Modeling and estimation of networked control systems with packet losses

Abstract

Packet loss in a networked control system (NCS) is a stochastic event that depends on the current network state, which, as an abstract and hidden variable, can not be well defined but can be perceived by the observation of the packet-loss process. We model the network in an NCS as a Markov chain and the packet losses as stochastic events whose probability depends on the Markov chain state (i.e. network state). Thus, the network state estimation is a hidden Markov model (HMM) estimation problem. To derive the HMM of the NCS under study, we propose the expectation maximization (EM) algorithm to estimate the parameters of the HMM based on the packet dropping sequence. Finally, a simulation example illustrates the effectiveness of the proposed approach.