A two‐fold optimization framework using hybrid B2 algorithm for resource allocation in long‐term evolution based cognitive radio networks system

Abstract

SummaryCognitive radio networks (CRNs) have allowed efficient spectrum sharing while also presenting new challenges to the conventional problems of resource allocation and wireless network interference management. The aim is to provide wireless connectivity to secondary stations on a best‐effort basis while preserving the primary station's service quality. In order to achieve this objective, we have developed a model using hybrid B2 optimization. This method is used for resource allocation in a CRN based on the long‐term evolution (LTE) standard platform of the Third Generation Partnership Project (3GPP). The hybrid B2 optimization algorithm is formed by integrating the bacterial foraging and black widow optimization algorithm. Initially, to optimize the level of service for primary customers, spectrum resources are allocated to primary stations using our proposed model. Later, the spare capacity of the primary channels is then spread among the secondary stations in order to increase the secondary users' service efficiency. The proposed work is twofold where it handles both the low traffic and high traffic scenarios. To reduce the prediction error in a high traffic and bursty environment, an adaptive weighted least square support vector machine (AWLSSVM) is presented. Furthermore, the proposed model is compared with other existing models to evaluate the system's effectiveness.