A two-segment LSTM based data center temperature prediction model

Abstract

Nowadays, data centers are critical infrastructure for the information industry. Thermal security is one of the most concerning problems of the data center efficiently providing service. The temperature prediction method is an effective way, which overcomes the lagging of the feedback control and rewards a high prediction accuracy. While the current LSTM based prediction methods are limited in accuracy and restricted in scalability due to the lack of knowledge of physical properties and consideration of time constant differences of features. To address this, we propose a data center temperature prediction model with two-segment LSTM for prediction separately for IT equipment load and other heat-related variables with different time constants. The model takes into account the physical properties of the equipment and achieves higher prediction accuracy. The experimental results show that the prediction accuracy of our method is 27.27% higher than the state-of-art single segment LSTM method.