Data center temperature prediction method and system based on two-segment LSTM

Abstract

The invention discloses a two-segment LSTM-based data center temperature prediction method and system. The method comprises the steps of performing server clustering by using a K-mean algorithm to obtain training data; establishing a resource occupancy prediction model of the shortest time period for the server resource occupancy rate; establishing a temperature prediction model for the longest time period of the server air inlet temperature to form a two-section type LSTM prediction model, taking a prediction result of the resource occupation prediction model as a part of input of the temperature prediction model, and training the two-section type LSTM prediction model by using the training data until convergence, and the server CPU utilization rate, the server air inlet temperature historical data and the air conditioner air outlet historical data are input into the converged two-section LSTM prediction model, and the predicted temperature is output. According to the method, model degradation caused by differences among the servers is reduced through server clustering, different change rules of data of different sources are matched through the two-section LSTM prediction model, and the precision of data center temperature prediction is improved.

Description

technical field [0001] The invention belongs to the technical field of data center temperature prediction, and in particular relates to a two-stage LSTM-based data center temperature prediction method and system. Background technique [0002] In recent years, with the development of the mobile Internet, the amount of Internet data has shown explosive growth, and more and more Internet services are also based on the analysis of big data. These have led to a rapid increase in the demand for computing resources. The computing power of a single computer can no longer meet the demand. So cloud computing came into being. Cloud computing is the product of the integration of traditional computer and network technologies such as distributed computing, parallel computing, virtualization, and load balancing. Cloud computing virtualizes a large number of servers into computing resource nodes through virtual machine technology. Users do not need to care about hardware implementation a...

AI Technical Summary

Problems solved by technology

However, the existing data-driven temperature prediction methods still have low prediction accuracy and do not consider the data center layout and physical properties.

Images