The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Reinforcement Learning Approach for Resource Allocation in Cloud Computing

클라우드 컴퓨팅 환경에서 강화학습기반 자원할당 기법

  • Choi, Yeongho (University of Suwon, Department of Computer Science) ;
  • Lim, Yujin (University of Suwon, Department of Information Media) ;
  • Park, Jaesung (Department of Information Security)
  • Received : 2015.03.03
  • Accepted : 2015.03.24
  • Published : 2015.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Cloud service is one of major challenges in IT industries. In cloud environment, service providers predict dynamic user demands and provision resources to guarantee the QoS to cloud users. The conventional prediction models guarantee the QoS to cloud user, but don't guarantee profit of service providers. In this paper, we propose a new resource allocation mechanism using Q-learning algorithm to provide the QoS to cloud user and guarantee profit of service providers. To evaluate the performance of our mechanism, we compare the total expense and the VM provisioning delay with the conventional techniques with real data.

다양한 강점을 지닌 클라우드 서비스는 현대 IT 사업에 주요 이슈 중 하나이다. 클라우드 환경에서 서비스 제공자는 사용자의 동적인 자원 요구량을 예측하여 사용자의 QoS를 만족시켜야 한다. 사용자의 자원 요구량을 예측하는 기존 모델들은 사용자의 QoS는 만족시키지만 서비스 제공자의 이득은 보장하지 않는다. 본 논문에서는 Q-learning 기반의 자원 예측 모델을 제안하여 사용자의 QoS 뿐만 아니라 서비스 제공자의 이득을 최대화하였다. 또한 제안 기법의 성능 분석을 위해 실측 데이터를 이용하여 다른 예측 모델들과 비교함으로써 제안 기법의 우수함을 증명하였다.

Keywords

References

  1. J. Almeida, V. Almedia, D. Ardagna, C. Francalanci, and M. Trubian, "Resource management in the autonomic service-oriented architecture," in Proc. IEEE ICAC 2006, pp. 84-92, Dublin, Ireland, Jun. 2006.
  2. H. Kim and H. Kim, "Control algorithm for virtual machine-level fairness in virtualized cloud data center," J. KICS, vol. 38C, no. 6, pp. 512-520, Jun. 2013.
  3. M. Kim and M. Park, "Energy-aware virtual machine deployment method for cloud computing," J. KICS, vol. 40, no. 1, pp. 61- 69, Jan. 2015. https://doi.org/10.7840/kics.2015.40.1.61
  4. Y. Jiang, C. Perng, T. Li, and R. N. Chang, "Cloud analytics for capacity planning and instant VM provisioning," IEEE Trans. Network and Service Management, vol. 10, no. 3, pp. 312-325, May 2013. https://doi.org/10.1109/TNSM.2013.051913.120278
  5. T. Ahn, Y. Kim and S. Lee, "Dynamic resource allocation in distributed cloud computing," J. KICS, vol. 38B, no. 7, pp. 512-518, Jul. 2013. https://doi.org/10.7840/kics.2013.38B.7.512
  6. R. E. Parr, "Hierarchical control and learning for markov decision processes," Ph.D. dissertation, University of California, Berkeley, CA, 1998.
  7. A. M. Daniel, W. D. Lawrence, and A. F. A. Virgilio, Performance by Design, Prentice Hall, 2003.
  8. R. N. Calheiros, R. Ranjan, A. Beloglazov, C. A. F. De Rose, and R. Buyya, "CloudSim: A toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms," Software: Practice & Experience, vol. 4, no. 1, pp. 23- 50, Jan. 2011.
  9. C. C. Li and K. Wang, "An SLA-aware load balancing scheme for cloud datacenters," in Proc. IEEE ICOIN 2014, pp. 58-63, Phuket, Thailand, Feb. 2014.
  10. D. G. Feitelson, Pallel workloads, http://www.cs.huji.ac.il/labs/parallel/workload/

Cited by

  1. Q-learning 모델을 이용한 IoT 기반 주차유도 시스템의 설계 및 구현 vol.11, pp.3, 2015, https://doi.org/10.14372/iemek.2016.11.3.153