load balancing in cloud computing newppt
TRANSCRIPT
Utshab Saha, Avijit Podder, Hillol Dhar, Shubrahjoity Paul
Under the guidance of: Prof. Santanu DamGROUP NO.:- 5
Topics
Introduction
Introduction
• Principles followed by Cloud Computing.• Resource Pooling.• Virtualization.• Elasticity.• Automatic resource deployment.• Metered Billing.
Cloud
Actual
resources
Background
BackgroundCloud component
• Cloud client platforms.• Thick client.• Thin client.• Zero client.(Ultra thin)
Cloud server
Thin clientThin client
Intern
et
Thick clientThick clientInternet
BackgroundCloud component
• Cloud Storage• Public cloud.• Private cloud.• Community cloud.• Hybrid cloud.
Public cloud
R1
R2
R3
Shared resourceShared resource
UB 1
UB 2
UB 3
UB 4
Private cloud
R1
R2
R3
UB 1/Org 1UB 2/Org 1
Private resourcePrivate resource
BackgroundCloud component
• Cloud Network• High bandwidth(low latency).• Agile network.• Network security.
Background
Background
• Deployment.• Public cloud.• Private cloud.• Community cloud.• Hybrid cloud.
Public
Background
• Deployment.• Public cloud.• Private cloud.• Community cloud.• Hybrid cloud.
Private
Background
• Deployment.• Public cloud.• Private cloud.• Community cloud.• Hybrid cloud.
Community
Background
• Deployment.• Public cloud.• Private cloud.• Community cloud.• Hybrid cloud.
Hybrid
Background
• Load balancing.• Type of load balancing.• Static.• Dynamic.
• Need of load balancing.• Improving the performance.• Maintaining the system stability.• Quality of services.(QoS)• Building fault tolerance.
Algorithm Survey from several Literature
• Proposed several load balancing algorithms• Scheduling algorithms.• Round Robin.• FCFS.
• Soft computing based algorithms.• Stochastic algorithm.[1]• Genetic algorithm.[2]• Ant colony optimization algorithm.[3]
Algorithm Survey from several Literature
From: Dam santanu et. Al. 2015 C3IT
Proposed work
• Our proposed algorithm.• VM allocation optimization using Simulated annealing.
• Host Side optimization.
• Target.• Balancing load of the virtual nodes and reducing Response Time(RT).
• Progress with the project.• Using Cloud Sim simulated Data Centers, Virtual Machines, Cloudlets.
• Virtually distributed the load.
Proposed work
• Progress with project.
Proposed work
• Our next move.• Migrating to Cloud Analyst and implementing our
proposed algorithm.
OUR WORK
• The two algorithms implemented are 1) ROUND ROBIN. 2)FCFS. 3)SIMULATED ANNEALING
• Round robin is the scheduling algorithm used by the CPU during execution of the process.• All processes in this algorithm are kept in the circular
queue also known as ready queue.• By using this algorithm, CPU makes sure, time slices
( any natural number ) are assigned to each process in equal portions and in circular order
IMPLEMENTING ROUND ROBIN
public int getNextAvailableVm(){ currVm++; if (currVm >= vmStatesList.size()){ currVm = 0; } allocatedVm(currVm); return currVm; }
RESULT OF ROUND ROBIN ALGORITHM
RESULT OF ROUND ROBIN ALGORITHM
First Come First Serve
• First come, first served (FCFS) is an operating system process scheduling algorithm and a network routing management mechanism.•With first come, first served, what comes first is handled
first.• The next request in line will be executed once the one
before it is complete.
IMPLEMENTING FCFS
public int getNextAvailableVm() { int temp=-1; if(vmStatesList.size()>0) { for (Iterator<Integer> itr = vmStatesList.keySet().iterator(); itr.hasNext();) { temp = itr.next(); VirtualMachineState state = vmStatesList.get(temp); if(state.equals(VirtualMachineState.AVAILABLE)){ allocatedVm(temp); break; } } } return temp; }
RESULT OF FCFS ALGORITM
RESULT OF FCFS ALGORITM
Simulated Annealing
• Simulated annealing (SA) is a probabilistic technique.• VMs are assigned to have probability which tells availability of
VMs.• Then using function call we checked highest probability and
selected the VM.• Accordingly decremented the probability.
Implementation of Simulated Annealing
•Probability Data Structure static float[][] anArrayOfFloats = new float[2][999999]; //probability array
•Implementationprivate float getHighProbability(){
float high_probability = anArrayOfFloats[1][0];for(int i = 1; i<vmStatesList.size(); i++) {if(high_probability<anArrayOfFloats[1][i])
high_probability = anArrayOfFloats[1][i];}return high_probability;
}
Result of Simulated Annealing
COMPARISON STUDY
Algorithms
Over All Response Time Data Center Processing Time
Avg(ms) Min(ms) Max(ms) Avg(ms) Min(ms) Max(ms)Round Robin
300.06 237.06 369.12 0.34 0.02 0.61
FCFS 300.09 237.06 369.12 0.38 0.08 4.5Simulated Annealing
297.87 271.61 346.62 0.48 0.10 0.61
Checks best Host
according to
Fitness
VM requested for Host
VM queueHost 1Host 2
.
.
.Host n
Host Side Optimization
Data center
Host information
Request for Host Info
Best Host
Request for Host
Request for Host
Best Host
Our proposed algorithm to optimize Host selection is Genetic Algorithm
References
[1] Avani Kansara, Ronak Patel et al. “A Various Load Balancing Techniques and Challenges in Cloud Computing – Survey ” International Journal for Scientific Research & Development Vol. 2, Issue 10, 2014 ISSN (online): 2321-0613 [2] Dasgupta, Kousik et al. "A Genetic Algorithm (GA) Based Load Balancing Strategy For Cloud Computing". Procedia Technology 10 (2013): 340-347. Web.[3] Santanu Dam 1, Gopa Mandal2, Kousik Dasgupta3, Paramartha Dutta4 et al. “An Ant Colony Based Load Balancing Strategy in Cloud Computing “. Advanced Computing, Networking and Informatics Volume 2 Smart Innovation, Systems and Technologies Volume 28, 2014, pp 403 413