Chaos cloud quantum bat hybrid optimization algorithm

Abstract

The bat algorithm (BA) has fast convergence, a simple structure, and strong search ability. However, the standard BA has poor local search ability in the late evolution stage because it references the historical speed; its population diversity also declines rapidly. Moreover, since it lacks a mutation mechanism, it easily falls into local optima. To improve its performance, this paper develops a hybrid approach to improving its evolution mechanism, local search mechanism, mutation mechanism, and other mechanisms. First, the quantum computing mechanism (QCM) is used to update the searching position in the BA to improve its global convergence. Secondly, the X-condition cloud generator is used to help individuals with better fitness values to increase the rate of convergence, with the sorting of individuals after a particular number of iterations; the individuals with poor fitness values are used to implement a 3D cat mapping chaotic disturbance mechanism to increase population diversity and thereby enable the BA to jump out of a local optimum. Thus, a hybrid optimization algorithm—the chaotic cloud quantum bats algorithm (CCQBA)—is proposed. To test the performance of the proposed CCQBA, it is compared with alternative algorithms. The evaluation functions are nine classical comparative functions. The results of the comparison demonstrate that the convergent accuracy and convergent speed of the proposed CCQBA are significantly better than those of the other algorithms. Thus, the proposed CCQBA represents a better method than others for solving complex problems.