Abstract

International audience; This paper presents our approach integrating a high level of intelligence within telecommunication networks. Artificial intelligence has proved its efficiency in resolving complex issues in different fields like air traffic control, robotics, and medical diagnosis. However its usage in telecommunication networks is still very moderated. The main objectives of our framework is to encourage the deployment of techniques characterized by a high level of intelligence – inspired from the artificial intelligence domain in networking. For this reason, we build an extension, with intelligent capabilities, to the J-Sim simulation environment. This extension proposes an intelligent package having the essential entities required for simulating intelligent features. Using this intelligent package and the abstract node model (INET) proposed by J-Sim for network simulations, it will be possible to test the efficiency of integrating intelligent techniques in networking. Document type: Part of book or chapter of book

Abstract

In order to accommodate fluctuations in network conditions, adaptive applications need to obtain information about resource availability. Using active networks, new models for adaptive applications can be envisaged, which can benefit from the possibility to send mobile code to the network nodes. We describe a model for trading resources inside an active network node, based on the interaction between capsules as reactive user agents, and resource manager agents which reside in the network nodes. We apply the model to the case of a many-to-one audio application with congestion control, which trades off link resources against memory when there is congestion at the outgoing interface towards the destination. Our simulation results indicate that the application makes effective use of the available reources, and it also allows resources to bc shared according to uscr preferences. Document type: Part of book or chapter of book

Abstract

We present how NFC transponders can be used for energy efficient programming of closed-loop sensor networks, to update or augment the existing functionality. Use cases include road tunnel inspection, water pipeline monitoring and maintaining safety information on behalf of mine workers. We utilize opportunistic movement of the human operator, the flow of fluid in a pipeline or material in mines, to move the NFC transponder in the system effortlessly and without external network connectivity. Transponders contain mobile agents in their memory, which are injected into the system when transponder comes to the proximity of a node with NFC reader component. Then mobile agents autonomously operate their tasks, i.e. collect and process sensor data in the devices, detect events from data, control physical components and report their results. Mobile agents can adapt to the operational conditions of the system and physical environment, e.g. to save energy or operate in isolated network segments in fault situations. Real-world evaluation shows that this method is energy efficient in comparison with communications atop similar wireless sensor network.