The obstructive sleep apnoea syndrome (OSAS) is characterized by a collapse of the upper respiratory tract, resulting in a reduction of the blood oxygen- and an increase of the carbon dioxide (CO2) - concentration, which causes repeated sleep disruptions. The gold standard to treat the OSAS is the continuous positive airway pressure (CPAP) therapy. The continuous pressure keeps the upper airway open and prevents the collapse of the upper respiratory tract and the pharynx. Most of the available CPAP-devices cannot maintain the pressure reference . In this work a model predictive control approach is provided. This control approach has the possibility to include the patient’s breathing effort into the calculation of the control variable. Therefore a patient-individualized control strategy can be developed.