Research on prediction of network utilization for NCS based on ARMA model and RELS

Abstract

This paper focuses research on prediction of network utilization for NCS (networked control system). The Two kind models of the network utilization are set up and discussed, which are AR (Auto-Regressive) model and ARMA (Auto-Regressive and Moving Average) model. The ARMA model of network utilization is proposed, which considers not only historical data of network utilization but also historical data of error. The parameter estimation algorithm method of RELS (Recursive Extended Least Square) is used to estimate parameters of proposed ARMA model of network utilization. The RELS to the ARMA model of network utilization is discussed in detail. A simulation example of prediction of network utilization is given and simulation results are analyzed.