Skip to main content
françaisFR
European Commission logo print header

Distributed Resource Evolutionary Algorithm Machine

Objectif

This project seeks to provide the technology and software infrastructure necessary to support the next generation of evolving infohabitants in a way that makes that infrastructure universal, open and scalable. The Distributed Resource Evolutionary Algorithm Machine (DREAM) will use existing hardware infrastructure in a much more efficient manner, by utilising otherwise unused CPU time. It will allow infohabitants to co-operate, communicate, negotiate and trade; and emergent behaviour is expected to result. It is expected that there will be an emergent economy that results from the provision and use of CPU cycles by infohabitants and their owners. The DREAM infrastructure will be evaluated with new work on distributed data mining, distributed scheduling and the modelling of economic and social behaviour.
This project seeks to provide the technology and software infrastructure necessary to support the next generation of evolving infohabitants in a way that makes that infrastructure universal, open and scalable. The Distributed Resource Evolutionary Algorithm Machine (DREAM) will use existing hardware infrastructure in a much more efficient manner, by utilising otherwise unused CPU time. It will allow infohabitants to co-operate, communicate, negotiate and trade; and emergent behaviour is expected to result. It is expected that there will be an emergent economy that results from the provision and use of CPU cycles by infohabitants and their owners. The DREAM infrastructure will be evaluated with new work on distributed data mining, distributed scheduling and the modelling of economic and social behaviour.

OBJECTIVES
*To create the software infrastructure necessary to support the next generation of evolving infohabitants in an open and scalable fashion, using existing Internet infrastructure and existing hardware resources.
*To unify evolution approaches, so that infohabitants can evolve using a number of complementary mechanisms.
*To allow meta-optimisation procedures, so that the algorithms for evolution themselves can be optimised by co-evolving a virtual world with the infohabitants it contains.
*To create the software infrastructure necessary to support the emergent virtual economy that will result from the implementation of virtual machine onto physical resources.
*To demonstrate the usefulness of the infrastructure by using it to implement three applications which can make full use of it.
*To facilitate an improved understanding of the dynamics underlying real-world economic and social systems by simulating these systems with the DREAM.

DESCRIPTION OF WORK
The project is divided into four distinct phases. In the first phase, which lasts 14 months, the participants will work together to provide a prototype DREAM infrastructure. Phase two lasts 13 months, and is concerned with the use of the prototype DREAM for three purposes. During phase two, three teams will be formed, with each participant joining two of the teams, so maintaining the cohesion of the project.
Application 1 involves the implementation of a new model of economic and social behaviour;
Application 2 concerns distributed data mining with the DREAM;
and Application 3 will look at how the DREAM can contribute to distributed scheduling.
The result of phase two will be an evaluation report on the prototype DREAM. This phase also includes an iterative process of evaluation and redesign. Required changes identified during implementation of the applications will results in changes to the DREAM prototype. The application areas are carefully chosen such that they together span a wide scale. Namely, we cover three types: optimisation (scheduling application), modelling (data mining application), and simulation (economic and social behaviour). The deliberately different focuses are meant to provide feedback on the general underlying paradigm, that is the distributed evolutionary mechanism, from different angles. However, the shared DREAM framework keeps these activities coherent; all findings will be fed back into the general architecture. Therefore, the three applications will illuminate different corners of the DREAM framework, thereby contributing to a widely applicable universal approach. Phase three is concerned with continuing to re-design and re-implement the DREAM based on the final DREAM evaluation report. The final phase brings the project to a close, with the all participants working together on the production of user documentation, and a book of scientific reports. This phase will also include the identification of avenues of exploitation.

Champ scientifique

Programme(s)

Thème(s)

Appel à propositions

Data not available

Régime de financement

CSC - Cost-sharing contracts

Coordinateur

Napier University
Contribution de l’UE
Aucune donnée
Adresse
10 Colinton road
EH10 5DT EDINBURGH
Royaume-Uni

Voir sur la carte
Liens
Coût total
Aucune donnée

Participants (5)

Partager cette page

Télécharger

Dernière mise à jour: 13 Juin 2005

Mon livret

Permalink: https://cordis.europa.eu/project/id/IST-1999-12679/fr

European Union, 2024