Self-Healing Virtual Desktop Infrastructure via Reinforcement Learning
Keywords:
reinforcement learning, virtual desktop infrastructure, self-healing systems, hypervisor orchestration, resource contentionAbstract
The objective of this study is to introduce self-healing in Virtual Desktop Infrastructure (VDI) environments through the help of Reinforcement Learning (RL) applications. A RL-based controller monitors session latency, resource congestion, and user activity in real time. By learning optimal migration policies, virtual machines (VMs) between hypervisors and cloud platforms automatically reallocates dynamically.
Downloads
References
M. Armbrust, A. Fox, R. Griffith, et al., “A view of cloud computing,” Commun. ACM, vol. 53, no. 4, pp. 50–58, Apr. 2010.
V. Sharma, H. Cho, and C. Lee, “Virtual desktop infrastructure: A comprehensive review and research agenda,” IEEE Access, vol. 5, pp. 18856–18878, 2017.
M. R. Endsley, “Toward a theory of situation awareness in dynamic systems,” Hum. Factors, vol. 37, no. 1, pp. 32–64, 1995.
H. Nguyen and C. S. Kim, “Resource management in virtual desktop infrastructure: A survey,” J. Supercomput., vol. 71, no. 3, pp. 967–993, 2015.
Y. Chen, M. Li, Y. Qian, and X. Huang, “Efficient load balancing for virtual desktop infrastructure,” IEEE Trans. Parallel Distrib. Syst., vol. 27, no. 5, pp. 1396–1409, May 2016.
C. Li, L. Jiang, and J. Zhou, “Self-healing systems: survey and challenges,” J. Comput. Sci. Technol., vol. 31, no. 3, pp. 433–446, May 2016.
S. Park and D. Lee, “An adaptive self-healing approach for virtualized cloud environments,” in Proc. IEEE Int. Conf. Cloud Computing, New York, USA, 2016, pp. 364–371.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA: MIT Press, 2018.
J. Kober, J. A. Bagnell, and J. Peters, “Reinforcement learning in robotics: A survey,” Int. J. Robot. Res., vol. 32, no. 11, pp. 1238–1274, Sept. 2013.
M. Ghasemi and M. Zafer, “Optimal resource allocation in virtualized cloud data centers via reinforcement learning,” in Proc. IEEE INFOCOM, San Francisco, CA, 2016, pp. 1–9.
H. Xu and B. Li, “Dynamic cloud resource allocation via distributed reinforcement learning,” IEEE Trans. Cloud Comput., vol. 5, no. 4, pp. 675–686, Oct.–Dec. 2017.
Z. Chen, Y. Wen, W. Wang, and Z. Sun, “A self-adaptive approach for virtual machine migration in cloud computing,” IEEE Trans. Cloud Comput., vol. 4, no. 3, pp. 327–339, July-Sept. 2016.
X. Wang, L. Li, and H. Zhu, “Reinforcement learning-based virtual machine migration policy in cloud environment,” in Proc. IEEE Int. Conf. Cloud and Autonomic Computing, London, UK, 2017, pp. 1–6.
K. Zhang, J. Li, and M. Wang, “A heuristic approach for virtual desktop infrastructure load balancing,” Comput. Netw., vol. 107, pp. 188–198, Feb. 2016.
S. P. Kumar and D. Chandra, “Rule-based versus learning-based resource management in cloud data centers: A comparative study,” J. Syst. Softw., vol. 130, pp. 215–225, Jan. 2017.
J. Guitart, J. Torres, and O. Rana, “A survey on self-healing techniques in cloud computing environments,” J. Netw. Comput. Appl., vol. 102, pp. 155–172, May 2018.
C. K. Williams and C. E. Rasmussen, Gaussian Processes for Machine Learning, Cambridge, MA: MIT Press, 2006.
A. Capone, L. Fratta, and M. Marchese, “A reinforcement learning approach for resource management in virtualized networks,” IEEE Commun. Lett., vol. 19, no. 7, pp. 1195–1198, July 2015.
N. Nagothu, S. Chatterjee, and J. Fan, “Dynamic VM placement in cloud data centers using reinforcement learning,” in Proc. IEEE Int. Conf. Big Data and Cloud Computing, Sydney, Australia, 2017, pp. 62–69.
T. R. Oliveira and R. L. F. Cunha, “Self-adaptive cloud management through reinforcement learning: A survey,” Future Gener. Comput. Syst., vol. 92, pp. 139–157, Jan. 2019.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
