Machine learning based energy efficient multichannel resource allocation in cognitive radio networks

The growth of the Internet of Things and mobile devices highly rely on independent and distributed operation in wireless networks. A focus on the allocation of spectrum for effective communication, mitigation of interference and reduction in the energy consumption in the wireless environment is essential. Non-availability of the spectrum in a wireless network can be overcome by spectrum reuse in Cognitive Radio Femtocell networks (CRFN) which improves the indoor communication coverage. is mostly preferred. The spectrum is sensed at regular intervals by the secondary user (SU) to detect the presence of the primary user(PU). Sensing the spectrum reduces the performance and the throughput of the secondary users. To overcome the above in this research, a novel multichannel spectrum allocation (MSA) technique combined with a decode-and-forward (DF) based cooperative spectrum sensing scheme is proposed. The information rate that can be transmitted over a given bandwidth is greatly enhanced in the proposed multichannel resource allocation (MRA) technique It is evident from the simulation results, that the throughput of the SUs is boosted when compared over the established techniques.