Exponentially weighted least squares identification of time-varying systems with white disturbances

The paper is devoted to the stochastic analysis of recursive least squares (RLS) identification algorithms with an exponential forgetting factor. A persistent excitation assumption of a conditional type is made that does not prevent the regressors from being a dependent sequence. Moreover, the system parameter is modeled as the output of a random-walk type equation without extra constraints on its variance. It is shown that the estimation error can be split into two terms, depending on the parameter drift and the disturbance noise, respectively. The first term turns out to be proportional to the memory length of the algorithm, whereas the second is proportional to the inverse of the same quantity. Even though these dependence laws are well known in very special mathematical frameworks (deterministic excitation and/or independent observations), this is believed to be the first contribution where they are proven in a general dependent context. Some idealized examples are introduced in the paper to clarify the link between generality of assumptions and applicability of results in the developed analysis. >

[1]  M. Morf,et al.  Recursive least squares ladder estimation algorithms , 1981 .

[2]  B. Widrow,et al.  Stationary and nonstationary learning characteristics of the LMS adaptive filter , 1976, Proceedings of the IEEE.

[3]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[4]  T. R. Fortescue,et al.  Implementation of self-tuning regulators with variable forgetting factors , 1981, Autom..

[5]  S. Bittanti,et al.  Adaptive RLS algorithms under stochastic excitation-L/sup 2/ convergence analysis , 1991 .

[6]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[7]  Rafael M. Canetti,et al.  Convergence analysis of the least-squares identification algorithm with a variable forgetting factor for time-varying linear systems , 1989, Autom..

[8]  Paolo Bolzern,et al.  TRACKING OF NONSTATIONARY SYSTEMS BY MEANS OF DIFFERENT PREDICTION ERROR DIRECTION FORGETTING TECHNIQUES , 1987 .

[9]  David R. Cox,et al.  The Theory of Stochastic Processes , 1967, The Mathematical Gazette.

[10]  Sergio Bittanti,et al.  Technical Notes and Correspondence Adaptive RLS Algorithms Under Stochastic Excitation--L2 Convergence Analysis , 1991 .

[11]  Toshiro Homma.  On an Iterative Method , 1964 .

[12]  David D. Falconer,et al.  Tracking properties and steady-state performance of RLS adaptive filter algorithms , 1986, IEEE Trans. Acoust. Speech Signal Process..

[13]  Maciej Niedzwiecki,et al.  Nonasymptotic results for finite-memory WLS filters , 1991 .

[14]  R. Lozano.  Identification of time-varying linear models , 1983, The 22nd IEEE Conference on Decision and Control.

[15]  S. Bittanti,et al.  Adaptive RLS algorithms under stochastic excitation: strong consistency analysis , 1991 .

[16]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[17]  K. Narendra,et al.  An iterative method for the identification of nonlinear systems using a Hammerstein model , 1966 .

[18]  Tulay Adali,et al.  Fixed-point roundoff error analysis of the RLS algorithm with time-varying channels , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[19]  O. Macchi.  Optimization of adaptive identification for time-varying filters , 1984, The 23rd IEEE Conference on Decision and Control.