A model reference neural controller is proposed and applied to control the temperature for air-conditioning system (A/C) of vehicle. The compressors with a brushless DC (BLDC) driver used to drive the compressor provides variable refrigerant flow (VRF) by changing the speed of compressor for energy saving. The BLDC driver will improve the high heat generation problem in low load operation conditions. In this paper, the dynamic model of vehicle A/C system is built and the simulation results of proposed method show the time response of temperature will follow the responses of the reference model with better adaptability than the conventional PID control.