Investigation and Improvement of Distributed Differential Evolution Algorithm Cloudde

As a kind of new emerging optimization technology, distributed evolutionary computation (DEC) algorithms have fast developed in recent years. The DEC algorithms, which make use of multiple computers or resources to enhance the optimization capabilities of algorithms, have received widespread attention. Among the DEC algorithms, a cloud-based distributed differential evolution (Cloudde) algorithm has shown excellent performance. The Cloudde has a double-layered heterogeneous distribution structure, which can run different differential evolution (DE) variants with various parameters and/or operators in different populations. Moreover, the Cloudde can adaptively migrate individuals among the populations to make best use of the computational resources among multiple populations. However, since the proposal of the Cloudde, there are still some questions remained to be discussed. The first is how to choose the basic DE algorithms to form various DE variants (i.e., the various populations). The second is how to evaluate the performance of different populations of individuals hence we can rank the populations. The third is how to design an efficient migration strategy to make full use of computing resources among multiple populations. This paper makes investigation on these issues and studies the performance of Cloudde variants with various configurations for these three aspects. The experimental results in this paper are useful for researchers who want to conduct further research on Cloulde and other related DEC algorithms. Moreover, based on the investigation results, an improved Cloudde (I-Cloudde) is proposed and the experimental results show the superiority of I-Cloudde when compared with Cloudde.