Open AccessAdaptive Resource Management Utilizing Reinforcement Learning Technique in Inter-Cloud Environments
Author(s) -
Vadla Pradeep Kumar,
Kolla Bhanu Prakash
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1055/1/012124
Subject(s) - cloud computing , provisioning , reinforcement learning , computer science , quality of service , resource (disambiguation) , virtual machine , service (business) , service level agreement , distributed computing , computer network , operating system , artificial intelligence , business , marketing
In cloud computing, the cloud provider agent offers the quality of service (QoS) for different categories of cloud consumer agents. In general, the inter-cloud environment provides resources as a virtual machine (VM) instance representing processing power, Memory allocated in RAM, and secondary storage for consumer agents with QoS guarantees. A service level agreement framework with a reinforcement learning mechanism is considered for provisioning VM’s for all categories of client classes. The parameters like cost of service, availability, and service demand are considered while provisioning VM’s in the inter-cloud environment. QoS violation happens because another set of cloud consumer agents receives the less no of VMs. In our approach, the adaptive resource provisioning is integrated with reinforcement learning mechanism during the service admission process and ensures the collaborated cloud providers will gain more profits without violation of SLA.