Multi-cognitive network resource allocation based on improved artificial bee colony algorithm

Abstract

This paper introduces a graph theory model for resource allocation in multi-cognitive wireless network scenarios. Aiming at the problems of low search accuracy and slow convergence speed of the basic artificial bee colony algorithm, an improved bee colony algorithm is proposed. The improved algorithm introduces an adaptive t-distribution mutation strategy. Compared with the original algorithm, the performance of the improved algorithm has greatly improved. At the same time, the improved bee colony algorithm is applied to multi-cognitive wireless network scenarios for resource allocation in the model. The experimental results show that the improved artificial bee colony algorithm can obtain greater system throughput and effectively reduce the performance of multi-cognitive wireless network systems, and can allocate resources more reasonably.

Binary Jaya‐based channel allocation in cognitive radio networks

“…More recently, metaheuristics algorithms are recommended to address the CA problem 12‐14 . For instance, GAs are applied in Reference 15, PSO in Reference 16, ant colony system (ACS) in Reference 17, artificial bee colony optimization (ABC) in Reference 18, and differential evolution (DE) in Reference 19. Among all the proposed approaches, bio‐inspired algorithms have drawn the most attention by achieving better allocation efficiency within a reasonable time.…”

Cognitive network spectrum allocation based on multi-agent reinforcement learning

“…The scenario of multiple cognitive networks is based on a single cognitive radio network, and its resource allocation also needs to rely on the basic functions of cognitive radio [2]. Reference [3] applies reinforcement learning to resource allocation in wireless networks, and reference [4] further analyzes energy and bandwidth in the downlink using reinforcement learning.…”