A novel multi-scale cooperative mutation Fruit Fly Optimization Algorithm

作者:

Highlights:

摘要

The Fruit Fly Optimization Algorithm (FOA) is a widely used intelligent evolutionary algorithm with a simple structure that requires only simple parameters. However, its limited search space and the swarm diversity weaken its global search ability. To tackle this limitation, this paper proposes a novel Multi-Scale cooperative mutation Fruit Fly Optimization Algorithm (MSFOA). First, we analyze the convergence of FOA theoretically and demonstrate that its convergence depends on the initial location of the swarm. Second, a Multi-Scale Cooperative Mutation (MSCM) mechanism is introduced that tackles the limitation of local optimum. Finally, the effectiveness of MSFOA is evaluated based on 29 benchmark functions. The experimental results show that MSFOA significantly outperforms the improved versions of FOA presented in recent literature, including IFFO, CFOA, and CMFOA, on most benchmark functions.

论文关键词:Fruit fly optimization algorithm,Multi-scale cooperative mutation,Global optimization,Convergence

论文评审过程:Received 10 June 2016, Revised 26 September 2016, Accepted 27 September 2016, Available online 21 October 2016, Version of Record 9 November 2016.

论文官网地址:https://doi.org/10.1016/j.knosys.2016.09.027