Implementation of Novel Machine Learning Techniques for Efficient Spectrum Management in Cognitive Radio Networks

Abstract

It has become increasingly easy for customers to live their lives to the fullest as a result of technology improvements in the last few years. Customers can choose when and where they want to access high-speed data at their leisure. Radio frequency space is becoming increasingly scarce due to the growing popularity of wireless devices and technologies that rely on well-established and reliable radio frequency spectrum. As the number of wireless devices grows, so does the need for more spectrum, and this has become a hot research area in recent years. In order to maximize the utilization of radio spectrum, cognitive radio is a technique that has been created. Cognitive radio networks function well when they have good spectrum sensing. Various cognitive spectrum sensing methods, classifications, and approaches are discussed in detail in this work. An overview of the major obstacles faced by CRNs is provided, as as some of the ML techniques and structures that can be utilized to address these issues. Existing techniques documented in the literature, along with it’s benefits & drawbacks, provide a wealth of knowledge that can be used to develop and improve existing spectrum sensing methods. Finally, we'll offer a Spectrum Sensing approach based on the most recent advances in machine learning.