The Vision of Autonomic Computing
Computer
Cognitive Packet Networks: QoS and Performance
MASCOTS '02 Proceedings of the 10th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems
NeXt generation/dynamic spectrum access/cognitive radio wireless networks: a survey
Computer Networks: The International Journal of Computer and Telecommunications Networking
Learning Bayesian Networks
Policy-Based Network Management: Solutions for the Next Generation (The Morgan Kaufmann Series in Networking)
Service configuration and traffic distribution in composite radio environments
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
IEEE Spectrum
A new concept for wireless reconfigurable receivers
IEEE Communications Magazine
Dynamic spectrum allocation in composite reconfigurable wireless networks
IEEE Communications Magazine
IEEE Communications Magazine
Cognitive networks: adaptation and learning to achieve end-to-end performance objectives
IEEE Communications Magazine
Software radio architecture: a mathematical perspective
IEEE Journal on Selected Areas in Communications
Trends in the development of communication networks: Cognitive networks
Computer Networks: The International Journal of Computer and Telecommunications Networking
Context Matching for Realizing Cognitive Wireless Network Segments
Wireless Personal Communications: An International Journal
Hi-index | 0.24 |
Current research efforts in wireless communications are targeted at the evolution of B3G (Beyond the 3rd Generation) wireless infrastructures. The operation of B3G infrastructures envisions dynamic adaptations to external stimuli, which can be facilitated through the exploitation of cognitive networking potentials. Cognitive networks dispose mechanisms for dynamically selecting their configuration (algorithms and parameter values, at different layers of the protocol stack), through appropriate management functionality that takes into account the context of operation (environment characteristics and requirements), profiles, goals, policies and knowledge that derives from previous experience. This paper focuses on such management functionality and it addresses a problem, dealing with ''Distributed, Cross-Layer Reconfigurations'' (DCLR), which aims at assessing and selecting the most appropriate configuration per network element in a cognitive network. In essence, this work contributes in four main areas. First, a fully distributed formulation and solution to the DCLR problem is provided, which is important for the management of a particular reconfigurable element in a cognitive context. Second, robust learning and adaptation, strategies are proposed, for estimating and gaining knowledge of the performance potentials of alternate reconfigurations. Third, a computationally efficient solution to the problem of exploiting the performance potentials of reconfigurations is provided, in order to rate reconfigurations and finally select the best ones. Finally, results that expose the behaviour and efficiency of the proposed schemes, are presented.