Data Science and Pattern Recognition ©2020 ISSN 2520-4165 Ubiquitous International Volume 4, Number 1, July 2020 A Multi-group Grasshopper Optimisation Algorithm for Application in Capacitated Vehicle Routing Problem Jeng-Shyang Pan College of Computer Science and Engineering Shandong University of Science and Technology, Qingdao, China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology, Fuzhou, China jspan@cc.kuas.edu.tw Xiaopeng Wang Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology, Fuzhou, China wangxp1993@163.com Shu-Chuan Chu College of Computer Science and Engineering Shandong University of Science and Technology, Qingdao, China scchu0803@gmail.com Trong-The Nguyen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology, Fuzhou, China vnthe@hpu.edu.vn Abstract. Grasshopper Optimisation Algorithm (GOA) is a new algorithm mimicking the behavior of grasshoppers in nature. It can effectively solve some optimization prob- lems in the real world. A novel algorithm named Multi-group Grasshopper Optimisation Algorithm (MGOA) is presented in this paper. MGOA adopts a multi-group strategy to randomly divide the initial solutions into several subgroups, and exchanges information through intergroup communication after a preset iteration value. Compared with the orig- inal GOA, MGOA can reduce both the premature convergence and easily trap into local optimal search space. CEC2013 is used as the benchmark for testing the efficiency and effectiveness for the proposed MGOA. The experimental results verify its performance as being superior to the original GOA algorithm and the other optimization algorithms, including PSO, PPSO and GWO in the literature. In addition, MGOA is also used to solve capacitated vehicle routing problem (CVRP). The tested results appear that MGOA surpasses GA and PSO in performance. Keywords: Meta-heuristic optimization, Global optimization, Particle swarm optimiza- tion, Multi-group grasshopper optimisation algorithm, Capacitated vehicle routing prob- lem 1. Introduction. In recent decades, evolutionary computation has attracted widespread interest from researchers. Due to significant advances in theory and practice, it has successfully solved optimization problems in many engineering fields [1]. The goal of an optimization algorithm is to discover the best value of a parameter, and standard 41