Spectrum Allocation Algorithm based on Improved Wolf Swarm Algorithm

In the complex and changeable electromagnetic environment, there are many frequency equipments, limited number of spectrum and low spectrum utilization. An improved wolf swarm algorithm is proposed in this paper. Firstly, aiming at the problems that the uncertainty of randomly generated solution set in the initial stage of population may lead to slow convergence speed and easy to fall into local optimization, the algorithm uses mean square deviation and back learning algorithm to improve the diversity of wolves during population initialization; Secondly, the discretization of the traditional wolf swarm is improved to further improve the optimization ability. Finally, when the wolf swarm is updated, the adaptive differential evolution algorithm is introduced to further improve the population diversity and avoid falling into the local optimal solution.