Optimized Sensor Collaboration for Estimation of Temporally Correlated Parameters

Abstract

Abstract-In this paper, we aim to design the optimal sensor collaboration strategy for the estimation of time-varying parameters, where collaboration refers to the act of sharing measurements with neighboring sensors prior to transmission to a fusion center. We begin by addressing the sensor collaboration problem for the estimation of uncorrelated parameters. We show that the resulting collaboration problem can be transformed into a special nonconvex optimization problem, where a difference of convex functions carries all the nonconvexity. This specific problem structure enables the use of a convexconcave procedure to obtain a near-optimal solution. When the parameters of interest are temporally correlated, a penalized version of the convex-concave procedure becomes well suited for designing the optimal collaboration scheme. In order to improve computational efficiency, we further propose a fast algorithm that scales gracefully with problem size via the alternating direction method of multipliers. Numerical results are provided to demonstrate the effectiveness of our approach and the impact of parameter correlation and temporal dynamics of sensor networks on estimation performance.

Optimization of distributed detection in energy harvesting wireless sensor networks with multiple antenna fusion center

“…For purpose of comparison, the work performed by adopting similar conditions (ie, collaboration among the sensors and without EH via WET) for the FC single antenna in the work of Liu et al and the work performed by adopting similar conditions (ie, without collaboration among the sensors and without EH via WET) for FC multiple‐antenna in the work of Nevat et al have been investigated. In those studies, unlike the proposed model, the effects of EH via WET is not considered as the target in WSN.…”

“…Figure depicts the detection and error probability versus k for the collaboration coefficients (1,10,31, and 100) and adopting similar conditional, with α =10. Further, there are increases in the collaboration coefficients as shown in Figure .…”

“…Since the data collected from IoT of sensors with additive white Gaussian noise (AWGN), the measurement vector for the n th sensor at time t is as follows: where is measurements vector, is the vector coefficients between IoT and sensors, θ t is the interest parameter with the distribution , is the noise vector with independent and identically distributed (iid) Gaussian random variables with the element of noise vector for 1 ≤ t ≤ T and 1 ≤ i ≤ N .…”

“…In topology matrix A , A mn =1 means that the n th sensor shares its data and energy sharing with the m th sensor, and A mn =0 shows the lack of a collaboration link from the n th sensor to the m th sensor …”

“…The transmission cost of the n th sensor at t th time refers to the energy consumption of transmitting the collaborative message z t , m as shown in Liu et al: where is a basis vector with a 1 at the m th coordinate and 0, elsewhere. It was noted that the M sensors are links with the FC, then automatically T m ( W t )=0 for n > M ).…”