Flower Pollination Algorithm Approach Towards IIR System Identification

This paper proposes a novel evolutionary optimization technique referred to the flower pollination algorithm (FPA) for system identification. The optimal parameters of an unknown infinite impulse response (IIR) system are computed using FPA. This algorithm is inspired by the pollination process of flowers. Proper tuning of control parameter has been performed in order to accomplish a balance between intensification and diversification phases. The proposed FPA based method for system identification is free from the problems of premature convergence and sub-optimal solutions, encountered in conventional methods. To validate the performance of FPA based system identification, simulations has been carried out for two benchmarked IIR systems of same order. Mean square error and convergence profile are the performance parameters used to evaluate the performance of the proposed method. Simulated results demonstrate that, the FPA based system identification gives superior performance over particle swarm optimization.