Quis custodiet ipsos custodes?

The design of automated systems for monitoring the performance of large numbers of MPC controllers is presented. The linear-quadratic-Gaussian (LQG) system is treated first, and analytical closed-form probability densities are derived for all variables of interest. The MPC controller’s stage cost is chosen as the key performance index (KPI) to use for monitoring purposes. The stage cost is shown to have a generalized chi-squared distribution in the LQG case. The effects of nonzero, deterministic disturbances and plant/model mismatch on monitoring systems are briefly presented. The problem of determining the disturbance variances required for monitoring is briefly reviewed. Next the case of constrained, linear MPC and nonlinear MPC is discussed. In place of closed-form probability densities, online simulation is proposed as a general method for generating the statistics required for monitoring purposes. An overall conclusion of the paper is that the timing may be ideal for vendors to start offering monitoring products tailored to enhance their advanced MPC control product offerings.