Cognitive radio (CR) is a spectrum sharing technology that facilitates a hierarchal coexistence between licensed and license-exempt users over licensed bands. One of the biggest challenges in cognitive radio network (CRN) is efficient spectrum management. Recently, a trend has shifted towards the use of machine learning techniques such as reinforcement learning for learning problem in CRN. This paper provides an insight into the working principles of reinforcement learning based CRN and summarizes the recent survey papers done on the topic of learning based CRN. This paper also presents a 5G technology i.e. network slicing, based intelligent CRN architecture for efficient spectrum management. Some challenges in the existing solutions and future research directions are also introduced.
This research was supported partially by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program (IITP-2019-2018-0-01431) supervised by the IITP(Institute for Information communications Technology Promotion), and also supported partially by the LIG Nex1 Co., Ltd.. \u2021: corresponding author