Contribution to Learning and Decision Making under Uncertainty for Cognitive Radio - Archive ouverte HAL Access content directly
Conference Papers Year :

Contribution to Learning and Decision Making under Uncertainty for Cognitive Radio


During the last century, most of the meaningful frequency bands were licensed to emerging wireless applications. Because of the static model of frequency allocation, the growing number of spectrum demanding services led to a spectrum scarcity. However, recently, series of measurements on the spectrum utilization showed that the different frequency bands were underutilized (sometimes even unoccupied) and thus that the scarcity of the spectrum resource is virtual and only due to the static allocation of the different bands to specific wireless services. Moreover, the underutilization of the spectrum resource varies on different scales in time and space offering many opportunities to an unlicensed user or network to access the spectrum. Cognitive Radio (CR) and Opportunistic Spectrum Access (OSA) were introduced as possible solutions to alleviate the spectrum scarcity issue. In order to provide a viable cognitive network, we analyse the main challenges involved within generic OSA scenarios. Thus, we consider that a set of users aim at exploiting communication opportunities left by incumbent users while having no prior information on their environment. The latter statement implicates that the cognitive network is uncertain about the characteristics of the channels to sense (e.g., noise level) as well as the quality of these channels (e.g., average availability). We suggest, throughout this tutorial, a sensing framework that enables overcoming sensing uncertainty and provide learning mechanisms that enables the cognitive network dealing with long term resource optimization under uncertainty. The considered sensing framework is based on the well-known energy detector, while the learning framework relies on the Multi-Armed Bandit paradigm. We argue that collaboration among the cognitive users is a key element to providing robust and efficient cognitive network in spite of the inherent uncertainties of OSA scenarios. Several simulations illustrate the tackled scenarios.
Not file

Dates and versions

hal-00811740 , version 1 (11-04-2013)


  • HAL Id : hal-00811740 , version 1


Christophe Moy. Contribution to Learning and Decision Making under Uncertainty for Cognitive Radio. "Tutorial Days" event on "Advances on Signal Waveforms, Decision Making and Implementation in CR Radio" supported by COST Action IC0902 "Cognitive Radio and Networking for Cooperative Coexistence of Heterogeneous Wireless Networks", Feb 2013, Barcelona, Spain. ⟨hal-00811740⟩
112 View
0 Download


Gmail Facebook Twitter LinkedIn More