1 / 8

A Minimum Cost Resource Allocation Approach for Cloud Data Centers

A Minimum Cost Resource Allocation Approach for Cloud Data Centers. 指導教授:王國禎 學生 :連懷恩 國立交通大學資訊工程系 行動計算與寬頻網路實驗室. Outline. Introduction Related work Phase 1: A branch and bound algorithm Phase 2: A server/VM chain algorithm Conclusion. Introduction.

lei
Download Presentation

A Minimum Cost Resource Allocation Approach for Cloud Data Centers

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. A Minimum Cost Resource Allocation Approach for Cloud Data Centers 指導教授:王國禎 學生:連懷恩 國立交通大學資訊工程系 行動計算與寬頻網路實驗室

  2. Outline • Introduction • Related work • Phase 1: A branch and bound algorithm • Phase 2: A server/VM chain algorithm • Conclusion

  3. Introduction • Existing approaches only consider come aspects of resource allocation problem(e.g., either for VM or for server level) in cloud data center. • A complete resource allocation approach should include the following features: per application resource allocation, resizing on both VM and server level, transition cost, VM placement, and optimization over time domain. • Our goal is a minimum cost (optimal) resource allocation approach in cloud data center.

  4. Related Work

  5. A Branch and Bound Algorithm • We use a branch and bound algorithm to deal with the resizing problem of VMs and servers. • B&B can lead to an optimal solution but is usually in high complexity. In our modified version, we can make it more efficiently by introducing the break-even time condition and off-line migration. • The algorithm itself is finished, but we still need to prove a necessary condition to bound its complexity.

  6. A Server/VM Chain Algorithm • A chain representation of server/VM in space-time diagram. • We face some troubles in proving its optimality.

  7. Conclusion • The most complete resource allocation approach in cloud data center so far. • It is theoretically optimal if we succeed, however the actual results still heavily rely on the quality of prediction. • Some important necessary condition and optimality still needs to be proven.

  8. Hw2 - Hadoop • Setup the Hadoop environment on the virtual machines inherited from Hw1. • Modify the code from Hw1 to a multinodesHadoop version • Performance comparison between single node, multinodes.

More Related