A data-driven subspace predictive control method for air-cooled data center thermal modelling and optimization.

•On the basis of power efficiently and safe operating environment, a data-driven control framework is proposed for for the modelling and managing the thermal environment of air-cooled data centers.•An sub-space model predictive control based technique is proposed for regulating the power allocation of the server racks and the supply temperature of cold air.•A reasonable event-triggered law is designed to solve the problem of the low computational efficiency of the conventional sub-space control method.