Host Load Prediction Based on PSR and EA-GMDH for Cloud Computing System

Host Load Prediction is one of the most effective measures to improve resource utilization in the Cloud systems. As the drastic fluctuation of the host load in the Cloud, accurate prediction of host load is still a challenge. In this paper, we propose a new prediction method which combines the Phase Space Reconstruction (PSR) method and the Group Method of Data Handling (GMDH) based on Evolutionary Algorithm (EA). Our proposed method could predict not only the mean load in consecutive future time intervals, but also the actual load in each consecutive future time interval. We evaluate our method using the host load trace in the Google data center with thousands of machines. According to the experiment results, our method outperforms the other methods by more than 60% in mean load prediction, and preforms well on actual load prediction over different time intervals, i.e. 0.5h to 3h.