Deep Reinforcement Learning-Based Automated Network Selection in Heterogenous CRNs

Abstract

The development of technology that enables network convergence and the rising acceptance of heterogeneous network architectures have made it possible for many of the most important cognitive radio networks to communicate with a broad variety of authorized networks. Traditional algorithms for network selection make use of selection approaches that are dependent on prior information about the network under consideration. We use the proposed algorithm to choose different networks and integrate them into computers. This paper offers a network selection technique that is based on deep reinforcement learning. This technique can be applied to cognitive radio networks that encompass a range of networks. We will utilize these findings to provide recommendations on how to remediate existing issues in the delivery of services to cognitive users. This paper aims to improve the service quality for cognitive users and find solutions to the identified problems.