Resource Allocation and Optimization Based on Queuing Theory and BP Network

  • Hong Tang
  • Delu Zeng
  • Xin Liu
  • Jiabin Huang
  • Yinghao Liao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634)


In this article, we present a resource allocation and optimization strategy for data center based on resource utilization prediction with back-propagation (BP) neural network, aiming to improve the resource utilization. We handle resource contention among virtual machines with resource migrating to improve the resource utilization under the assumption of different functional applications integrated in each server. With the BP network predicted resources utilization and throughput rate of SFC, we adjust and optimize the resource configuration in virtual resource pool and servers, which further improves resource utilization in data center. Our experiments show that the proposed dynamic resource allocation and optimization strategy performs effectively. And also the BP network achieves more accuracy prediction compared with linear regression model.


Resource allocation BP neural network Resource utilization prediction Network Function Virtualization 



This work was supported in part by the grants of National Science Foundation of China (No. 61571005, No. 61103121, No. 61571382, No. 61372142), the NSF of Guangdong Province (No. 2015A030313589), and the XMU President Funding (No. 20720150093).


  1. 1.
    Masdari, M., Nabavi, S.S., Ahmadi, V.: An overview of virtual machine placement schemes in cloud computing. J. Netw. Comput. Appl. 66, 106–127 (2016)CrossRefGoogle Scholar
  2. 2.
    Hieu, N.T., Francesco, M.D., Jaaski, A.Y.: A virtual machine placement algorithm for balanced resource utilization in cloud data centers. In: 7th IEEE International Conference on Cloud Computing, pp. 474–481. IEEE Press, Alaska (2014)Google Scholar
  3. 3.
    Zhang, Z., Hsu, C.W., Chang, M.: Cool cloud: a practical dynamic virtual machine placement framework for energy aware data centers. In: 8th IEEE International Conference on Cloud Computing, pp. 758–765. IEEE Press, New York (2015)Google Scholar
  4. 4.
    Vigliotti, A., Batista, D.M.: A green network-aware VMs placement mechanism. In: IEEE Global Communications Conference, pp. 2530–2535. IEEE Press, Austin (2014)Google Scholar
  5. 5.
    Machida, F., Kawato, M., Maeno, Y.: Redundant virtual machine placement for fault-tolerant consolidated server clusters. In: IEEE Network Operations and Management Symposium, pp. 32–39. IEEE Press, Osaka (2010)Google Scholar
  6. 6.
    Van, H.N., Tran, F.D., Menaud, J.: Performance and power management for cloud infrastructures. In: 3th IEEE International Conference on Cloud Computing, pp. 329–336. IEEE Press, Miami (2010)Google Scholar
  7. 7.
    Tso, F.P., Hamilton, G., Oikonomou, K., Pezaros, D.P.: Implementing scalable, network-aware virtual machine migration for cloud data centers. In: 6th IEEE International Conference on Cloud Computing, pp. 557–564. IEEE Press, Santa Clara Marriott (2013)Google Scholar
  8. 8.
    Duongba, T., Nguyen, T., Bose, B., Tran, T.: Joint virtual machine placement and migration scheme for datacenters. In: IEEE Global Communications Conference, pp. 2320–2325. IEEE Press, Austin (2014)Google Scholar
  9. 9.
    Sato, K., Samejima, M., Komoda, N.: Dynamic optimization of virtual machine placement by resource usage prediction. In: 11th IEEE International Conference on Industrial Informatics, pp. 86–91. IEEE Press (2013)Google Scholar
  10. 10.
    Yin, J., Lu, X., Chen, H., Zhao, X., Xiong, N.N.: System resource utilization analysis and prediction for cloud based applications under bursty workloads. Inf. Sci. 279, 338–357 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Hong Tang
    • 1
  • Delu Zeng
    • 2
  • Xin Liu
    • 3
  • Jiabin Huang
    • 3
  • Yinghao Liao
    • 3
  1. 1.Sun Yat-sen UniversityGuangzhouChina
  2. 2.South China University of TechnologyGuangzhouChina
  3. 3.Xiamen UniversityXiamenChina

Personalised recommendations