Ph.D.

Program-2021 (odd semester)

(Department name CSE)

(Priority-aware VM Allocation and Network

Bandwidth Provisioning in Software-Defined
Networking (SDN)-enabled Clouds)

G.ABHINAV RISHI
 Introduction to domain

• Cloud computing offers tremendous potential benefits in agility, resiliency,

and economy. Organizations can move faster reduce downtime (thanks to inherent
elasticity and other cloud characteristics), and save money). We also
see security benefits since cloud providers have significant economic incentives to
protect customers.

• This domain provides the conceptual framework for the rest of the Cloud
Security Alliance’s guidance. It describes and defines cloud computing, sets our
baseline terminology, and details the overall logical and architectural frameworks
used in the rest of the document.

•There are many different ways of viewing cloud computing: It's a technology, a
collection of technologies, an operational model, a business model, just to name a
few. It is, at its essence, transformative and disruptive. It's also growing very, very
quickly, and shows no signs of slowing down.
 Introduction to the research topic
• Majority of the recent Internet applications utilize cloud computing
infrastructure to provide elastic and cost-effective services.
• Cloud providers provision computing, memory, storage, and networking
resources for tenants to serve their applications with different
requirements. These applications require different amounts of resources
with a different priority.
• Compute-intensive applications such as large scientific application
require more computing and memory power than networking resources,
while network intensive applications need more networking bandwidth
than computing power.
• Cloud providers should allocate and provision resources efficiently in
the data centre to satisfy various requirements.
 Need / Rational & scope of the study

• A priority-aware VM placement algorithm that places VMs of a critical

application into proximity hosts with enough resources;
• Bandwidth allocation method for higher-priority flows to guarantee the
minimum bandwidth in overloaded data centre networks.
• A system that provisions both compute and network resources jointly to
offer quality of service to critical applications in SDN-enabled cloud data
centres.
• Performance evaluation of algorithm that is compared with related
approaches and depicted its effectiveness through detailed simulation
experiments using both synthetic and real workloads.
 Objectives of the study

• It explain the strategy for computing and networking resource allocation in

aware of application’s priority.

• Model the priority of application discretely. Each application provides its priority
as a critical (higher priority) or normal (lower-priority) application.

• Propose a novel VM and network allocation approach (PAVA+BWA) in the

combination of a priority-aware VM allocation algorithm (PAVA) considering
network connection between VMs on the application level with a network
bandwidth allocation algorithm (BWA) to differentiate the higher-priority flows
over normal network traffics.
 Research problem

• It is difficult to guarantee such QoS in clouds because resources in a data centre

are shared by multiple tenants and applications, which are often over-booked to
save the operational cost of a cloud provider.
• A simple method for providers to guarantee the QoS is to assign dedicated hosts
and networks solely for a certain tenant, but it is deprived of all the benefits of
clouds such as elasticity, low-cost, and dynamic provisioning of the resources.
• In cloud data centres, there are trade-offs between network proportionality,
minimum guarantee, and high utilization . This limitation lets cloud providers in
capable of guaranteeing a minimum bandwidth for a certain tenant while
targeting network proportionality and high utilization at the same time.
 Research Methodology / Technique

• The strategy for computing and networking resource allocation in aware of

application’s priority. We model the priority of application discretely. Each
application provides its priority as a critical (higher priority) or normal (lower-
priority) application.
• Priority-Aware VM Allocation (PAVA) which allocates a closely connected host
for a critical application with the information of network topology. In this
method, we consider the priority of application as well as the network
connectivity of physical hosts in a data centre.
•Bandwidth Allocation for Priority Applications.
•Baseline Algorithms The proposed approaches are compared with three
baseline algorithms: exclusive resource allocation, random allocation, and state-
of-the-art heuristic.
 References & Text Books
● [1] J. Son, A. V. Dastjerdi, R. N. Calheiros, and R. Buyya, “SLA-aware and energy-efficient dynamic
overbooking in SDN-based cloud data centers,” IEEE Transactions on Sustainable Computing, vol. 2, no. 2,
pp. 76–89, April 2017.

● [2] M. Al-Fares, A. Loukissas, and A. Vahdat, “A scalable, commodity data center network architecture,” in
Proceedings of the ACM SIGCOMM 2008 Conference on Data Communication. New York, NY, USA: ACM,
2008, pp. 63–74.

● [3] L. Popa, G. Kumar, M. Chowdhury, A. Krishnamurthy, S. Ratnasamy, and I. Stoica, “Faircloud: Sharing
the network in cloud computing,” in Proceedings of the ACM SIGCOMM 2012 Conference on Applications,
Technologies, Architectures, and Protocols for Computer Communication. New York, NY, USA: ACM, 2012,
pp. 187– 198.

● [4] B. Heller, S. Seetharaman, P. Mahadevan, Y. Yiakoumis, P. Sharma, S. Banerjee, and N. McKeown,

“Elastictree: Saving energy in data center networks,” in Proceedings of the 7th USENIX Conference on
Networked Systems Design and Implementation. Berkeley, CA, USA: USENIX Association, 2010, pp. 17–
17. [6] X. Wang, X. Wang, K. Zheng, Y. Yao, and Q. Cao, “Correlationaware traffic consolidation for power
optimization of data center networks,” IEEE Transactions on Parallel and Distributed Systems, vol. 27, no. 4,
pp. 992–1006, April 2016.
 Details regarding publications & patents

• Published My Research Paper By title Enabling Secure and

Effective Cloud Based Spatial Request.

• Published in International Journal of Scientific & Engineering

Research.
Thank you