24
國國國國國國國國國國國國國國國國 NTHU High-Speed Communication & Computing Laboratory Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing 101062558 國國國

Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

  • Upload
    aideen

  • View
    42

  • Download
    0

Embed Size (px)

DESCRIPTION

Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing. 101062558 劉冠逸. Outline. Introduction Problem description G enetic A lgorithm-based H euristic Algorithm (GAH) Simulations. Introduction. - PowerPoint PPT Presentation

Citation preview

Page 1: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

101062558 劉冠逸

Page 2: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Outline Introduction Problem description Genetic Algorithm-based Heuristic Algorithm

(GAH) Simulations

Page 3: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Introduction Cloud computing paradigm enables users to

access services and applications hosted in data centers based on their requirements.

The service or application request submitted to a data center can be abstracted as a virtual network (VN) request, which consists of a set of VN nodes and VN edges.

Page 4: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Virtual Network

Page 5: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Introduction How to efficiently provision VN requests in

multi datacenters is of utmost importance

For the elastic resource requirement services, providers need to make sure the QoS or SLAs are satisfied.

Page 6: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Problem description (I)

Page 7: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Problem description (II) For a provisioned VN request , we define the

gross income GI() as:

The cost C() of provisioning a VN request :

Page 8: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Problem description (III) The revenue R(GV) generated by provisioning a VN

request can be calculated as follows:

Page 9: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Greedy VN Provisioning Algorithm(GVNP) sss

Page 10: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Greedy VN Provisioning Algorithm(GVNP) sss

Page 11: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Genetic Algorithm-based Heuristic Algorithm (GAH)

Chromosome Coding Chromosome Operations Genetic Algorithm-based Heuristic Algorithm

(GAH)

Page 12: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Coding The number of columns in the array equals to the

number of server nodes in substrate network The total number of element “1” in the array equals

to the number of VN nodes in a VN request

Page 13: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Cloning Crossover Mutation Feasibility checking Selection

Page 14: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Cloning

The cloning operation involves generating theinitial population

The GA procedure begins its iterations from this population

Page 15: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Crossover

Page 16: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Mutation

The mutation operation is used to prevent solutions from being trapped at a local optimum

Mutation is done in the children population, by changing the values of some genes with a small probability pm (from 0.001 to 0.1)

Page 17: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Feasibility checking

Some of the newly generated children may not be feasible solutions for the original problem.

Page 18: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Chromosome Operations Selection

The chromosome selection is to select parent chromosomes from the particular generation of population, and assign reproductive opportunities to these selected chromosomes

Page 19: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Genetic Algorithm-based Heuristic Algorithm (GAH)

Page 20: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Simulations Use the ITALYNET (Figure 4) with 20 nodes and 36

links as substrate network in our simulation

Page 21: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Simulations

Page 22: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Simulations

Page 23: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

Conclusion In this work we address the problem of optimal

provisioning for elastic service oriented VN request in cloud-based datacenters.

We model this problem as a mathematical optimization problem by using mixed integer programming and propose a genetic algorithm based heuristic algorithm for solving this NP-hard problem efficiently.

The experimental results demonstrate that the solution obtained by our approach is near to the optimal solution

Page 24: Optimal Provisioning for Elastic Service Oriented Virtual Network Request in Cloud Computing

國立清華大學高速通訊與計算實驗室NTHU High-Speed Communication & Computing Laboratory

The End