Lower air supply data center CFD simulation verification method based on neural network

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a lower air supply data center CFD simulation verification method based on a neural network, and the method comprises the following steps: 1, selecting initial data of a machine room to build a CFD simulation model of the machine room, and obtaining a simulation result through the calculation of CFD software;2, collecting the actual air inlet temperature of the cabinet and the actual power of the air conditioner according to a certain sampling period to serve as training samples of the neural network; 3,establishing a neural network model; 4, inputting the training sample into a neural network to predict the predicted power of the air conditioners, and obtaining the influence degree of the cold condition of the cabinet and the actual power of each air conditioner; and step 5, comparing a flow field result under the floor of the machine room predicted by the neural network with a simulation result, adjusting the position of a cabinet in the machine room according to the adjusted initial data, and optimizing the airflow layout of the machine room. The method enables the cooling effect of the cabinet to be more remarkable, and is convenient to use.

Description

Technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a CFD simulation verification method for a downward air supply data center based on a neural network. Background technique [0002] In the entire life cycle of the computer room data center, generally with the upgrading of IT equipment, the power density of the computer room equipment will be greatly improved compared with the initial stage of construction, which puts forward higher requirements on the cooling system of the computer room. Blindly increasing the number of air conditioners or lowering the set temperature of air conditioners not only cannot completely solve the problem of equipment overheating, but also leads to a significant increase in the energy consumption of the data center in the computer room, which has also become the main bottleneck restricting the expansion of the capacity of the data center in the computer room. In fact, if the air distribution...

AI Technical Summary

Problems solved by technology

Blindly increasing the number of air conditioners or reducing the set temperature of the air conditioners will not only fail to completely solve the problem of equipment overheating, but will also lead to a sharp increase in energy consumption of the data center in the computer room, which has become the main bottleneck restricting the capacity expansion of the data center in the computer room

In fact, if the airflow organization of the data center in the computer room is unreasonable, even if the total cooling capacity of the air conditioner is much greater than the heat generated by the IT equipment, the inlet temperature of some equipment will still be too high

Lowering the set temperature of the air conditioner will cause overcooling problems, and the cooling energy consumption will remain high.

[0003] In the existing process of using CFD software to carry out energy-saving transformation of data centers, since the air is colorless and transparent, it is impossible to intuitively and efficiently judge whether the gas flow range in the CFD simulation results is consistent with the actual situation

Images