Convergence of forgetting factor least square algorithms

Abstract

Convergence of the forgetting factor least square (FFLS) algorithm is analyzed by using stochastic process theory; and the upper bound of the parameter estimation error is derived. For time-varying stochastic systems, the FFLS algorithm is capable of tracking the time-varying parameters and the parameter estimation error is bounded. The upper bound of the parameter estimation error can be minimized by choosing the forgetting factor properly. Simulated results obtained support the theoretical findings.