Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS

Event category

Content archived on 2022-07-06

Article available in the following languages:

EN

IST-FET launches a new project on 'Dynamically Evolving, Large Scale Information Systems'

FET, the Unit dealing with Future and Emerging Technologies and acting as the pathfinder of IST by exploring new science and technology frontiers, has launched a new project in the area of Information Systems.

5 December 2004 - 6 December 2004
Cyprus
Networks are the unifying feature of a large variety of Information Systems whose interacting components establish relationships in a decentralized and autonomous way. Examples of such systems include peer-to-peer networks, mobile ad-hoc networks, the hyperlinked structure of the World Wide Web, the physical Internet, and telephone networks. Such information systems tend to evolve dynamically over time, i.e. components change or are removed or inserted permanently. For instance, in the Internet setting, servers, routers, communication links etc. are continuously added and removed. In the WWW as in peer-to-peer systems and grid networks, sites and resources of different types appear and disappear with relatively high frequency. The complexity of these systems has reached a level that puts them beyond our ability to deploy them, manage them, and keep them functioning correctly through traditional techniques. Reasons for this are: 1) their sheer size with millions of users and interconnected devices and their dynamics; 2) their extremely complex interactions that may result among components even when their numbers are modest and 3) their highly dynamic, unpredictable changes of the systems. Our current understanding of these systems is such that minor perturbations in some remote corner of the system often not only lead to local modifications, but have unforeseen, and at times catastrophic, global repercussions. In addition to being fragile, many situations (e.g. adding/removing components, topology changes) arising from the highly dynamic environment in which they are deployed require manual intervention to keep them functioning. The situation is further aggravated by their size and extreme dynamics.
For these systems, we have to abandon the goal of global optimality and concentrate our efforts in seeking self-regulating and self-repairing mechanisms that are decentralized, scalable and that are able to adapt to changes in their environments and maintain the system in states corresponding to acceptable behavior, avoiding those that are undesirable or unstable. Components of such systems need to find their equilibrium by collaboration just as well as by competition as in real market systems or in a biological evolution context.
The objectives of the project are:,1. To understand the structure, self organization and dynamics of large scale information systems.
2. To provide methods, techniques and tools for controlling and optimizing such systems.
3. To apply methods from market mechanism and game theory.
4. To provide platforms for experiments and prototypical implementations of projects ,findings, in order to test and compare them, and to make them accessible.
5. To demonstrate the capabilities of our methods, techniques and tools in two application areas of high scientific and economic impact:,- a management platform for telecommunication transport networks that integrates the wide range of current and future data formats and services, and,- a decentralized, self-organizing Web search engine based on a peer-to-peer architecture, where peers collaborate in order to answer search request with higher result quality than current centralized search engines.
DELIS is structured into six subprojects. Each of them covers a topic that needs specific areas of expertise from different disciplines. More particularly subprojects 1, 2 and 3 deal with all aspects concerning the understanding of the topology, the dynamics, and the evolution of large scale information systems, in cooperation between Computer Scientists and Physicists. Subprojects 4 and 5 are devoted to the aspects of adaptation, self-regulation, and self organization, in cooperation between Computer Scientists, Economists, and Biologists. Finally, Subproject 6 addresses the development of methods and techniques for designing peer-to-peer systems and Web information search systems.
A specific characteristic of our approach becomes visible in the composition of the consortium. Besides computer scientists, several colleagues from disciplines like Physics, Bio-Computing and Economics with expertise in actively carrying on multi-disciplinary research are included. In particular the 18 participants are: Universität Paderborn that is also the co-coordinating site; Universita degli Studi di Roma La Sapienza; Research Academic Computer Technology Institute, Patras; Telecom Italia; Telenor; Universita di Bologna; Max-Planck-Institut für Informatik, Saarbrücken; Universität Karlsruhe; Universitat Politecnica de Catalunya, Barcelona; Universitat Pompeu Fabra, Barcelona; University of Cyprus; TU München; Universita Karlova, Prague; Polytechnika Wroclawska; University of Cambridge; Universite Paris-Sud; ETH Zürich; Ecole Polytechnique Federale de Lausanne.
Together with four other EU projects, DELIS organizes a high level conference on Complex Systems in Information Science and Technology that will take place in Torino, Italy, on December 5-6, 2004.Project Information in brief:,Project Type: Integrated Project,Start Date: 2004-01-01,Duration: 48 months,Project Cost: 6.93 million euro,End Date: 2007-12-31,Project Funding: 4.50 million euro,Contact Person: Friedhelm Meyer auf der Heide, fmadh@upb.be,For more Info: http://delis.upb.de(opens in new window)
My booklet 0 0