Resource Allocation and Optimization in Cognitive Radio using Cascaded Machine Learning Algorithm

Abstract

The scarcity of dynamic spectrum allocation is a major issue in wireless networks. The limitations and bottleneck problems of wireless network addressing with cognitive radio networks,the cognitive radio network-based framework changes the dynamic resource allocation and ensures the ability of resources for primary and secondary users. The process of resource allocation and optimization enhances the performance of the cognitive radio network. The major issues related to cognitive radio networks are power control and spectrum allocation. This paper proposes a cascaded machine learning algorithm for the allocation of resources and the utilisation of power in a cognitive radio network. The proposed cascading algorithm of resource optimization focuses on energy efficiency, fairness, and spectrum utilization. The cascading algorithm trained the factors of energy and spectrum approach for the allocation of secondary users. The proposed algorithm dynamically manages resources and predicts new optimal resources. The proposed algorithm increases the rate of convergence of resource allocation. The proposed algorithm is simulated in MATLAB tools and applies standard parameters for the validation of proposed algorithms. The proposed algorithm results are compared with existing algorithms. The performance of the results suggests that the proposed algorithm is efficient in terms of resource allocation and power control.