Abstract
Parametric estimation is a canonical problem in sensor networks. The intrinsic nature of sensor networks requires regression algorithms based on sensor data to be distributed and recursive. Such algorithms are studied in this chapter for the problem of (conditional) least squares regression when the data collected across sensors is homogeneous, i.e., each sensor observes samples of the dependent and independent variable in the regression problem. The chapter is divided into three parts. In the first part, distributed and recursive estimation algorithms are developed for the nonlinear regression problem. In the second part, a distributed and recursive algorithm is designed to estimate the unknown parameter in a parametrized state-space random process. In the third part, the problem of identifying the source of a diffusion field is discussed as a representative application for the algorithms developed in the first two parts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
When Z k = R k–1 , the model set is auto-regressive.
- 2.
Not knowing anything about the joint statistics of the sensor measurements, should not be confused with knowing that they are independent.
- 3.
When the function in (1) has multiple minima, then each minimum is a CLSE estimate. For example, this would be the case if less than three sensors were used in the acoustic source localization. In most cases, by increasing the number of sensors, and thus the spatial diversity of the measurements, it is possible to ensure that the estimation problem is well defined and there is a unique least squares estimate. Such an assumption would be analogous the observability condition of [10].
- 4.
We make the zero mean assumption to keep the presentation simple. The algorithm can be extended to the case when they are not zero mean.
References
Alpay, M.E., Shor, M.H.: Model-based solution techniques for the source localization problem. IEEE Transactions on Control Systems Technology 8(6), (2000)
Aysal, T., Coates, M., Rabbat, M.: Distributed average consensus with dithered quantization. IEEE Transactions on Signal Processing 56(10), 4905–4918 (2008)
Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation: Numerical Methods. Athena Scientific, Belmont, MA (1997)
Borkar, V., Varaiya, P.P.: Asymptotic agreement in distributed estimation. IEEE Transactions on Automatic Control 27, 650–655 (1982)
Calafiore, G., Abrate, F.: Distributed linear estimation over sensor networks. International Journal of Control 82(5), 868–882 (2009)
Cannon, J.R., DuChateau, P.: Structural identification of an unknown source term in a heat equation. Inverse Problems 14, 535–551 (1998)
Cattivelli, F.: Diffusion recursive least-squares for distributed estimation over adaptive networks. IEEE Transactions on Signal Processing 56(5), 1865–1877 (2008)
Ermoliev, Y.: Stochastic quasi-gradient methods and their application to system optimization. Stochastics 9(1), 1–36 (1983)
Jadbabaie, A., Lin, J., Morse, S.: Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Transactions on Automatic Control 48(6), 998–1001 (2003)
Kar, S., Moura, J., Ramanan, K.: Distributed parameter estimation in sensor networks: nonlinear observation models and imperfect communication. Submitted, available at http://arxiv.org/abs/0809.0009 (2008)
Khachfe, A.R., Jarny, Y.: Estimation of heat sources within two dimensional shaped bodies. In: Proceedings of 3rd International Conference on Inverse Problems in Engineering (1999)
Klimko, L., Nelson, P.: On conditional least squares estimation for stochastic processes. The Annals of Statistics 6(3), 629–642 (1978)
Levinbook, Y., Wong, T.F.: Maximum likelihood diffusive source localization based on binary observations. In: Conference Record of the Thirty-Eighth Asilomar Conference on Signal, Systems and Computers (2004)
Levy, E., Louchard, G., Petit, J.: A distributed algorithm to find Hamiltonian cycles in G(n,p) random graphs. Lecture Notes in Computer Science 3405, 63–74 (2005)
Ljung, L., Söderström, T.: Theory and Practice of Recursive Identification. The MIT Press, Cambridge, MA (1983)
Lopes, C.G., Sayeed, A.H.: Incremental adaptive strategies over distributed networks. IEEE Transactions on Signal Processing 55(8), 4064–4077 (2007)
Matthes, J., Gröll, L., Keller, H.B.: Source localization for spatially distributed electronic noses for advection and diffusion. IEEE Transactions on Signal Processing 53(5), 1711–1719 (2005)
Nedić, A., Bertsekas, D.P.: Incremental subgradient method for nondifferentiable optimization. SIAM Journal of Optimization 12, 109–138 (2001)
Nedić, A., Ozdaglar, A.: Distributed sub-gradient methods for multi-agent optimization. Transactions on Automatic Control 54(1), 48–61 (2009)
Niliot, C.L., Lefévre, F.: Multiple transient point heat sources identification in heat diffusion: application to numerical two- and three-dimensional problems. Numerical Heat Transfer 39, 277–301 (2001)
Piterbarg, L.I., Rozovskii, B.L.: On asymptotic problems of parameter estimation in stochastic PDE’s: the case of discrete time sampling. Mathematical Methods of Statistics 6, 200–223 (1997)
Polyak, B.T.: Introduction to Optimization. Optimization Software Inc., New York (1987)
Rabbat, M.G., Nowak, R.D.: Quantized incremental algorithms for distributed optimization. IEEE Journal on Select Areas in Communications 23(4), 798–808 (2005)
Ram, S.S., Nedić, A., Veeravalli, V.V.: Asynchronous gossip algorithms for stochastic optimization. Submitted to IEEE CDC (2000)
Ram, S.S., Nedić, A., Veeravalli, V.V.: Distributed stochastic subgradient algorithm for convex optimization. Submitted to SIAM Journal on Optimization. Available at http://arxiv.org/abs/0811.2595 (2008)
Ram, S.S., Nedić, A., Veeravalli, V.V.: Incremental stochastic sub-gradient algorithms for convex optimization. SIAM Journal on Optimization 20(2), 691–717 (2009)
Ram, S.S., Veeravalli, V.V., Nedić, A.: Distributed and recursive parameter estimation in parametrized linear state-space models. To appear in IEEE Transactions on Automatic Control
Robbins, H., Monro, S.: A stochastic approximation method. Annals of Mathematical Statistics 22(3), 400–407 (1951)
Rossi, L., Krishnamachari, B., Kuo, C.C.J.: Distributed parameter estimation for monitoring diffusion phenomena using physical models. In: First IEEE International Conference on Sensor and Ad Hoc Communications and Networks (2004)
Sayed, A., Lopes, C.: Distributed recursive least-squares strategies over adaptive networks. In: 40th Asilomar Conference on Signals, Systems and Computers, pp. 233–237 (2006)
Schizas, I., Mateos, G., Giannakis, G.: Stability analysis of the consensus-based distributed LMS algorithm. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3289–3292 (2008)
Tsitsiklis, J.N.: Problems in decentralized decision making and computation. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA (1984)
Xiao, L., Boyd, S., Lall, S.: A space-time diffusion scheme for peer-to-peer least-square estimation. In: Fifth International Conference on Information Processing in Sensor Networks, pp. 168–176 (2006)
Zhao, T., Nehorai, A.: Distributed sequential Bayesian estimation of a diffusive source in wireless sensor networks. IEEE Transactions on Signal Processing 55, 4669–4682 (2007)
This work was supported in part by a Vodafone Fellowship, Motorola, and the National Science Foundation, under CAREER grant CMMI 07-42538.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ram, S.S., Veeravalli, V.V., Nedić, A. (2010). Distributed and Recursive Parameter Estimation. In: Ferrari, G. (eds) Sensor Networks. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01341-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-01341-6_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01340-9
Online ISBN: 978-3-642-01341-6
eBook Packages: EngineeringEngineering (R0)