Sensor placement for optimal estimation of vector-valued diffusion processes

Abstract Diffusion processes are commonplace in many scientific disciplines, as they describe a broad range of physical phenomenon. Consider a diffusion process observed through linear sensors with additive white noise. We derive the optimal placement of these sensors for estimating this process, where optimality is defined in terms of the mean squared estimation error (MSE) of the state given past observations. We consider two cases. First, we assume the sensors to be orthogonal. We show in this case that the minimum MSE is related to the nuclear norm of the system matrix of the process. Second, we remove the orthogonality constraint and show that the MSE is related to the Schatten p -norm of the system matrix of the process and the optimal sensors are proportional its matrix cube root. We present simulation results illustrating the fact that the gain afforded by optimizing the choice of sensors depends on the ratio p ∕ n , where n is the dimension of the system and p the dimension of the Wiener processes driving it, and this gain is in general large, especially when p ∕ n is small.

[1]  Zhi-Quan Luo,et al.  An ADMM algorithm for optimal sensor and actuator selection , 2014, 53rd IEEE Conference on Decision and Control.

[2]  Sergio Verdu,et al.  Multiuser Detection , 1998 .

[3]  George Michailidis,et al.  Optimal experiment design in a filtering context with application to sampled network data , 2010, 1010.1126.

[4]  M. Manoliu,et al.  Energy futures prices: term structure models with Kalman filter estimation , 2002 .

[5]  Kirsten Morris.  Linear-Quadratic Optimal Actuator Location , 2011, IEEE Transactions on Automatic Control.

[6]  Shreyas Sundaram,et al.  Sensor selection for Kalman filtering of linear dynamical systems: Complexity, limitations and greedy algorithms , 2017, Autom..

[7]  Guillaume Sagnol,et al.  Optimal Designs for Steady-State Kalman Filters , 2015 .

[8]  Michael Athans,et al.  The Importance of Kalman Filtering Methods for Economic Systems , 1974 .

[9]  Susanne Ditlevsen,et al.  Introduction to stochastic models in biology. , 2013 .

[10]  Charles R. Johnson,et al.  Topics in Matrix Analysis , 1991 .

[11]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[12]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[13]  L. Mirsky.  A trace inequality of John von Neumann , 1975 .

[14]  Richard Bellman,et al.  Some inequalities for the square root of a positive definite matrix , 1968 .

[15]  Michael A. Demetriou,et al.  Optimal actuator/sensor location for active noise regulator and tracking control problems , 2000 .

[16]  N. Shephard,et al.  Econometric analysis of realized volatility and its use in estimating stochastic volatility models , 2002 .

[17]  Amir Khajepour,et al.  An algorithm for LQ optimal actuator location , 2013 .

[18]  Mohamed-Ali Belabbas,et al.  Geometric methods for optimal sensor design , 2015, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[19]  G. Picci,et al.  Linear Stochastic Systems: A Geometric Approach to Modeling, Estimation and Identification , 2016 .

[20]  U. Helmke,et al.  Optimization and Dynamical Systems , 1994, Proceedings of the IEEE.

[21]  A. Horn.  Doubly Stochastic Matrices and the Diagonal of a Rotation Matrix , 1954 .

[22]  Don S. Lemons,et al.  An Introduction to Stochastic Processes in Physics , 2002 .

[23]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[24]  B. Øksendal.  Stochastic differential equations : an introduction with applications , 1987 .

[25]  John Crank,et al.  The Mathematics Of Diffusion , 1956 .