Parallel Programming of Swarm Intelligence Algorithm Inpired in Fish Schools for Global and Multimodal Optimization

• Grant number: 12/03577-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2012
• End date: April 30, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Adriane Beatriz de Souza Serapião
• Grantee: Guilherme Sanchez Corrêa
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil

Abstract

In recent years, population-based bioinspired algorithms have become quite popular in the field of multiobjective optimization. However, due to the large number of evaluations of the objective function, the runtime of such algorithms can become long for complex problems applications. With the development of graphics processing units (GPU) and CUDA (Compute Unified Device Architecture) of NVIDIA some recent studies of the parallelization of bioinspired evolutionary algorithms for optimization has been carried out by scientific communities worldwide. In this project, we propose the implementation in GPU of the Fish School Search (FSS) Algorithm, which is a metaheuristic based on the behavior of fish schools, for parallelization of general-purpose problems in global and multimodal optimization. Experiments will be conducted for the implementation of FSS algorithm on the GPU and CPU aimed at optimization of classical test functions, in order to evaluate the gain in speed and performance of this algorithm in its parallel version compared to the serial version.