A Review on Machine Learning Based Resource Allocation in Cloud Computing

Abstract

Cloud computing is the most advanced technology in the real world environment and provides flexible and convenient possibilities for users to utilize available services. Resource provisioning to the satisfaction of user requirements becomes the most challenging task in the heterogeneous cloud environment. Proper admission control algorithms need to be proposed for better resource provisioning with improved user satisfaction level. The proposed approaches and algorithms have been implemented using CloudSim and the final results have been assessed under the cloud environment. The experimental results indicate that the proposed research methodologies reduce the makespan, cost and result in more efficient satisfaction level for users and service providers when compared to existing algorithms like SLA based model.From the results, the overall findings of the research work can be thus concluded that the proposed research methodologies have the potential to achieve better admission control in cloud environment yielding a better satisfaction of user specified constraints. The comparison of the experimental results show that the proposed research work DLAPUJS provides better results than the previous and existing research methods in terms of profit, number of Virtual Machines(VMs) initiated, execution time and data transfer cost. In future scenario, big data applications can be experimented for the admission control methodologies to adapt to the real world environment. Dynamic switching of resources can be introduced in response to dynamic requests submitted by cloud users. Fault tolerance mechanisms can be integrated with admission control frameworks to avoid the risk factors.