Distributed Fusion Estimation With Missing Measurements, Random Transmission Delays and Packet Dropouts

Estimation, filtering and fusion for networked systems with network-induced phenomena: New progress and prospects

“…It is well recognized that the existence of the randomly occurring incomplete information would highly degrade the system performance if not handled properly. So far, a series of estimation and filtering schemes has been developed for networked systems with randomly occurring incomplete information in the literature, and great efforts have been made to deal with the randomly occurring nonlinearities in [49], [95]- [99], the randomly occurring uncertainties in [94], [97], the randomly occurring sensor saturations in [40], [72], the randomly occurring sensor delays in [31], [32], [38], [100], [101], the randomly occurring signal quantization in [41], [102], and the randomly occurring faults in [103]. Accordingly, several techniques for analysis and synthesis of the networked systems have been given, including innovation analysis approach [31], [32], linear matrix inequality approach [97], Hamilton-Jacobi-Isaacs inequality method [100], difference linear matrix inequality method [41], Riccati difference equation approach [101], [102], and game theory method [54].…”

“…For the case that the state-space model of the signal is unavailable, both distributed and centralized fusion schemes have been developed in [167] to deal with the phenomena of the multi-sensor random measurement delays which are modeled by the homogeneous Markov chains and, subsequently, the extended result has been given in [168] to handle the missing measurements and random measurement delays with individual delay rate in a unified framework. Moreover, the distributed Kalman filtering fusion problems have been studied in [38], [169] for networked systems with missing measurements, random transmission delays and packet dropouts, new distributed fusion Kalman filters have been designed based on the innovation analysis method and matrixweighted fusion mechanism. With respect to the multi-sensor fusion for nonlinear networked systems, a few results can be found in the literature.…”

Distributed dynamic state estimation over a lossy communication network with an application to smart grids

“…This kind of centralized estimation technique is generally not only in need of huge amount of communication and computation resources but also vulnerable to the central point failures which may lead to massive blackouts. To deal with the communication impairments, a distributed fusion based KF algorithm for sensor networks is developed in [18], [19]. The fusion centre linearly combines the local estimators through a set of designed weighting factors.…”

“…In summary, after initialization the system parameters such as P i k|k−1 andx i k|k−1 through KF based prediction step, each estimator computes the optimal local and neighbouring gains by (18) and (19).x i k+1|k and P i k+1|k are given by:…”

Least-Squares Filtering Algorithm in Sensor Networks with Noise Correlation and Multiple Random Failures in Transmission

“…However, usually the network characteristics may not be completely reliable and some anomalies (e.g., uncertain observations or missing measurements, random delays, and/or packet dropouts) may arise when the sensor measurements are transmitted to the fusion center. Ignoring these random phenomena in the derivation of the estimators may deteriorate their accuracy and performance and, for this reason, the design of new fusion estimation algorithms for linear systems featuring one of these uncertainties (see, e.g., [3][4][5] and references therein) or even several of them simultaneously (see, e.g., [6][7][8][9] and references therein) has become an active research topic. Specifically, multisensors subject to random packet dropouts are dealt with in [3], a packet-dropping network is considered in [4], and networked systems in the presence of stochastic sensor gain degradations are object of study in [5].…”