Virtual Machine Migration Planning in Software-Defined Networks - 2017

PROJECT TITLE :

Virtual Machine Migration Planning in Software-Defined Networks - 2017

ABSTRACT:

Live migration may be a key technique for virtual machine (VM) management in information center networks, that enables flexibility in resource optimization, fault tolerance, and load balancing. Despite its usefulness, the live migration still introduces performance degradations during the migration method. Thus, there was continuous efforts in reducing the migration time so as to minimize the impact. From the network’s perspective, the migration time is set by the number of knowledge to be migrated and also the offered bandwidth used for such transfer. During this paper, we examine the matter of a way to schedule the migrations and the way to allocate network resources for migration when multiple VMs would like to be migrated at the same time. We have a tendency to contemplate the matter within the Software-defined Network (SDN) context since it provides versatile control on routing. A lot of specifically, we tend to propose a method that computes the optimal migration sequence and network bandwidth used for every migration. We have a tendency to formulate this downside as a mixed integer programming, that is NP-laborious. To form it computationally possible for massive scale data centers, we propose an approximation scheme via linear approximation plus fully polynomial time approximation, and obtain its theoretical performance sure and computational complexity. Through in depth simulations, we have a tendency to demonstrate that our totally polynomial time approximation (FPTA) algorithm has a sensible performance compared with the optimal answer of the primary programming problem and two state-of-the-art algorithms. That's, our proposed FPTA algorithm approaches to the optimal resolution of the first programming drawback with but 10percent variation and much less computation time. Meanwhile, it reduces the entire migration time and service downtime by up to forty% and 20p.c compared with the state-of-the-art algorithms, respectively.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here