Object-Oriented Modelling and Simulation of Air Flow in Data Centres Based on a Quasi-3D Approach for Energy Optimisation

Cloud computing has recently received considerable attention, as a promising approach for delivering ICT services by improving the utilisation of data centre resources. On the other hand, the increased usage of ICT, jointly with the increased cost of energy, make designing and managing data centres with energy efficient strategies a crucial and strategical problem.

In the literature there are many studies based on Computational Fluid Dynamics (CFD) simulation models. While the obtained results are usually very reliable and accurate, the massive use of such models for control design require a large amount of time due to their computational complexity and scarce flexibility. In addition, CFD models are usually quite sensitive to any kind of change to the operating conditions, e.g. when varying the considered load balancing algorithm.
In this paper, we propose a modelling and simulation framework suited for control design, that is able to simulate both heating and energy phenomena, and different load balancing strategies in a data centre. The purpose of this work is to provide a tool to perform energy-efficiency targeted studies, providing accurate and reliable results.