A dynamic programming approach to manage virtual machines allocation in cloud computing

Authors

  • Abdellah Ouammou
  • Mohamed Hanini
  • Abdelghani Ben Tahar
  • Said El Kafhali

DOI:

https://doi.org/10.14419/ijet.v7i4.6.20448

Published:

2018-09-25

Keywords:

Dynamic Programming, Cloud Computing, Management resources, Value Iteration, Stochastic Modeling.

Abstract

As a result of the dynamic nature of Virtual Machine allocation in cloud computing, it is not easy to manage system resources or choose the best configuration based solely on human experience.  In this work, we used stochastic modelling instead of comprehensive experiments to evaluate the best resource management of the system. In such complex systems, choosing the best decision is a challenge, for this reason we have designed a heuristic algorithm, specifically, dynamic programming as a resource management and programming tool that finds a way that attempts to satisfy the conflicting objectives of high performance and low power consumption. As a scenario for using this algorithm, we addressed the problem of virtual machine allocation, a subset of physical machines is designated as "reserve", and the reserves are actives when the number of jobs in the system is sufficiently high. The question is how to decide when to activate the reserves. The simulation results demonstrated the benefit of using our framework to identify the policy for consolidation or for a low energy consumption and in order to have a good quality of service in the system

References

[1] A.Ouammou, A.Ben Tahar, M.Hanini, S.El Kafhali , “Modeling and Analysis of Quality of Service and Energy Consumption in Cloud Environmentâ€, International Journal of Computer Information Systems and Industrial Management Applications , ISSN 2150-7988, vol.10, (2018),pp. 98–106.

[2] Hajek, Bruce, “Optimal control of two interacting service stationsâ€, IEEE transactions on automatic control, Vol.29, No.6, (1984), pp.491-499.

[3] Kumar, P.Ramana, Varaiya, Pravin, Stochastic systems: Estimation, identification, and adaptive control, SIAM , (2015).

[4] Lippman, A.Steven, “Applying a new device in the optimization of exponential queuing systemsâ€, Operations Research, Vol.23, No.4, (1975), pp.687–710.

[5] Narayan, Prakash, “Jointly optimal admission and routing controls at a network nodeâ€, Stochastic Models , Vol.10, No.1, (1994), pp.223-252.

[6] A.Ouammou, M.Hanini, S.El Kafhali, A.Ben Tahar , “Energy Consumption and Cost Analysis for Data Centers with Workload Controlâ€, International Conference on Innovations in Bio-Inspired Computing and Applications , (2017), pp.92-101. Springer.

[7] Rosberg, Zvi, P.Varaiya, J.Walrand, “Optimal control of service in tandem queuesâ€, IEEE Transactions on Automatic Control , Vol.27, No.3, (1982), pp.600–610

[8] O.Mjihil, H.Taramit, A.Haqiq, and D.Huang, “Optimized Security as a Service Platforms via Stochastic Modeling and Dynamic Programmingâ€, International Conference on Innovations in Bio-Inspired Computing and Applications , (2017), pp.277-287. Springer.

[9] Tijms, C.Henk Stochastic models, John Wiley and Sons, (1994).

View Full Article: