Time-Series Load Prediction for Cloud Resource Allocation Using Recurrent Neural Networks

Authors
  • Yun Zi

Abstract

This study proposes a container scheduling optimization system based on recurrent neural network (RNN) to improve the efficiency of cloud computing platform in resource management. By using the RNN model to analyze and predict historical load data, this system can accurately estimate future resource requirements and dynamically adjust the container scheduling strategy to achieve efficient resource allocation and utilization. Experimental results show that compared with other comparison models such as support vector regression (SVR), decision tree regression (DTR), multi-layer perceptron (MLP) and long short-term memory network (LSTM), the RNN model performs best in load prediction tasks, with high prediction accuracy and good generalization ability. This system can not only effectively reduce resource waste, but also improve server utilization, providing a reliable solution for container management in actual production environments. Future research can introduce graph neural network (GNN) or self-attention mechanism on the existing basis to further improve the prediction performance of the system. In addition, expanding cross-platform container scheduling optimization methods and creating a more intelligent resource management system will also be an important research direction in the future.

References
Cover Image
Downloads
Published
2024-10-30
Section
Articles
License
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Academic Scholar Hub Press also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.

How to Cite

Zi, Y. (2024). Time-Series Load Prediction for Cloud Resource Allocation Using Recurrent Neural Networks. Journal of Computer Technology and Software, 3(7). https://doi.org/10.5281/zenodo.14172329

Most read articles by the same author(s)