Introduction

The field in Cognitive Radio (CR) and Cognitive Networking (CN) requires ‘cross-layer’ thinking to maximise the utility of the radio spectrum and can be applied to several layers of the protocol stack.

The big driver for CR has been the obvious success of unlicensed band communications, whose rules enable efficient ‘semi-intelligent’ assignment of spectral resources and control of interference.

CR came to prominence with the publication of the doctoral thesis by Joseph Mitola III in 2000. He used CR as a way of incorporating machine-based learning into software-defined radio. Since then, the definition has been broadened to address the general concept of intelligent assignment of available radio spectrum [4].

Emerging Fields

Two fields are already emerging: cognitive radio, which deals with the intelligent assignment and use of the radio spectrum; and cognitive networking, which deals with the intelligent routing of information through a network, taking into account local constraints. But this application of distributed artificial intelligence can be extended to other areas in communications that today rely on fixed-rule adaptivity, allowing for the first time, flexible changes to complex varying local circumstances [1].

To help realise the revolutionary change required by this global challenge, the WUN Cognitive Communications Consortium [1] aims to bring together the important disciplines of wireless communications, distributed artificial intelligence, electromagnetics, regulatory policy and economics, and implementation .

Glossary:

Opportunistic spectrum access (OSA) :

The concept of OSA whereby radios identify unused portions of licensed spectrum, and utilize that spectrum without adverse impact on the primary licensees. OSA allows both dramatically higher spectrum utilization and near-zero deployment time, with an obvious and significant impact on both civilian and military communications[2].

Spectrum agility:
Involves wideband sensing, opportunity identification, coordination and use.

Policy agility:
Enables regulatory policies to be applied dynamically using machine understandable policies.

Distributed artificial intelligence (DAI):
Was a subfield of Artificial intelligence research dedicated to the development of distributed solutions for complex problems regarded as requiring intelligence. These days DAI has been largely supplanted by the field of Multi-Agent Systems [3].

Sources:

[1]: http://www.wun-cogcom.org/background.html
[2]: Santivanez, C., Ramanathan, R., Partridge, C., Krishnan, R., Condell, M., and Polit, S. 2006. Opportunistic spectrum access: challenges, architecture, protocols. In Proceedings of the 2nd Annual international Workshop on Wireless internet (Boston, Massachusetts, August 02 – 05, 2006). WICON ’06, vol. 220. ACM, New York, NY, 13.
[3]: Carl Hewitt and Jeff Inman. DAI Betwixt and Between: From “Intelligent Agents” to Open Systems Science IEEE Transactions on Systems, Man, and Cybernetics. Nov./Dec. 1991.
[4]: The Communications Research Group, University of York, York, UK