Objectif
Main Objective
The overall objective of IMPACT is to implement control strategies on an ATM testbed as a society of interacting/co-operating agents. The work will use the EXPERT platform in Basel and will interconnect the switch on which the agents are implemented with the existing testbed network in order that the performance of the agent approach may be tested.
The application will concentrate on Connection Admission Control (CAC) but to demonstrate the attractiveness of agents in controlling co-operating functions, the work will also introduce an accounting/charging agent.
The project will also validate the FIPA model for agent management and communication in the context of a real time distributed telecommunications environment.
Technical Approach
Existing applications will communicate with a signalling entity in a new switch, the FLEXTEL switch, to request a new connection; that entity will have an agent wrapper to allow it to communicate with the CAC agent which then requests resources brokered by other agents. Once a connection end-to-end has been negotiated, the CAC agent informs the signalling (and hence the application) that the connection has been set-up and user-to-user transfer of data can start. The CAC agent will also notify the charging agent of the parameters to be used for charging and, in this simplified model, data from the Usage Parameter Control (UPC) function will be used by the charging agent to calculate the actual cost. It should be noted that here it is assumed that the switch connection is also initiated by the CAC agent through a switch interface function.
Where an agent function is installed in the terminal, control-plane communication is entirely by the Agent Control Language (ACL) (through a user agent); the advantage of this approach is that it allows more flexibility in negotiations between terminal and network. The network interface provides adaptation between the existing network (here the existing testbed) with the agent-based network control architecture.
Summary of Trial
Having implemented a set of co-operating agents that make the CAC decision on entry to the network, it is necessary to validate the way in which this works. In this project two approaches will be used:
-By comparing the behaviour with the conventional CAC on the testbed: This is the core of the validation, as real applications will be used to compare and validate the agent approach. Where possible, as much of this work as possible will be done through trials.
-By network simulation: To check that the decisions being taken by the agents lead to a QoS comparable with that obtained from conventional step-by-step algorithmic CAC, traffic mixes corresponding to those being handled by the agents will be presented to the agents. Those mixes that are admitted will be modelled by simulation to confirm that the required QoS is obtained and that the performance obtained is comparable with that obtained using conventional CAC. Having these two approaches available is made possible through the connection of the FLEXTEL to the existing testbed.
Expected Achievements
IMPACT will be demonstrating the potential of agent technology to control complex telecommunications systems. By opening up the "agent dimension", the project will be providing input into the technological decisions being made on control and management as systems become ever more complex. This work will be input to Standards bodies.
Expected Impact
Current control strategies are generally based on deterministic and algorithmic approaches. Using autonomous intelligent agents is a new dimension offering the possibility of being able to control complex systems in a holistic manner more than is possible at present.
The use of the EXPERT platform, already a showcase for the ACTS programme as a whole, will ensure that the results from IMPACT will have maximum visibility throughout ACTS and beyond.
Main contributions to the programme objectives:
Main deliverables
A connection admission control functionality in an ATM testbed using agent technologies.
Contribution to the programme
Development of agent technology for the intelligent control of telecommunications networks
Key Issues
-Definition of a suitable subset of Agent Communication Language to be used instead of signalling
-Design of an agent architecture and the component agents
-Implementation of the agent architecture onto the EXPERT platform
-Validation of the performance of agent control
Champ scientifique (EuroSciVoc)
CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: Le vocabulaire scientifique européen.
CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: Le vocabulaire scientifique européen.
- sciences naturelles informatique et science de l'information intelligence artificielle
- ingénierie et technologie génie électrique, génie électronique, génie de l’information ingénierie de l’information télécommunication réseau de télécommunications
Vous devez vous identifier ou vous inscrire pour utiliser cette fonction
Programme(s)
Programmes de financement pluriannuels qui définissent les priorités de l’UE en matière de recherche et d’innovation.
Programmes de financement pluriannuels qui définissent les priorités de l’UE en matière de recherche et d’innovation.
Thème(s)
Les appels à propositions sont divisés en thèmes. Un thème définit un sujet ou un domaine spécifique dans le cadre duquel les candidats peuvent soumettre des propositions. La description d’un thème comprend sa portée spécifique et l’impact attendu du projet financé.
Les appels à propositions sont divisés en thèmes. Un thème définit un sujet ou un domaine spécifique dans le cadre duquel les candidats peuvent soumettre des propositions. La description d’un thème comprend sa portée spécifique et l’impact attendu du projet financé.
Appel à propositions
Procédure par laquelle les candidats sont invités à soumettre des propositions de projet en vue de bénéficier d’un financement de l’UE.
Données non disponibles
Procédure par laquelle les candidats sont invités à soumettre des propositions de projet en vue de bénéficier d’un financement de l’UE.
Régime de financement
Régime de financement (ou «type d’action») à l’intérieur d’un programme présentant des caractéristiques communes. Le régime de financement précise le champ d’application de ce qui est financé, le taux de remboursement, les critères d’évaluation spécifiques pour bénéficier du financement et les formes simplifiées de couverture des coûts, telles que les montants forfaitaires.
Régime de financement (ou «type d’action») à l’intérieur d’un programme présentant des caractéristiques communes. Le régime de financement précise le champ d’application de ce qui est financé, le taux de remboursement, les critères d’évaluation spécifiques pour bénéficier du financement et les formes simplifiées de couverture des coûts, telles que les montants forfaitaires.
Coordinateur
3000 Bern
Suisse
Les coûts totaux encourus par l’organisation concernée pour participer au projet, y compris les coûts directs et indirects. Ce montant est un sous-ensemble du budget global du projet.