Direct least squares estimation for linear time varying systems

In this paper we propose a Least Squares based non-recursive identification algorithm capable of dealing with TV parameters. The minimized criterion is an L₂ norm of the identification error with forgetting factor. The estimates and their change ratio are shown to be bounded. We study the case when there is no persistent excitation and show how the estimates can be modified without losing their properties. The proposed estimation algorithm does not require explicit knowledge on the noise bound or the region where the true parameters lie.