Cloud Computing Resource Planning Based on Imperialist Competitive Algorithm

Abstract. Resource allocation in cloud computing and the scheduling of each user works on existing virtual machines is an NP-Complete problem, in which many algorithms are provided for solving the problem so far. But none of these algorithms are able to meet the requirements related to speed and accuracy in cloud computing environments. In this paper, a combination of imperialist competitive and local search optimization algorithms is proposed to solve this problem. The algorithm attempts to improve the possible responses by creating an initial empire, through applying imperialist competitive algorithm. To avoid premature convergence, imperialist competitive algorithm is combined with a local search algorithm. The hybrid proposed algorithm used a convergence diagnosis mechanism based on semblance coefficient, and in times of premature convergence in imperialist competitive algorithm, local search algorithm runs. Quality and efficiency of the proposed algorithm are compared with round-robin, ant colony and genetic algorithms. The results show that the proposed algorithm in terms of time and the responses ' quality is faster than the ant colony optimization and genetic algorithms