Virtual machine migration method based on load cognition

Abstract

Virtualization technology plays an important role in cloud computing. Virtual machine (VM) migration not only enables load balancing of hosts in data center to avoid overload anomalies, but also reduces the cost of cloud computing data centers. Our work mainly focused on the communication costs of VMs migration in data center. In this paper, a double auction-based VM migration algorithm is proposed, which takes the cost of communication between VMs into account under normal operation situation. The algorithm of VM migration is divided into two parts: (i) selecting the VMs to be migrated according to the communication and occupied resources factors of VMs and (ii) determining the destination host for VMs which to be migrated. In the first process of VM migration, we proposed VMs greedy selection algorithm (VMs-GSA) to select VMs. A VM Migration Double Auction Mechanism was applied to the second process of VM migration to obtain the mappings between VMs and underutilized hosts. The simulation result shows that the proposed VM migration algorithm-based heuristic is efficient. The traffic generated by VMs-GSA is 35% less than the random algorithm, and the success rate of VM migration is very high.