Variance-Constrained Recursive State Estimation for Time-Varying Complex Networks With Quantized Measurements and Uncertain Inner Coupling

• Published in: IEEE transaction on neural networks and learning systems Vol. 31; no. 6; pp. 1955 - 1967
• Main Authors: Hu, Jun, Wang, Zidong, Liu, Guo-Ping, Zhang, Hongxu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Boundedness analysis; Complex networks; Computer simulation; Constraints; Coupling; Couplings; Covariance; Error analysis; Estimation error; Measurement; Measurement uncertainty; optimal state estimation; Quantization (signal); signal quantization; State estimation; Stochasticity; time-varying stochastic complex networks; uncertain inner coupling; Upper bounds; Variance; variance-constrained approach
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2019.2927554

In this paper, a new recursive state estimation problem is discussed for a class of discrete time-varying stochastic complex networks with uncertain inner coupling and signal quantization under the error-variance constraints. The coupling strengths are allowed to be varying within certain intervals, and the measurement signals are subject to the quantization effects before being transmitted to the remote estimator. The focus of the conducted topic is on the design of a variance-constrained state estimation algorithm with the aim to ensure a locally minimized upper bound on the estimation error covariance at every sampling instant. Furthermore, the boundedness of the resulting estimation error is analyzed, and a sufficient criterion is established to ensure the desired exponential boundedness of the state estimation error in the mean square sense. Finally, some simulations are proposed with comparisons to illustrate the validity of the newly developed variance-constrained estimation method.