A Distributed Particle Swarm Optimization Algorithm for Distributed Clustering

With the rapid development of the Internet of Things, distributed clustering has emerged as an attractive research topic. Although evolutionary computation (EC) has been introduced as an effective approach to solve complex data clustering problems, few studies realize the use of EC for distributed clustering. In this paper, we intend to propose a distributed particle swarm optimization (PSO) for distributed clustering. The main idea of the work is to take advantage of the natural distributed computing feature of EC to solve distributed clustering. Since each site only knows a part of the data, the performance of distributed clustering algorithm usually deteriorates. To address this challenge, the proposed algorithm includes two main steps. Firstly, PSO is introduced in each local site to perform local data clustering. Secondly, to combine the local clustering results together, the K-means algorithm is used in the global site to generate the global clustering result. Experimental results demonstrate the overall performance superiority of the proposed algorithm compared with two other algorithms.