Time optimization in spectrum sensing: Interesting cases

Abstract

Traditionally spectrum sensing approaches do not take the historical traffic data into account. In such approaches, equal amount of time is allocated for spectrum sensing of the sub-bands in the band of interest. In this research paper, we formulate the problem of time optimal spectrum sensing taking the historical data into account. We solve the problem in practically interesting special cases. Effectively interesting integer programming problems are solved. In that effort it is shown that the variance of discrete random variable constitutes a quadratic form associated with a laplacian like matrix. Using this result, time optimal spectrum sensing is formulated as a multi-linear objective function optimization problem.