Cooperative Spectrum Sensing using Extreme Learning Machine for Cognitive Radio Networks with Multiple Primary Users
Xiaolin Ma, Shiwen Ning, Xinhua Liu, Hailan Kuang, Youying Hong · 2018
Cognitive radio networks can improve spectrum efficiency by allowing primary users (i.e., authorized users) to share spectrum with secondary users (i.e., unauthorized users) when the spectrum is sensed in idle state. Spectrum sensing is thus one of the key technologies in cognitive radio networks. Recently, cooperative spectrum sensing strategies using machine learning are found to be an effective way to obtain high sensing performance. In this paper, a cooperative spectrum sensing scheme is proposed for the cognitive radio networks with multiple primary users where channel states are more complex than that with one primary user. Specifically, the proposed scheme uses extreme machine learning to achieve high reliable channel state identification and classification, and then, the secondary users can accurately access to the idle channel and share such channel with primary users temporarily. The sensing performance of the proposed scheme is validated by simulation.