Optimal linear estimators for systems with random measurement delays

This paper is concerned with the optimal linear estimation problem for linear discrete-time stochastic systems with random measurement delays. A new model that describes the random delays is constructed where possible the largest delay is bounded. Based on this new model, the optimal linear estimators including filter, predictor and smoother are developed via an innovation analysis approach. The estimators are recursively computed in terms of the solutions of a Riccati difference equation and a Lyapunov difference equation. The steady-state estimators are also investigated. A sufficient condition for the convergence of the optimal linear estimators is given. A simulation example shows the effectiveness of the proposed algorithms.

OPTIMAL DISTRIBUTED FUSION ALGORITHM WITH ONE-STEP OUT-OF-SEQUENCE ESTIMATES

The transmission modes of multi-hop and broadcasting for Wireless Sensor Networks(WSN)often make random and unknown transmission delays appear,so multisensor data fusion based ondelayed systems attracts intense attention from lots of researchers.The existing achievements for thedelayed fusion all focus on Out-Of-Sequence Measurements(OOSM)problem which has many dis-advantages such as high communication cost,low computational efficiency,huge computational com-plexity and storage requirement,bad real-time performance and so on.In order to overcome theseproblems occurred in the OOSM fusion,the Out-Of-Sequence Estimates(OOSE)are considered tosolve the delayed fusion for the first time.Different from OOSM which belongs to the centralized fusion,the OOSE scheme transmits local estimates from local sensors to the central processor and is thus thedistributed fusion;thereby,the OOSE fusion can not only avoid the problems suffered in the OOSMfusion but also make the design of fusion algorithm highly simple and easy.Accordingly,a novel optimallinear recursive prediction weighted fusion method is proposed for one-step OOSE problem in this letter.As a tradeoff,its fusion accuracy is slightly lower than that of the OOSM method because the currentOOSM fusion is a smooth estimate and OOSE gets a prediction estimate.But,the smooth result of theOOSE problem also has good fusion accuracy.Performance analysis and computer simulation show thatthe total performance of the proposed one-step OOSE fusion algorithm is better than the current one-step OOSM fusion in the practical tracking systems.