Abstract
A computationally efficient technique for the identification of the parameters of a deterministic linear dynamical model is introduced. The method is based on the state space formulation. The gradiant and Hessian of the objective function are computed recursively. The performance of the method is evaluated by modeling demand for a specific product with price as the input to the system. Other modeling and forecasting applications of the method are discussed. A brief description of the extension of the results to the stochastic system identification is given.
Similar content being viewed by others
References
Box GEP, Jenkins GM (1976) Time series analysis, forecasting and control. Holden-Day, San Francisco
Faurre PL (1976) Stochastic realization algorithms. In: Mehra RK, Lainiotis DG (eds) System identification: advances and case studies. Academic Press, New York
Anderssen RS, Bloomfield DP (1975) Properties of the random search in global optimization. Journal of Optimization Theory and Applications 16/5–6
Levy AV, Gomez S (1980) The tunneling algorithm for the global optimization of constrained functions. Technical Communication 231, Institute de Investigaciones en Matematicos Applicadas y en Sistemas (IIMAS), Universidad Mexico, Mexico City, Mexico
Lee DTL, Morf M, Friedlander B (1981) Recursive squares — root ladder estimation algorithms. IEEE Transactions, Acoustics, Speech, Signals Processing 29:627–741
Tsay RS, Tiao GC (1984) Consistent estimates of autoregressive parameters and extended sample autocorrelation function for stationary and non stationary ARMA models. Journal of American Statistical Association 84–96
Li S, Dickinson BW (1986) An efficient method to compute consistent estimates of the AR parameters of an ARMA model. IEEE Transactions on Automatic Control 31/3:275–278
Baram Y (1981) Realization and reduction of Markovian models from non stationary data. IEEE Transactions on Automatic Control 26/6:1225–1231
Kabaila PV (1983) On output — error methods for system identification. IEEE Transactions on Automatic Control 78/1:12–23
Cazdow JA, Solomon OM (1986) Algebraic approach to system identification. IEEE Transactions on Acoustic, Speech, and Signal Processing 34/3:462–469
Chen CT (1970) Introduction to linear system theory. HRW Inc, New York
Fletcher R, Powell MJD (1963) A rapidly convergent descent method for minimization. Comput J 163–168
Kahl RD, Ledolter J (1983) A recursive Kalman filter forecasting approach. Management Science 29/11:1325–1333
Makridakis S, Wheelwright SC (1977) Adaptive filtering an integrated autoregressive/moving average filter for time series forecasting. Operations Research Quarterly 28:425–437
Author information
Authors and Affiliations
Additional information
This work was done while the author was with Bell Laboratories, Murray Hill, New Jersey, USA.
Rights and permissions
About this article
Cite this article
Aminzadeh, F. Parameter identification of a linear dynamic model A state space approach. Zeitschrift für Operations Research 31, B73–B95 (1987). https://doi.org/10.1007/BF01258138
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01258138