Machine Learning-based Energy Consumption Model for Data Center

The accurate prediction of time series data in the industrial production process can provide important guidance for the scheduling and decision-making of industrial systems, and is also an important part of predictive control technology. In this paper, a time series prediction model which introduces the graph neural network (GCN) is proposed. This model mainly consists of a time series feature extraction module and a relational modeling module. In the time series feature extraction module, the Att-LSTM model is proposed to extract the feature information of time series data. In the relational modeling module, a novel M-GCN network is proposed to model the relevance among different time series nodes. In addition, based on the time series prediction model, a time series multi-classification model is also proposed. The proposed model can predict the energy consumption conditions of the data center accurately. The experimental results demonstrate that the propose model can provide a desirable performance superior to some traditional models in accuracy and robustness.