Particle Swarm Optimization with Discrete Recombination: An Online Optimizer for Evolvable Hardware

AbstractSelf-reconfigurable adaptive systems have the possibilityof adapting their own hardware configuration. This featureprovides enhanced performance and flexibility, reflected incomputational cost reductions. Self-reconfigurable adaptationrequires powerful optimization algorithms in order tosearch in a space of possible hardware configurations. Ifsuch algorithms are to be implemented on chip, they mustalso be as simple as possible, so the best performance canbe achieved with the less cost in terms of logic resources,convergence speed, and power consumption. This paperpresents an hybrid bio-inspired optimization technique thatintroduces the concept of discrete recombination in a particleswarm optimizer, obtaining a simple and powerful algorithm,well suited for embedded applications. The proposedalgorithm is validated using standard benchmark functionsand used for training a neural network-based adaptiveequalizer for communications systems.8 Halama