SlideShare uma empresa Scribd logo
1 de 31
ENERGY EFFICIENT AND TRAFFIC
AWARE VIRTUAL MACHINE
MANAGEMENT IN CLOUD COMPUTING
PROJECT ADVISOR :
Dr. Melody Moh
COMMITTEE MEMBERS :
Dr. Robert Chun
Mr. Giridhar Jayavelu
SWETHA KOGATAM
 INTRODUCTION
 PROBLEM & SOLUTION
 MAIN ALGORITHMS
 RESULTS
 CONCLUSION & FUTURE STUDIES
 Cloud computing has revolutionized the technology industry by enabling on-
demand provisioning of elastic computing resources
 Funded by Google, Lawrence Berkeley National Laboratory investigated the
energy impact of cloud computing
Cloud data centers still consume huge amounts of electrical energy resulting in
 High Operating Costs
 Carbondioxide (CO2) emissions
 Energy consumption by data centers worldwide has risen
by 56% from 2005 to 2010
 Around 1.1% - 1.5% of the global electricity usage in 2010
 INTRODUCTION
PROBLEM & SOLUTION
 MAIN ALGORITHMS
 RESULTS
 CONCLUSION & FUTURE STUDIES
Problem :
Need for the cloud data centers to reduce the power consumption to
save the costs and reduce CO2 emissions
How can this be solved ?
 CPU Utilization is the only dynamic resource
Focusing on optimizing the resource allocation and utilization
But..Performance is not relied only on CPU Utilization
With applications that require high communication, the communication cost
can influence the overall performance.
Ex: 3- Tier Web Application
One of the solutions to improve the effective utilization of resources and reduce
energy consumption is “Dynamic consolidation of Virtual Machines”
We propose the dynamic consolidation of virtual machines which
considers both the traffic and power among the VMs by keeping
the SLA violations at its lowest possible
Beloglazov has proposed the Dynamic VM consolidation algorithms
based on the analysis of historical data of the resource usage by VMs.
The whole dynamic consolidation problem is broken down into 4 small
problems i.e.,
1. Host Underload detection
2. Host Overload detection
3. VM Selection
4. Placement algorithms
Recently Huang , Wu and Moh has extended the work of Beloglazov
and proposed new dynamic VM consolidation heuristics and proposed :
 Least increase in Power by sorting the Hosts as placement policy
 Best Fit Host allocation policy
 Best fit VM allocation policy
Trong Vu also extended the work of Beloglazov and proposed a
mechanism considering power and the communication latency between
the VMs
 But considered only the VMs from underutilized hosts and not the over
utilized hosts.
 INTRODUCTION
 PROBLEM & SOLUTION
MAIN ALGORITHMS
 RESULTS
 CONCLUSION & FUTURE STUDIES
1. Developed clustering mechanims to cluster the VMs based on the
communication/traffic factor
2. Enhanced the existing Least Increase in Power with Host Sort allocation
policy by implementing the clustering mechanism – LIP-VMCL (HostSort)
3. Adopted and enhanced two VM placement heuristics , the Best Fit Host for
the VMClusters (BFH-VMCL) and the Best Fit VMClusters (BF-VMCL)
placement algorithms
4. Developed a new dynamic mechanism to create new hosts
1. A mechanism to find the over utilized hosts and underutilized hosts based on
the CPU utilization
2. A selection policy which selects the VM clusters to be migrated
3. Three different allocation policies
I. Least Increase in Power with Host Sort Allocation policy
II. Best Fit Host for VM Clusters Allocation policy
III. Best Fit VM Cluster Allocation policy.
4. Designed a dynamic mechanism to create a new host
LEAST INCREASE IN POWER WITH HOST SORT FOR VM
CLUSTERS : LIP_VMCL(HOST SORT)
Input : Migrating VM list , AvailableHostList
Step1 : Sort hosts in descending order of current CPU utilization and select the
VMs to be migrated
Step 2 : Cluster the VMs using VM Clustering algorithm
Step 3 : Calculate and store the increased power of the host by allocating the
VMCluster
Step 4 : Find the host with the least increase in power
Output : Migration Map
Input : Migrating VM list , AvailableHostList
Step1 : Sort hosts in descending order of current CPU utilization and select the
VMs to be migrated
Step 2 : Cluster the VMs using VM Clustering algorithm
Step 3 : Calculate predicted utilization of the host if that VM Cluster is allocated
using local regression method.
Step 4 : Find the host with the highest predicted utilization (and <1)
Output : Migration Map
Input : Migrating VM list , AvailableHostList
Step1 : Sort hosts in descending order of current CPU utilization and select the
VMs to be migrated
Step 2 : Cluster the VMs using VM Clustering algorithm
Step 3 : Find optimal combination of VMClusters for that host using dynamic
programming.
Output : Migration Map
 Step 1: Finding over-utilized and underutilized hosts
If host is over-utilized then
 Step 2: Select the VMs to be migrated from over-utilized hosts and use VM
Clustering Algorithm to cluster the VMs
 Step 3: Select the VMCluster(s) to be migrated from Migrating VMCluster List
using VMCluster Selection algorithm
 Step 4: Placement of VMCluster(s) from over-utilized hosts to Available host(s)
using Energy and Traffic aware VM Placement algorithm
 Step 5: Find the most under-utilized host and select all VMs from that host and
generate VMCluster(s) using VMClustering Algorithm
 Step 6: Placement of VMCluster(s) from the under-utilized host to other host(s)
using Energy and Traffic aware VM placement algorithm
 INTRODUCTION
 PROBLEM & SOLUTION
 MAIN ALGORITHMS
RESULTS
 CONCLUSION & FUTURE STUDIES
 INTRODUCTION
 PROBLEM & SOLUTION
 MAIN ALGORITHMS
 RESULTS
CONCLUSION & FUTURE STUDIES
 Number of migrated VMs reduced significantly for BFH_VMCL and
BFV_VMCL compared to LIP-HostSort_VMCL.
 The SLA violations reduced by almost 50%.
 BFH_VMCL has performed better considering minimal SLA violations and
better efficiency in terms of energy.
 BFV_VMCL is the best energy efficiency model at the price of high SLA
violations.
 Further work can be concentrated on improving the algorithms considering
the Storage IOPS
 Further research can be done towards the betterment of BF_VMCL algorithm
to reduce the SLA Violations
 Current approach is not yet implemented in real time data centers. The real
time situations might demand different kind of approaches.
This can be considered as potential future work towards an efficient green
cloud computing solution.
CS298_presentation
CS298_presentation

Mais conteúdo relacionado

Mais procurados

Resource provisioning optimization in cloud computing
Resource provisioning optimization in cloud computingResource provisioning optimization in cloud computing
Resource provisioning optimization in cloud computingMasoumeh_tajvidi
 
Job sequence scheduling for cloud computing
Job sequence scheduling for cloud computingJob sequence scheduling for cloud computing
Job sequence scheduling for cloud computingSamruddhi Gaikwad
 
33. dynamic resource allocation using virtual machines
33. dynamic resource allocation using virtual machines33. dynamic resource allocation using virtual machines
33. dynamic resource allocation using virtual machinesmuhammed jassim k
 
The Potential of cloud computing in accelerating the search for curing seriou...
The Potential of cloud computing in accelerating the search for curing seriou...The Potential of cloud computing in accelerating the search for curing seriou...
The Potential of cloud computing in accelerating the search for curing seriou...Mãrwã MãrwØùt'ã
 
Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...IEEEFINALYEARPROJECTS
 
MSIT Research Paper on Power Aware Computing in Clouds
MSIT Research Paper on Power Aware Computing in CloudsMSIT Research Paper on Power Aware Computing in Clouds
MSIT Research Paper on Power Aware Computing in CloudsAsiimwe Innocent Mudenge
 
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUD
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUDG-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUD
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUDAlfiya Mahmood
 
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...ijceronline
 
Energy aware load balancing and application scaling for the cloud ecosystem
Energy aware load balancing and application scaling for the cloud ecosystemEnergy aware load balancing and application scaling for the cloud ecosystem
Energy aware load balancing and application scaling for the cloud ecosystemLeMeniz Infotech
 
Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...IEEEFINALYEARPROJECTS
 
Challenges of cloud final
Challenges of cloud finalChallenges of cloud final
Challenges of cloud finalAbdul Aslam
 
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...SaikiranReddy Sama
 
A Survey on Resource Allocation & Monitoring in Cloud Computing
A Survey on Resource Allocation & Monitoring in Cloud ComputingA Survey on Resource Allocation & Monitoring in Cloud Computing
A Survey on Resource Allocation & Monitoring in Cloud ComputingMohd Hairey
 
dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...Kumar Goud
 
Green cloud computing
Green cloud computingGreen cloud computing
Green cloud computingPbvn Prasad
 
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALAGREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALASaikiran Panjala
 
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTING
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTINGRESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTING
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTINGSathmica K
 

Mais procurados (19)

Resource provisioning optimization in cloud computing
Resource provisioning optimization in cloud computingResource provisioning optimization in cloud computing
Resource provisioning optimization in cloud computing
 
Job sequence scheduling for cloud computing
Job sequence scheduling for cloud computingJob sequence scheduling for cloud computing
Job sequence scheduling for cloud computing
 
33. dynamic resource allocation using virtual machines
33. dynamic resource allocation using virtual machines33. dynamic resource allocation using virtual machines
33. dynamic resource allocation using virtual machines
 
The Potential of cloud computing in accelerating the search for curing seriou...
The Potential of cloud computing in accelerating the search for curing seriou...The Potential of cloud computing in accelerating the search for curing seriou...
The Potential of cloud computing in accelerating the search for curing seriou...
 
Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...
 
MSIT Research Paper on Power Aware Computing in Clouds
MSIT Research Paper on Power Aware Computing in CloudsMSIT Research Paper on Power Aware Computing in Clouds
MSIT Research Paper on Power Aware Computing in Clouds
 
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUD
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUDG-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUD
G-SLAM:OPTIMIZING ENERGY EFFIIENCY IN CLOUD
 
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...
Efficient Resource Allocation to Virtual Machine in Cloud Computing Using an ...
 
Energy aware load balancing and application scaling for the cloud ecosystem
Energy aware load balancing and application scaling for the cloud ecosystemEnergy aware load balancing and application scaling for the cloud ecosystem
Energy aware load balancing and application scaling for the cloud ecosystem
 
Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...Dynamic resource allocation using virtual machines for cloud computing enviro...
Dynamic resource allocation using virtual machines for cloud computing enviro...
 
Scheduling in CCE
Scheduling in CCEScheduling in CCE
Scheduling in CCE
 
Challenges of cloud final
Challenges of cloud finalChallenges of cloud final
Challenges of cloud final
 
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...
Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Enviro...
 
A Survey on Resource Allocation & Monitoring in Cloud Computing
A Survey on Resource Allocation & Monitoring in Cloud ComputingA Survey on Resource Allocation & Monitoring in Cloud Computing
A Survey on Resource Allocation & Monitoring in Cloud Computing
 
dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...dynamic resource allocation using virtual machines for cloud computing enviro...
dynamic resource allocation using virtual machines for cloud computing enviro...
 
Green cloud computing
Green cloud computingGreen cloud computing
Green cloud computing
 
Green cloud computing
Green  cloud computingGreen  cloud computing
Green cloud computing
 
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALAGREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
GREEN CLOUD COMPUTING BY SAIKIRAN PANJALA
 
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTING
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTINGRESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTING
RESOURCE ALLOCATION AND STORAGE IN MOBILE USING CLOUD COMPUTING
 

Destaque

SAS Cloud Computing and MapReduce
SAS Cloud Computing and MapReduceSAS Cloud Computing and MapReduce
SAS Cloud Computing and MapReduceDaqing Zhao
 
0324663854 151818
0324663854 1518180324663854 151818
0324663854 151818Nhu Le
 
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...Susheel Thakur
 
Big Data Analysis and Business Intelligence
Big Data Analysis and Business IntelligenceBig Data Analysis and Business Intelligence
Big Data Analysis and Business IntelligenceDaqing Zhao
 
Long arm supervision models
Long arm supervision modelsLong arm supervision models
Long arm supervision modelsJanet Thomas
 
A Survey on Virtualization Data Centers For Green Cloud Computing
A Survey on Virtualization Data Centers For Green Cloud ComputingA Survey on Virtualization Data Centers For Green Cloud Computing
A Survey on Virtualization Data Centers For Green Cloud ComputingIJTET Journal
 
A survey on live virtual machine migrations and its techniques
A survey on live virtual machine migrations and its techniquesA survey on live virtual machine migrations and its techniques
A survey on live virtual machine migrations and its techniquesAlexander Decker
 
Rapid Survey on Routing in Data Centers
Rapid Survey on Routing in Data CentersRapid Survey on Routing in Data Centers
Rapid Survey on Routing in Data CentersGhazal Tashakor
 
Open / Free Cloud platforms and Open Hardware Systems
Open / Free Cloud platforms and Open Hardware SystemsOpen / Free Cloud platforms and Open Hardware Systems
Open / Free Cloud platforms and Open Hardware SystemsCharalampos Doukas
 
Memory forensics using VMI for cloud computing
Memory forensics using VMI for cloud computingMemory forensics using VMI for cloud computing
Memory forensics using VMI for cloud computingPriyanka Aash
 

Destaque (20)

cloud computing ppt
cloud computing pptcloud computing ppt
cloud computing ppt
 
VM placement
VM placementVM placement
VM placement
 
SAS Cloud Computing and MapReduce
SAS Cloud Computing and MapReduceSAS Cloud Computing and MapReduce
SAS Cloud Computing and MapReduce
 
Salsa roots engl
Salsa roots englSalsa roots engl
Salsa roots engl
 
UEDA Annual Summit 2016: Virginia Tech; Same Ecosystem, Different Entrepreneurs
UEDA Annual Summit 2016: Virginia Tech; Same Ecosystem, Different EntrepreneursUEDA Annual Summit 2016: Virginia Tech; Same Ecosystem, Different Entrepreneurs
UEDA Annual Summit 2016: Virginia Tech; Same Ecosystem, Different Entrepreneurs
 
Cartão branco
Cartão brancoCartão branco
Cartão branco
 
Funcion de la luna
Funcion de la lunaFuncion de la luna
Funcion de la luna
 
T3 Selecting a Target Audience
T3 Selecting a Target AudienceT3 Selecting a Target Audience
T3 Selecting a Target Audience
 
0324663854 151818
0324663854 1518180324663854 151818
0324663854 151818
 
Estadistica
EstadisticaEstadistica
Estadistica
 
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...
A Study on Energy Efficient Server Consolidation Heuristics for Virtualized C...
 
Big Data Analysis and Business Intelligence
Big Data Analysis and Business IntelligenceBig Data Analysis and Business Intelligence
Big Data Analysis and Business Intelligence
 
Long arm supervision models
Long arm supervision modelsLong arm supervision models
Long arm supervision models
 
Empresa MIACTIVEWEAR grupo 6A
Empresa MIACTIVEWEAR grupo 6AEmpresa MIACTIVEWEAR grupo 6A
Empresa MIACTIVEWEAR grupo 6A
 
A Survey on Virtualization Data Centers For Green Cloud Computing
A Survey on Virtualization Data Centers For Green Cloud ComputingA Survey on Virtualization Data Centers For Green Cloud Computing
A Survey on Virtualization Data Centers For Green Cloud Computing
 
A survey on live virtual machine migrations and its techniques
A survey on live virtual machine migrations and its techniquesA survey on live virtual machine migrations and its techniques
A survey on live virtual machine migrations and its techniques
 
Rapid Survey on Routing in Data Centers
Rapid Survey on Routing in Data CentersRapid Survey on Routing in Data Centers
Rapid Survey on Routing in Data Centers
 
Open / Free Cloud platforms and Open Hardware Systems
Open / Free Cloud platforms and Open Hardware SystemsOpen / Free Cloud platforms and Open Hardware Systems
Open / Free Cloud platforms and Open Hardware Systems
 
Memory forensics using VMI for cloud computing
Memory forensics using VMI for cloud computingMemory forensics using VMI for cloud computing
Memory forensics using VMI for cloud computing
 
Resource scheduling
Resource schedulingResource scheduling
Resource scheduling
 

Semelhante a CS298_presentation

A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...
A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...
A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...IRJET Journal
 
IEEE Paper Presentation by Chandan Kumar
IEEE Paper Presentation by Chandan KumarIEEE Paper Presentation by Chandan Kumar
IEEE Paper Presentation by Chandan KumarChandan Kumar
 
Virtual machine consolidation for balanced resource utilisation and energy ef...
Virtual machine consolidation for balanced resource utilisation and energy ef...Virtual machine consolidation for balanced resource utilisation and energy ef...
Virtual machine consolidation for balanced resource utilisation and energy ef...SuvomDas
 
CNR @ VMUG.IT 20150304
CNR @ VMUG.IT 20150304CNR @ VMUG.IT 20150304
CNR @ VMUG.IT 20150304VMUG IT
 
Load Balancing in Cloud Computing Through Virtual Machine Placement
Load Balancing in Cloud Computing Through Virtual Machine PlacementLoad Balancing in Cloud Computing Through Virtual Machine Placement
Load Balancing in Cloud Computing Through Virtual Machine PlacementIRJET Journal
 
INTECHDublinConference-247-camera-ready
INTECHDublinConference-247-camera-readyINTECHDublinConference-247-camera-ready
INTECHDublinConference-247-camera-readyKieran Flesk
 
Optimal load balancing in cloud computing
Optimal load balancing in cloud computingOptimal load balancing in cloud computing
Optimal load balancing in cloud computingPriyanka Bhowmick
 
Vm Management For Green It Data Centers
Vm Management For Green It Data CentersVm Management For Green It Data Centers
Vm Management For Green It Data CentersIgnacio M. Llorente
 
Server Consolidation through Virtual Machine Task Migration to achieve Green ...
Server Consolidation through Virtual Machine Task Migration to achieve Green ...Server Consolidation through Virtual Machine Task Migration to achieve Green ...
Server Consolidation through Virtual Machine Task Migration to achieve Green ...IJCSIS Research Publications
 
Virtual machine placement in cloud using artificial bee colony and imperiali...
Virtual machine placement in cloud using artificial bee colony  and imperiali...Virtual machine placement in cloud using artificial bee colony  and imperiali...
Virtual machine placement in cloud using artificial bee colony and imperiali...IJECEIAES
 
Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...Papitha Velumani
 
LOAD BALANCING IN CLOUD COMPUTING
LOAD BALANCING IN CLOUD COMPUTINGLOAD BALANCING IN CLOUD COMPUTING
LOAD BALANCING IN CLOUD COMPUTINGIRJET Journal
 
Load Balancing traffic in OpenStack neutron
Load Balancing traffic in OpenStack neutron Load Balancing traffic in OpenStack neutron
Load Balancing traffic in OpenStack neutron sufianfauzani
 
Distributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesDistributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesPapitha Velumani
 
Distributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesDistributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesPapitha Velumani
 
Migration Control in Cloud Computing to Reduce the SLA Violation
Migration Control in Cloud Computing to Reduce the SLA ViolationMigration Control in Cloud Computing to Reduce the SLA Violation
Migration Control in Cloud Computing to Reduce the SLA Violationrahulmonikasharma
 
A New QoS Renegotiation Mechanism for Multimedia Applications
A New QoS Renegotiation Mechanism for Multimedia ApplicationsA New QoS Renegotiation Mechanism for Multimedia Applications
A New QoS Renegotiation Mechanism for Multimedia ApplicationsABDELAAL
 
The Role of Elastic Load Balancer - Apache Stratos
The Role of Elastic Load Balancer - Apache StratosThe Role of Elastic Load Balancer - Apache Stratos
The Role of Elastic Load Balancer - Apache StratosImesh Gunaratne
 

Semelhante a CS298_presentation (20)

kogatam_swetha
kogatam_swethakogatam_swetha
kogatam_swetha
 
A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...
A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...
A Host Selection Algorithm for Dynamic Container Consolidation in Cloud Data ...
 
IEEE Paper Presentation by Chandan Kumar
IEEE Paper Presentation by Chandan KumarIEEE Paper Presentation by Chandan Kumar
IEEE Paper Presentation by Chandan Kumar
 
Virtual machine consolidation for balanced resource utilisation and energy ef...
Virtual machine consolidation for balanced resource utilisation and energy ef...Virtual machine consolidation for balanced resource utilisation and energy ef...
Virtual machine consolidation for balanced resource utilisation and energy ef...
 
CNR @ VMUG.IT 20150304
CNR @ VMUG.IT 20150304CNR @ VMUG.IT 20150304
CNR @ VMUG.IT 20150304
 
Load Balancing in Cloud Computing Through Virtual Machine Placement
Load Balancing in Cloud Computing Through Virtual Machine PlacementLoad Balancing in Cloud Computing Through Virtual Machine Placement
Load Balancing in Cloud Computing Through Virtual Machine Placement
 
INTECHDublinConference-247-camera-ready
INTECHDublinConference-247-camera-readyINTECHDublinConference-247-camera-ready
INTECHDublinConference-247-camera-ready
 
Optimal load balancing in cloud computing
Optimal load balancing in cloud computingOptimal load balancing in cloud computing
Optimal load balancing in cloud computing
 
Vm Management For Green It Data Centers
Vm Management For Green It Data CentersVm Management For Green It Data Centers
Vm Management For Green It Data Centers
 
Server Consolidation through Virtual Machine Task Migration to achieve Green ...
Server Consolidation through Virtual Machine Task Migration to achieve Green ...Server Consolidation through Virtual Machine Task Migration to achieve Green ...
Server Consolidation through Virtual Machine Task Migration to achieve Green ...
 
Virtual machine placement in cloud using artificial bee colony and imperiali...
Virtual machine placement in cloud using artificial bee colony  and imperiali...Virtual machine placement in cloud using artificial bee colony  and imperiali...
Virtual machine placement in cloud using artificial bee colony and imperiali...
 
Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...
 
LOAD BALANCING IN CLOUD COMPUTING
LOAD BALANCING IN CLOUD COMPUTINGLOAD BALANCING IN CLOUD COMPUTING
LOAD BALANCING IN CLOUD COMPUTING
 
Homework2
Homework2Homework2
Homework2
 
Load Balancing traffic in OpenStack neutron
Load Balancing traffic in OpenStack neutron Load Balancing traffic in OpenStack neutron
Load Balancing traffic in OpenStack neutron
 
Distributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesDistributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databases
 
Distributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databasesDistributed, concurrent, and independent access to encrypted cloud databases
Distributed, concurrent, and independent access to encrypted cloud databases
 
Migration Control in Cloud Computing to Reduce the SLA Violation
Migration Control in Cloud Computing to Reduce the SLA ViolationMigration Control in Cloud Computing to Reduce the SLA Violation
Migration Control in Cloud Computing to Reduce the SLA Violation
 
A New QoS Renegotiation Mechanism for Multimedia Applications
A New QoS Renegotiation Mechanism for Multimedia ApplicationsA New QoS Renegotiation Mechanism for Multimedia Applications
A New QoS Renegotiation Mechanism for Multimedia Applications
 
The Role of Elastic Load Balancer - Apache Stratos
The Role of Elastic Load Balancer - Apache StratosThe Role of Elastic Load Balancer - Apache Stratos
The Role of Elastic Load Balancer - Apache Stratos
 

CS298_presentation

  • 1. ENERGY EFFICIENT AND TRAFFIC AWARE VIRTUAL MACHINE MANAGEMENT IN CLOUD COMPUTING PROJECT ADVISOR : Dr. Melody Moh COMMITTEE MEMBERS : Dr. Robert Chun Mr. Giridhar Jayavelu SWETHA KOGATAM
  • 2.  INTRODUCTION  PROBLEM & SOLUTION  MAIN ALGORITHMS  RESULTS  CONCLUSION & FUTURE STUDIES
  • 3.  Cloud computing has revolutionized the technology industry by enabling on- demand provisioning of elastic computing resources  Funded by Google, Lawrence Berkeley National Laboratory investigated the energy impact of cloud computing
  • 4. Cloud data centers still consume huge amounts of electrical energy resulting in  High Operating Costs  Carbondioxide (CO2) emissions  Energy consumption by data centers worldwide has risen by 56% from 2005 to 2010  Around 1.1% - 1.5% of the global electricity usage in 2010
  • 5.  INTRODUCTION PROBLEM & SOLUTION  MAIN ALGORITHMS  RESULTS  CONCLUSION & FUTURE STUDIES
  • 6. Problem : Need for the cloud data centers to reduce the power consumption to save the costs and reduce CO2 emissions How can this be solved ?  CPU Utilization is the only dynamic resource Focusing on optimizing the resource allocation and utilization But..Performance is not relied only on CPU Utilization
  • 7. With applications that require high communication, the communication cost can influence the overall performance. Ex: 3- Tier Web Application One of the solutions to improve the effective utilization of resources and reduce energy consumption is “Dynamic consolidation of Virtual Machines” We propose the dynamic consolidation of virtual machines which considers both the traffic and power among the VMs by keeping the SLA violations at its lowest possible
  • 8. Beloglazov has proposed the Dynamic VM consolidation algorithms based on the analysis of historical data of the resource usage by VMs. The whole dynamic consolidation problem is broken down into 4 small problems i.e., 1. Host Underload detection 2. Host Overload detection 3. VM Selection 4. Placement algorithms
  • 9. Recently Huang , Wu and Moh has extended the work of Beloglazov and proposed new dynamic VM consolidation heuristics and proposed :  Least increase in Power by sorting the Hosts as placement policy  Best Fit Host allocation policy  Best fit VM allocation policy Trong Vu also extended the work of Beloglazov and proposed a mechanism considering power and the communication latency between the VMs  But considered only the VMs from underutilized hosts and not the over utilized hosts.
  • 10.  INTRODUCTION  PROBLEM & SOLUTION MAIN ALGORITHMS  RESULTS  CONCLUSION & FUTURE STUDIES
  • 11. 1. Developed clustering mechanims to cluster the VMs based on the communication/traffic factor 2. Enhanced the existing Least Increase in Power with Host Sort allocation policy by implementing the clustering mechanism – LIP-VMCL (HostSort) 3. Adopted and enhanced two VM placement heuristics , the Best Fit Host for the VMClusters (BFH-VMCL) and the Best Fit VMClusters (BF-VMCL) placement algorithms 4. Developed a new dynamic mechanism to create new hosts
  • 12. 1. A mechanism to find the over utilized hosts and underutilized hosts based on the CPU utilization 2. A selection policy which selects the VM clusters to be migrated 3. Three different allocation policies I. Least Increase in Power with Host Sort Allocation policy II. Best Fit Host for VM Clusters Allocation policy III. Best Fit VM Cluster Allocation policy. 4. Designed a dynamic mechanism to create a new host
  • 13.
  • 14. LEAST INCREASE IN POWER WITH HOST SORT FOR VM CLUSTERS : LIP_VMCL(HOST SORT) Input : Migrating VM list , AvailableHostList Step1 : Sort hosts in descending order of current CPU utilization and select the VMs to be migrated Step 2 : Cluster the VMs using VM Clustering algorithm Step 3 : Calculate and store the increased power of the host by allocating the VMCluster Step 4 : Find the host with the least increase in power Output : Migration Map
  • 15. Input : Migrating VM list , AvailableHostList Step1 : Sort hosts in descending order of current CPU utilization and select the VMs to be migrated Step 2 : Cluster the VMs using VM Clustering algorithm Step 3 : Calculate predicted utilization of the host if that VM Cluster is allocated using local regression method. Step 4 : Find the host with the highest predicted utilization (and <1) Output : Migration Map
  • 16. Input : Migrating VM list , AvailableHostList Step1 : Sort hosts in descending order of current CPU utilization and select the VMs to be migrated Step 2 : Cluster the VMs using VM Clustering algorithm Step 3 : Find optimal combination of VMClusters for that host using dynamic programming. Output : Migration Map
  • 17.  Step 1: Finding over-utilized and underutilized hosts If host is over-utilized then  Step 2: Select the VMs to be migrated from over-utilized hosts and use VM Clustering Algorithm to cluster the VMs  Step 3: Select the VMCluster(s) to be migrated from Migrating VMCluster List using VMCluster Selection algorithm  Step 4: Placement of VMCluster(s) from over-utilized hosts to Available host(s) using Energy and Traffic aware VM Placement algorithm
  • 18.  Step 5: Find the most under-utilized host and select all VMs from that host and generate VMCluster(s) using VMClustering Algorithm  Step 6: Placement of VMCluster(s) from the under-utilized host to other host(s) using Energy and Traffic aware VM placement algorithm
  • 19.  INTRODUCTION  PROBLEM & SOLUTION  MAIN ALGORITHMS RESULTS  CONCLUSION & FUTURE STUDIES
  • 20.
  • 21.
  • 22.
  • 23.
  • 24.
  • 25.
  • 26.
  • 27.  INTRODUCTION  PROBLEM & SOLUTION  MAIN ALGORITHMS  RESULTS CONCLUSION & FUTURE STUDIES
  • 28.  Number of migrated VMs reduced significantly for BFH_VMCL and BFV_VMCL compared to LIP-HostSort_VMCL.  The SLA violations reduced by almost 50%.  BFH_VMCL has performed better considering minimal SLA violations and better efficiency in terms of energy.  BFV_VMCL is the best energy efficiency model at the price of high SLA violations.
  • 29.  Further work can be concentrated on improving the algorithms considering the Storage IOPS  Further research can be done towards the betterment of BF_VMCL algorithm to reduce the SLA Violations  Current approach is not yet implemented in real time data centers. The real time situations might demand different kind of approaches. This can be considered as potential future work towards an efficient green cloud computing solution.

Notas do Editor

  1. However, cloud data centers consume huge amounts of electrical energy resulting in high operating costs and carbon dioxide (CO2) emissions to the environment.
  2. CPU Utilization is the only resource which is provided dynamically according to the performance requirement, whereas the other resources are provided with fixed size Example: for a 3 tier web application, migrating an application server to a host far from the front end web server and the database server will increase the communication latency and thus reduce the overall throughput. One such example is non- overlap MPI applications which wait for messages before continuing
  3. One of the solutions to improve the effective utilization of resources and reduce energy consumption is “Dynamic consolidation of Virtual Machines” Non- overlap MPI applications which wait for messages before continuing
  4. Host overload and underload detection :Median Absolute Deviation , Local Regression and Robust Local Regression methods The VM Selection policies : minimum migration time and maximum correlation policies. VM Placement Algorithms are solved a NP hard problems and proposed Best Fit Decreasing algorithm
  5. Best Fit Host Algorithm in which the best fit host is found for the VMs to be migrated based on the predicted CPU history utilization Best fit VM allocation policy by choosing the optimal combination of VMs for the Hosts available using dynamic programming method. Trong Vu proposed a mechanism considering energy and the communication latency between the VMs as the factors to achieve the better results in energy efficiency .
  6. For each VMCluster in the VMCluster List check if each of the host from the AvailableHostListPartition is suitable for migration
  7. - For each VMCluster in the VMCluster List check if each of the host from the AvailableHostListPartition is suitable for migration. - If it is suitable then
  8. Proposed the clustering mechanism to cluster the VMs considering both the energy and traffic matrix and have implemented the four different allocation policies.