Minimum-Variance Recursive Filtering Over Sensor Networks With Stochastic Sensor Gain Degradation: Algorithms and Performance Analysis

Liu, Yang; Wang, Zidong; He, Xiao; Zhou, Donghua

doi:10.1109/tcns.2015.2459351

Cited by 38 publications

(29 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remark Compared with existing results with respect to the KF problem subject to the limited network resource, 9,42 one of the distinct features of the protocol‐based KF scheme proposed in this article lies in the reduction of data collisions during data transmission via a shared communication network. Moreover, a novel technical skill is developed to embed the RR protocol into the filter design.…”

Section: Protocol‐based Filter Designmentioning

confidence: 87%

Protocol‐based extended Kalman filtering with quantization effects: The Round‐Robin case

Liu

Wang

et al. 2020

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This article investigates the extended Kalman filtering problem for a class of stochastic nonlinear systems with quantization effects and Round-Robin (RR) communication protocols. The uniform quantization is considered and the resulting quantization error is characterized as an additive white noise sequence obeying the uniform distribution over certain intervals. For the sake of reducing communication traffic of the network as well as alleviating data collisions, the RR mechanism is introduced to schedule the data transmission from the sensors to the filter. By combining the periodic property of the RR protocol and the zero-order holder strategy, the input signal of the filter is modeled by a sequence of delayed quantized measurements. The main purpose of this article is to design an extended Kalman filter for the stochastic nonlinear systems, in the simultaneous presence of quantization errors, stochastic nonlinearities, and stochastic noises, such that an optimized upper bound for the filtering error covariance is derived. By solving two coupled Riccati-like difference equations, the filter gain matrix is explicitly formulated. An RR protocol-based recursive filtering algorithm is developed for the online implementation. Furthermore, a sufficient condition is established to ensure the uniform boundedness of the filtering error in the mean-square sense. Finally, a simulation example is given to demonstrate the practical validity of the designed filter algorithm.

show abstract

Section: Protocol‐based Filter Designmentioning

confidence: 87%

Protocol‐based extended Kalman filtering with quantization effects: The Round‐Robin case

Liu

Wang

et al. 2020

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…Consider the following discrete time-varying networked sensor system first introduced by [40]. The target system is described with the parameters below: Consider a network whose communication rate is 50%, T = 50 and n = 25.…”

Section: An Illustrative Examplementioning

confidence: 99%

Distributed filtering for time-varying networked systems with sensor gain degradation and energy constraint: a centralized finite-time communication protocol scheme

Zhao

Zhou

2018

Sci. China Inf. Sci.

Self Cite

View full text Add to dashboard Cite

This paper focuses on the distributed filtering problem for a class of time-varying networked systems with sensor gain degradation and energy constrained communication protocol. To satisfy the requirement of power consumption and reduce the schedule computing complexity, centralized cyclic finite-time communication strategy optimization is taken into account. The networked system considered in this paper consists of spatially distributed sensors linked to their neighbor sensors, where each sensor node suffers from different gain degradation, and the transmission decisions of all the communication channels obey the centralized transmission schedule strategy identically. First, we present scattered communication action based on single-sensor transmission modeling with an energy constraint. Subsequently, an optimal communication protocol considering expected average error covariance is derived between the target system and each sensor node over the distributed sensor systems, based on a centralized finite-time scheme. Finally, by transforming the overall estimation error covariance of the systems at each sampling time into quadratic form, a conditionally unbiased least-square recursive distributed filtering technique over the networked system is designed at each sensor node. The system stability condition under such an optimal schedule is also accomplished with bounded covariance. A numerical example is provided to demonstrate the utility and effectiveness of the distributed filtering technique using the proposed optimized energy constrained communication protocol.

show abstract

“…In recent years, there has been increasing interest in considering the problem of estimation in systems with sensor gain degradation, which has been addressed by various approaches assuming knowledge of the statespace model. For example, He et al (2009) derived a robust H ∞ filtering algorithm for a class of nonlinear time-varying system with parameter uncertainties and probabilistic sensor faults; Liu et al (2014) studied the optimal filtering problem for networked time-varying systems with stochastic gain degradations by a recursive matrix equation approach; and Liu et al (2016) obtained a minimum variance filtering algorithm for a class of time-varying systems.…”

Section: Introductionmentioning

confidence: 99%

Least-squares estimators for systems with stochastic sensor gain degradation, correlated measurement noises and delays in transmission modelled by Markov chains

García-Ligero

Hermoso-Carazo

Linares-Pérez

2020

International Journal of Systems Science

View full text Add to dashboard Cite

This paper addresses the linear least-squares estimation of a signal from measurements subject to stochastic sensor gain degradation and random delays during the transmission. These uncertainty phenomena, common in network systems, have traditionally been described by independent Bernoulli random variables. We propose a model that is more general and therefore has greater applicability to real-life situations. The model has two particular characteristics: firstly, the sensor gain degradation is represented by a white sequence of random variables with values in [0,1]; in addition, the absence or presence of delays in the transmission is described by a homogeneous three-state Markov chain, which reflects a possible correlation of delays at different sampling times. Furthermore, assuming that the measurement noise is one-step correlated, we obtain recursive prediction, filtering and fixed-point smoothing algorithms using the first and second-order moments of the signal and the processes present in the observation model. Simulation results for a scalar signal are provided to illustrate the feasibility of the proposed algorithms, using the estimation error variances as a measure of the quality of the estimators.

show abstract

Minimum-Variance Recursive Filtering Over Sensor Networks With Stochastic Sensor Gain Degradation: Algorithms and Performance Analysis

Cited by 38 publications

References 36 publications

Protocol‐based extended Kalman filtering with quantization effects: The Round‐Robin case

Protocol‐based extended Kalman filtering with quantization effects: The Round‐Robin case

Distributed filtering for time-varying networked systems with sensor gain degradation and energy constraint: a centralized finite-time communication protocol scheme

Least-squares estimators for systems with stochastic sensor gain degradation, correlated measurement noises and delays in transmission modelled by Markov chains

Contact Info

Product

Resources

About