Open AccessReinforcement Learning Based APO-PTIRIAL for Load Balancing in Cloud Computing Environment
Author(s) -
V. Radhamani*,
G. Dalin
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b3014.098319
Subject(s) - reinforcement learning , cloud computing , computer science , virtual machine , load balancing (electrical power) , resource (disambiguation) , traffic intensity , distributed computing , power consumption , power (physics) , artificial intelligence , computer network , operating system , physics , geometry , mathematics , quantum mechanics , grid
Power consumption-Traffic aware-Improved Resource Intensity Aware Load balancing (PT-IRIAL) method was proposed to balance load in cloud computing by choosing the migration Virtual Machines (VMs) and the destination Physical Machines (PMs). In this paper, an Artificial Intelligence (AI) technique called Reinforcement Learning (RL) is introduced to find out an optimal time to migrate the selected VM to the selected destination PM. RL enables an agent to find out the most appropriate time for VM migration based on the resource utilization, power consumption, temperature and traffic demand. RL is incorporated into the cloud environment by creating multiple state and action space. The state space is obtained through the computation of resource utilization, power consumption, temperature and traffic of selected VMs. The action space is represented as wait or migrate which is learned through a reward function. Based on the action space, the selected VMs are waiting or migrating to the selected destination PMs.