A RNN-LSTM based Predictive Autoscaling Approach on Private Cloud

Authors

  • E. G. Radhika  Department of Information Technology, PSG College of Technology, Coimbatore, Tamilnadu, India
  • G. Sudha Sadasivam  Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, Tamilnadu, India
  • J. Fenila Naomi  Department of Information Technology, PSG College of Technology, Coimbatore, Tamilnadu, India

Keywords:

Web applications, Autoscaling, Recurrent Neural Network, Long Short Term Memory, OpenStack

Abstract

Web applications are the most prevalent applications of today’s technology. They are typically characterized by IT resource requisites that fluctuate with usage, predictably or unpredictably. Failure to respond will impact customer satisfaction. Autoscaling is a feature of cloud computing that has the ability to scale up the cloud resources according to demand. It provides better availability, cost and fault tolerance. In the existing scenario, reactive autoscaling is used where the system reacts to changes and scale up the resources when there is a demand. The proposed system uses predictive autoscaling approach to predict future resource requisites in order to ascertain adequate resource are available ahead of time. The system uses a deep learning technique termed Recurrent Neural Network with Long Short Term Memory (RNN-LSTM) to predict the future demand based on the historical data. The predicted result is integrated with an OpenStack open source cloud platform to perform predictive autoscaling.

References

  1. Ching-Chi Lin, Jan-Jan Wu, Pangfeng Liu, Jeng-An Lin and Li-Chung Song, "Automatic Resource Scaling for Web Applications in the Cloud", in Grid and Pervasive Computing, pp. 81–90, 2013.
  2. Craig Sterrett, Yih Leong Sun, Shamail Tahir, "OpenStack Workload Reference Architecture: Web Applications",URL https://www.openstack.org/assets/ software/mitaka/ OpenStackWorkloadRefArchWebApps-v7.pdf.
  3. Sushil Deshmukh , Sweta Kale, "Automatic Scaling Of Web Applications For Cloud Computing Services: A Review", in International Journal of Research in Engineering and Technology, Vol. 03, pp. 2321-7308, January 01, 2014.
  4. AWS Auto Scaling Pricing, URL https://aws.amazon.com/autoscaling/pricing/.
  5. Kirk Evans, "Autoscaling Azure–Virtual Machines", URL https://blogs.msdn.microsoft.com/kaevans/2015/02/20/ autoscaling-azurevirtual-machines/ 
  6. Jianyu Sun, Haopeng Chen and Zhida Yin,"AERS: An Autonomic and Elastic Resource Scheduling Framework for Cloud Applications" in 2016 IEEE International Conference on Services Computing (SCC), pp: 66-73, September 2016.
  7. Raouia Bouabdallah, Soufiene Lajmi, Khaled Ghedira," Use of Reactive and Proactive Elasticity to Adjust Resources Provisioning in the Cloud Provider", in 2016 IEEE 18th International Conference on High Performance Computing and Communications, 12-14 December, 2016.
  8. Jingqi Yang, Chuanchang Liu, Yanlei Shang, Zexiang Mao, Junliang Chen, "Workload Predicting-Based Automatic Scaling in Service Clouds", in IEEE Sixth International Conference on Cloud Computing, 2013.
  9. Hector Fernandez, Guillaume Pierre, Thilo Kielmann, "Autoscaling Web Applications in Heterogeneous Cloud Infrastructures", 2014 IEEE International Conference on Cloud Engineering (IC2E), March 2014.
  10. Nilabja Roy, Abhishek Dubey, Aniruddha Gokhale, "Efficient Autoscaling in the Cloud Using Predictive Models for Workload Forecasting", in 2011 IEEE International Conference on Cloud Computing (CLOUD), September, 2011.
  11. Mehran N. A. H. Khan, Yan Liu, Hanieh Alipour, "Modeling the Autoscaling Operations in Cloud with Time Series Data", IEEE 34th Symposium on Reliable Distributed Systems Workshop (SRDSW), January 07,2016.
  12. Martin Duggan, Karl Mason, Jim Duggan, Enda Howley, Enda Barrett," Predicting Host CPU Utilization in Cloud Computing using Recurrent Neural Networks", in 8th International Workshop on Cloud Applications and Security, November, 2017.
  13. Lindsay Hill, "Using Telegraf, InfluxDB and Grafana to Monitor Network Statistics", URL https://lkhill.com/telegraf-influx-grafana-network-stats/, November 24, 2017.
  14. How to Use Hashicorp Terraform with OpenStack, URL https://platform9.com/blog/how-to-use-terraform-with-openstack/, July 22, 2016.
  15. Michal Medvecky, "Managing your (OpenStack) infrastructure with Hashicorp Terraform" URL https://medium.com/@michalmedvecky/managing-your-openstack-infrastructure-with-hashicorp-terraform-8c93ade214b4, May 17, 2017.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-04-30

Issue

Volume 3, Issue 3, March-April-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

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

How to Cite

[1]
E. G. Radhika, G. Sudha Sadasivam, J. Fenila Naomi, " A RNN-LSTM based Predictive Autoscaling Approach on Private Cloud, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 3, pp.1940-1946, March-April-2018.