Self-optimizing Control of an Air Source Heat Pump

Self-optimizing Control (SOC) is a method for finding appropriate controlled variables for which implementation of feedback control yields nearly-optimal operation regardless of variation in disturbances. The Jacobian estimation process in conventional SOC rely on an offline analysis of large amounts of steady-state data, which can be difficult in practice. In this paper, we propose a new SOC procedure enabled by extremum-seeking control (ESC). First, by presenting periodic disturbance dither into the plant model, the Jacobian estimation can be carried out with the dither-demodulation process in multivariable ESC, and then the nullspace method is used to find the optimal sensitivity matrix. The ESC can then be used to find the optimum setpoint value for the controlled variable from the previous step. The proposed method is compared with conventional SOC using a Modelica-based dynamic simulation of an air-source heat pump (ASHP) system.