|The Model Order Reduction using LS, RLS and MV Estimation Methods
Ehsan Malekshahi and Seyed-Mohammad-Ali Mohammadi
International Journal of Control, Automation, and Systems, vol. 12, no. 3, pp.572-581, 2014
Abstract : Reducing the order of high-order systems eliminates the complexity of them. So, the system analysis and the controller design are done easily. Many model reduction methods have been presented up to now. In this paper, LS (Least squares), RLS (Recursive Least Squares) and MV (Minimum Variance) will be presented as model reduction methods. MV is an adaptive theory that we will use the concept of it to reduce the order of systems. This idea has not been presented so far. One advantage of this method over the other methods, is that it has several parameters to achieve the desired reduced system. The other advantages of this method are that the speed is more and the computations are less compared to the other methods. In this paper, after explaining the three methods, two illustrative ex-amples are provided to demonstrate the applicability of them.
Keyword : High order, least squares, LS, minimum variance, model reduction, MV, order reduction, RLS, system identification.