Name
Title | ||
|---|---|---|
Multi-step-ahead Host Load Prediction with GRU Based Encoder-Decoder in Cloud Computing |
Abstract | ||
|---|---|---|
The details of the host workloads in cloud computing environment and the application demands of the real world computing system are becoming so complex that it throws a big challenge to the major cloud infrastructure vendors. To achieve service level agreements between users and cloud service vendors, it is essential to apply accurate prediction of future host load, which is also significant to improve the resource allocation and utilization in cloud computing. Although that there were several various methods and models developed, few of them can acquire the long-term temporal dependencies appropriately to make accurate predictions. In this paper, we apply a GRU based Encoder-Decoder network(GRUED) which contains two gated recurrent neural networks(GRUs) to address these issues. Thorough empirical studies based upon the Google resources usage traces and the traditional Unix system load traces demonstrate that our proposed method outperforms other state- of-the-art approaches for the prediction of multi-step-ahead host workload in cloud computing. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/KST.2018.8426104 | 2018 10th International Conference on Knowledge and Smart Technology (KST) |
Keywords | DocType | ISSN |
Cloud computing,Encoder-Decoder,Recurrent neural network,Host load prediction,GRU | Conference | 2374-314X |
ISBN | Citations | PageRank |
978-1-5386-4016-6 | 0 | 0.34 |
References | Authors | |
15 | 5 | |