A GPU-based implementation of brain storm optimization

Abstract

Brain storm optimization (BSO) is a newly emerging family of swarm intelligence techniques inspired by the human's creative problem-solving process, which has achieved successes in many applications. BSO is characterized by its unique process of grouping a population of ideas and carrying out brainstorming based on the grouped ideas to search for optima generation by generation. Although the original BSO is a sequential algorithm based on the central processing unit (CPU), its major algorithmic modules are highly suitable for parallelization. Nowadays, modern graphic processing units (GPUs) have become widely affordable, which empower personal computers to undertake massively parallel computing tasks. Therefore, this work investigates a GPU-based implementation of BSO using NVIDIA's CUDA technology, aiming to accelerate BSO's computation speed while maintaining its optimization accuracy. Experimental results on 30 CEC2014 single-objective real-parameter optimization benchmark problems demonstrate the remarkable speedups of the proposed GPU-based parallel BSO compared to the original CPU-based sequential BSO across varying problems and population sizes.