System identification using simultaneous perturbation stochastic approximation

摘要

The simultaneous perturbation stochastic approximation(SPSA) is an extension of Kiefer-Wolfowitz stochastic approximation algorithm In this paper, we propose a parameter identification algorithm using SPSA. The proposed algorithm can modify estimators with two values of an evaluation function. Compared with the usual Kiefer-Wolfowitz stochastic approximation, the algorithm is efficient. Simulation result shows a feasibility of the algorithm proposed here.