Cognitive Networks: Towards Self-Aware Networks

7.1. Introduction

Cognitive radio (CR) today includes a relatively wide range of technologies for making wireless systems computationally intelligent. This has resulted from an interdisciplinary integration of complementary but somewhat isolated technologies: perception, planning and machine learning technologies from artificial intelligence on the one hand, and on the other hand software radio technologies that had come to include self-description in the extensible markup language, XML ^{[] [] []}. The first significant application proposed for such smarter radios was the autonomous sharing of pooled spectrum ^[], which the US Federal Communications Commission (FCC) endorsed relatively soon thereafter to encourage the development of secondary spectrum markets ^[]. The original visionary formulation of the ideal cognitive radio (iCR) remains underdeveloped: an autonomous agent that perceives the user's situation (shopping or in distress) to proactively assist the user (kiosk or ambulance), particularly if the user is too busy or otherwise occupied to go through the tedium of using the cell phone, such as when in distress. At the 2004 Dagstuhl workshop ^[], the notion was extended to cognitive wireless networks (CWN).

This chapter summarizes important aspects of the architecture of the iCR that is more fully developed in the foundation text ^[], particularly with respect to the critical machine learning technologies. The iCR vision includes isolated radio devices and CWNs with machine ...