RLS算法的改进性能分析

This paper discussed the performance analysis of the recursive least squares (RLS) algo- rithm. Both mean and mean square behavior are studied. By using a novel and more accurate ap- proaching method, accompany with averaging principle, an improved performance analysis of mean square behavior is carried out. It is shown that the theoretical analysis and the simulation result are close to each other, outperforming of the conventional analysis of RLS algorithm. The stability of the basic RLS algorithm is discussed under the new analysis result