent Exchange Algorithm
11.3.3 Extending to N Nodes
11.3.4 Greedy Algorithmic Approach
11.4 Experiments
11.4.1 Expenmeniai ociup
11.4.2 Comparison against the Optimal.
11.4.3 Experiments with a Larger Netwoiis..
11.4.4 Discussion
11.5 Conclusions
12 A Game Theoretic Approach to Dynamic Network Formation In
Market-Oriented Resource Providing Networks
Yutaka Okaie, Tadashi Nakano
12.1 Introduction
12.2 Network Formation Game Example
12.3 The Model
12.3.1 Agents
12.3.2 Platforms
12.4 Simulation Experiments
12.4.1 Simulation Algorithms.
12 4.2 Default Simulation Configurations
12A.3 Simulation Results: Simple Scenario
12.4.4 Simulation Results: Realistic Scenario
12.5 Theoretical Analysis.
12.5.1 Edgeless Topologies.
12.5.2 Fully Connected Topologies
12.5.3 rf-Regular Topologies
12.5.4 Hub Topologies.
12.5.5 Summary of Theoretical Analysis
12.6 Related Work
12.7 Conclusion
13 Distributed Evoiutionary Algorithm Using the MapReduee
piradigm - A Case Study for Data CompacUon Problem
Doina Ugoato, Manfred Graber, Dumitn. (Dan) Dumitrescu
13.1 Introduction
13.2 Problem Description
13 3 Recent Work
13:4 Parallel Evolutionary Algonthm Using MapReduee
13.5 Implementation Details
13.6 Experimental Results and Statistical Tests
13.7 Conclusions and Future Work .
14 Virtual Accelerated Life Testing of Complex Systems
Michael T. Todinov
14.1 Introduction
14.1.1 Arrhenius Stress-Life Relationship and Arrhenius-TVpe
Acceleration Life Models
14.1.2 Inverse Power Law Relationship (IPL) and IPL-TVpe
Acceleration Life Models
14.1.3 Eyring Stress-Life Relationship and Eyring-Type
Acceleration Life Models
14.1.4 A Motivation for the Proposed Method
14.2 Limitations of Available Analytical Methods for Determining
the Reliability of Large and Complex Systems
14.3 Efficient Representation of Reliability Networks with Complex
Topology and a Large Number of Components
14.3.1 Representing the Topology of a Complex Reliability
Network by an Array of Pointers to Dynamic Arrays
14.3.2 Updating the Link Arrays after a Component
Failure
14.4 Existence of Paths to Each End Node in a Complex Reliability
Network Represented by Adjacency Arrays and Link Arrays
14.5 Accelerated Time to Failure of a Complex System
14.6 A Software Tool
14.7 A Solved Test Example.
14.8 Conclusions
15 Alvis - Modelling Language for Concurrent Systems
Marcin Szpyrka, Piotr Matyasik, Rafal Mr6wka
15.1 Introduction
15.2 Related Works
15.3 Communication Diagrams
15.4 Language Statements
15.5 System Layers
15.6 Rule-Based Systems
15.7 Alvis Model Example
15.8 Agent and Model State
15.9 Summary
ER  -