Implementation of Particle Swarm Optimization in FPSoC devices

Abstract

Particle Swarm Optimization (PSO) is a widely used algorithm to solve complex optimization problems with non-linear objective functions. PSO usually requires powerful and expensive computers to achieve reasonable execution times. Sometimes the price or size of the computing system is unacceptable, forcing designers to simplify the objective function or to discard PSO. To overcome this limitation, this paper proposes the implementation of PSO in Field Programmable Systems-on-Chip (FPSoCs). FPSoC devices combine in the same chip powerful processors and reconfigurable logic (FPGA fabric). Experimental results are presented demonstrating that the proposed system achieves a performance similar to that of a desktop computer for a fraction of cost and size. It can be clearly concluded that the proposed system is a good option for running PSO both at design and final application deployment levels.