A nonparametric distributed sequential algorithm for quick detection ofspectral holes in a Cognitive Radio set up is proposed. Two or more local nodesmake decisions and inform the fusion centre (FC) over a reporting MultipleAccess Channel (MAC), which then makes the final decision. The local nodes useenergy detection and the FC uses mean detection in the presence of fading,heavy-tailed electromagnetic interference (EMI) and outliers. The statistics ofthe primary signal, channel gain or the EMI is not known. Differentnonparametric sequential algorithms are compared to choose appropriatealgorithms to be used at the local nodes and the FC. Modification of a recentlydeveloped random walk test is selected for the local nodes for energy detectionas well as at the fusion centre for mean detection. It is shown via simulationsand analysis that the nonparametric distributed algorithm developed performswell in the presence of fading, EMI and is robust to outliers. The algorithm isiterative in nature making the computation and storage requirements minimal.
展开▼