Enhanced Resource Allocation and Workload Management using Reinforcement Learning Method for Cloud Environment
P Suresh1, P Keerthika2, K Logeswaran3, R Manjula Devi4, M Sangeetha5
1P Suresh, Information Technology, Kongu Engineering College, Perundurai, Erode, TamilNadu, India.
2P Keerthika, Computer Science and Engineering, Kongu Engineering College, Perundurai, Erode, TamilNadu, India.
3K Logeswaran, Information Technology, Kongu Engineering College, Perundurai, Erode, TamilNadu, India.
4R Manjula Devi, Computer Science and Engineering, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India.
5M Sangeetha, Computer Science and Engineering, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India.
Manuscript received on November 12, 2019. | Revised Manuscript received on November 23, 2019. | Manuscript published on 30 November, 2019. | PP: 8296-8302 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8983118419/2019©BEIESP | DOI: 10.35940/ijrte.D8983.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cloud computing is a delivery model of IT resources such as computing servers, storage, databases, networking and software over the Internet. It offers the resources as services based on demand with more faster, flexible and economies of scale. The major challenges in the cloud computing are resource allocation and workload management due to the scalability of the cloud users and the services deployed in it. Even though there are various approaches available to manage workload and resource allocation, unfortunately most of them fail to mange it properly. This paper proposes a Reinforcement Learning based Enhanced Resource Allocation and Workload Management (RL-ERAWM) approach to increase the performance of cloud with large number of tasks and users. It implements the Q-Learning approach which effectively considers arrival rate of the requests and workload of the virtual machine. Experimental results prove that the proposed method alleviates the performance of task scheduling and workload management process compared with other approaches in terms of response time, makespan and virtual machine utilization. Keywords :
Keywords: Cloud Computing, Task Scheduling, Workload management, Reinforcement Learning, Resource Allocation, Q-Learning.
Scope of the Article: Cloud Computing.