Discrete-time inverse optimal control for indoor air temperature and humidity in a direct expansion (DX) air conditioning (A/C) system

This paper presents a discrete-time inverse optimal control scheme for trajectory tracking of a direct expansion (DX) air conditioning (A/C) system. A recurrent high order neural network (RHONN) is used to identify the plant model, and based on this model, a discrete-time inverse optimal control law is derived. The neural network learning is performed on-line by Kalman filtering. The proposed scheme has a structure in which the trajectories can be defined hierarchical by a building energy management system. This novel scheme is tested via simulation. The obtained results for trajectory tracking illustrate the effectiveness of the proposed approach.