Queue Based Q-Learning for Efficient Resource Provisioning in Cloud Data Centers

Meera, A.; Swamynathan, S.

doi:10.4018/ijiit.2015100103

“…Resource allocation is very essential for work ow scheduling in the cloud. The Queue based Q-learning method [24] used reinforcement learning for optimized resource allocation. The algorithm uses the inter quartile range to identify the VM with minimum load for allocation.…”

Section: Literature Surveymentioning

confidence: 99%

Computational Intelligence Approach in Optimizing the Resource Allocation for Workflow Execution in the Cloud

Kanagaraj¹,

Swamynathan

²

,

RADHA³

2023

Preprint

0

View full text Add to dashboard Cite

Virtual Machine (VM) assignment is an important phase during workflow execution in the cloud. Identifying a suitable type of VM for executing the workflow is a difficult problem. Cloud resource providers offer diverse categories of VMs to cater the needs of the users and encourage the users to select an appropriate type of VM to reduce the workflow execution time and cost. A suitable VM type can be selected only if the resource requirements of the workflow is known, which a difficult task for cloud users till now. Hence many users depend on general purpose VMs, rather than using a suitable type of VM for their application. This work proposes an intelligent recommendation system that helps the cloud users to select suitable type of VM for their application. The main objective of this work is to identify the type of the workflow using computational intelligence and to recommend a sutitable type of VM for execution. The system uses three supervised learning algorithms such as Probabilistic Neural network (PNN) , Deep Forward Neural Network (DFNN) and Naïve Bayes classier for workflow classification. The Bayes classifier is found be very accurate for workflow classification, when compared to the other algorithms. Also the relative optimality of the classifier is tested using popular workflow scheduling algorithms like ICPCP (IAAS Cloud Partial Critical Path algorithm), MER (Maximum Effective Reduction) and LBS (Level Based Scheduling). The results confirm that the workflow execution time and cost are reduced to a great extent, when executing a workflow using a suitable type of VM than with the general purpose VM.

show abstract

Securely Communicating With an Optimal Cloud for Intelligently Enhancing a Cloud's Elasticity

Kirthica

¹

,

Ramaswamy

²

2019

Cloud Security

0

View full text Add to dashboard Cite

One of the principle features on which cloud environments operate is the scaling up and down of resources based on users' needs, called elasticity. This feature is limited to the cloud's physical resources. This article proposes to enhance the elasticity of a cloud in an intelligent manner by communicating with an optimal external cloud (EC) and borrowing additional resources from it when the cloud runs out of resources. This inter-cloud communication is secured by a model whose structure is similar to the Kerberos protocol. To choose the optimal EC for a particular request of a user, a list of parameters, collectively termed as RePVoCRaD, are enumerated. Once chosen, trust is established with the chosen EC and inter-cloud communication begins. While existing works deal with third parties to establish or secure inter-cloud communication, this work is novel in that there is absence of third parties in the entire process, thereby reducing security threats and additional costs involved. Evaluating this work based on turnaround time and transaction success rate, in a real-time cloud environment, it is seen that the cloud's elasticity is so enhanced that it successfully accommodates its users' additional demands by the fastest means possible.

show abstract

Securely Communicating with an Optimal Cloud for Intelligently Enhancing a Cloud's Elasticity

Kirthica

¹

,

Ramaswamy

²

2018

International Journal of Intelligent Information Technologies

View full text Add to dashboard Cite

One of the principle features on which cloud environments operate is the scaling up and down of resources based on users' needs, called elasticity. This feature is limited to the cloud's physical resources. This article proposes to enhance the elasticity of a cloud in an intelligent manner by communicating with an optimal external cloud (EC) and borrowing additional resources from it when the cloud runs out of resources. This inter-cloud communication is secured by a model whose structure is similar to the Kerberos protocol. To choose the optimal EC for a particular request of a user, a list of parameters, collectively termed as RePVoCRaD, are enumerated. Once chosen, trust is established with the chosen EC and inter-cloud communication begins. While existing works deal with third parties to establish or secure inter-cloud communication, this work is novel in that there is absence of third parties in the entire process, thereby reducing security threats and additional costs involved. Evaluating this work based on turnaround time and transaction success rate, in a real-time cloud environment, it is seen that the cloud's elasticity is so enhanced that it successfully accommodates its users' additional demands by the fastest means possible.

show abstract

Queue Based Q-Learning for Efficient Resource Provisioning in Cloud Data Centers

Cited by 3 publications

References 27 publications

Computational Intelligence Approach in Optimizing the Resource Allocation for Workflow Execution in the Cloud

Computational Intelligence Approach in Optimizing the Resource Allocation for Workflow Execution in the Cloud

Securely Communicating With an Optimal Cloud for Intelligently Enhancing a Cloud's Elasticity

Securely Communicating with an Optimal Cloud for Intelligently Enhancing a Cloud's Elasticity

Contact Info

Product

Resources

About