Reconfigurable Sensing Time in Cooperative Cognitive Network Using Machine Learning

A cognitive radio network (CRN) intelligently utilizes the available spectral resources by sensing and learning from environment to maximize spectrum utilization. In CRNs, secondary users (SUs) opportunistically access primary (PUs) spectrum. Therefore, unambiguous detection of PU channel occupancy is most critical aspect operations CRNs. Cooperative (CSS) rated as best choice for making reliable decisions. This paper employs machine-learning tools sense channels reliably in CSS. The parameters are reconfigured utilization while reducing error cost with improved throughput. fine-k-nearest neighbor algorithm (FKNN), employed this paper, estimates number samples based on nature under-specific false alarm probability demands. simulation results reveal that suppressed time exploiting traditional fusion rules, validating effectiveness proposed scheme. Furthermore, global decision made at center (FC) modified samples, low energy consumption, higher throughput, probabilities.