Simultaneous Perturbation Particle Swarm Optimization Using FPGA

In this paper, we present an algorithm of the particle swarm optimization and the simultaneous perturbation optimization method. The algorithms utilize local information of an objective function based on the simultaneous perturbation method and global shape of the function based on the usual PSO, at the same time. On the other hand, it is interesting to implement this kind of search scheme as a hardware system. Especially, PSO has property of parallel operations. Operations for particles can be implemented in parallel processing manner. We implemented the SPPSO using FPGA. Details of the FPGA design are described. Moreover, an example for a function optimization is shown.