Seasonal Forecasting Model of Data Center Net Load Based on LSTM-Attention Fusion Neural Network

Accurate load forecasting of data centers is an important supporting means for them to participate in demand response or power market. In view of the problems such as large errors and poor stability existing in current load forecasting methods of data centers, and considering the differences of cooling loads in different seasons, in this paper, a LSTM-Attention fusion neural network model based on Attention mechanism is proposed for the net load prediction of data centers. LSTM neural network is used to extract the time series characteristics of data center loads, and then the Attention mechanism is added to capture the fluctuation characteristics to improve the prediction accuracy. Based on the data set provided by the National Renewable Energy Laboratory (NREL), seasonal forecasting is carried out in this paper. The results show that the introduction of the Attention mechanism in the model can effectively improve the accuracy of data center load forecasting, and the model has transferability.