Paper-7 QoS Provisioning of Cognitive Radio using Soft Computing Techniques – A Survey
Resource provisioning optimization in cloud computing
-
Upload
masoumehtajvidi -
Category
Technology
-
view
320 -
download
5
Transcript of Resource provisioning optimization in cloud computing
![Page 1: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/1.jpg)
Dynamic Optimization of Heterogeneous Resource Provisioning in Cloud Computing
Masoumeh Tajvidi
Supervisors: A/Prof. Michael MaherDr. Daryl Essam
School of Engineering and Information Technology (SEIT)
![Page 2: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/2.jpg)
• Introduction
- Cloud computing and its potential benefits
- Challenges!
• Research question
• Related Work
• Research Plan
• Preliminary Work
Outline
1/16
![Page 3: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/3.jpg)
What is Cloud Computing? A broad and deep platform that helps customers build
sophisticated, scalable applications
2/16
![Page 4: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/4.jpg)
Why are companies adopting cloud computing so quickly?
Agility
3/16
![Page 5: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/5.jpg)
Main benefits of utility-like computing
Convert CAPEX to OPEX
Lower Total Cost
No Need to Guess Capacity
Lower Maintenance Cost
4/16
![Page 6: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/6.jpg)
Effectively using of cloud computing
Over-provisioning: purchased resources are not fully utilized cost more than necessary
Under-provisioning: purchased resources are not sufficient to meet the actual demand hurts application performance,
5/16
![Page 7: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/7.jpg)
Efficient resource provisioning: challenge #1 : Various cloud providers offering
multiple Virtual Machine (VM) types
• Virtualization technologies help providers pack their hardware resources into different type of Virtual Machines
• The end-users encounter a complicated decision making problem for choosing the right mix of VMs!
6/16
![Page 8: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/8.jpg)
Efficient resource provisioning: challenge #2 : Multiple pricing models
7/16
![Page 9: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/9.jpg)
Efficient resource provisioning: challenge #3 : Deal with COST and DEMAND
uncertainty The application’s demand is not
known in advance• e.g. online video streaming
applications, like YouTube Channel
The cost of instances in both on-demand and spot is varying!
8/16
![Page 10: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/10.jpg)
Efficient resource provisioning: challenge #4 : Multi-objective problem
Cost is not the only objective for this problem
The trade-off among cost and QoS must also be
handled
For example response time is very critical in latency
sensitive applications , online gaming services, as
the users tend to be very impatient
9/16
![Page 11: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/11.jpg)
Research Question ?
How to dynamically optimize cloud resource provisioning plan as a multi-objective problem in
the real-world?
10/16
![Page 12: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/12.jpg)
Literature review
11/16
![Page 13: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/13.jpg)
stochastic optimization
The time at which parameters become known, divide the problem into stages
Main Question: what to decide in the first stage? Main question: how many VM to reserve Recourse: how to deal with under or over provisioning
Objective function is to minimize the expected cost
12/16
![Page 14: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/14.jpg)
Add complexities of the real-world problem into our model.
Take into account the heterogeneity of VM types
Take into account all three pricing schemes into our model
Solve the problem as a multi-objective optimization problem
Dealing with uncertainty by solving the problem with both
stochastic and approximate programming approaches
enhance the performance of the optimization problem by
using Machine Learning techniques
Research Plan : Big Picture
Challenge #1
Challenge #2
Challenge #4
Challenge #3
13/16
![Page 15: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/15.jpg)
Preliminary results
Replicated one of the available multi stage
programming approach
Modelled the problem in Stochastic MiniZinc
modelling language
Added spot-instance pricing model into our model
14/16
![Page 16: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/16.jpg)
Stochastic MiniZinc Model Results Before and After Adding Spot Instances
15/16
![Page 17: Resource provisioning optimization in cloud computing](https://reader033.fdocuments.us/reader033/viewer/2022061505/58ea95841a28ab983e8b661b/html5/thumbnails/17.jpg)
Thank you .