Cloud Computing
• The practice of using a network of remote
servers hosted on the Internet to store,
manage, and process data, rather than a
local server or a personal computer.
Characteristics
Service Model
Deployment Model
Challenges in Cloud Computing
 Security
 Efficient Load Balancing
 Performance Monitoring
 Consistent and Robust Service abstractions
 Resource Scheduling
 Scale and QoS management
 Requires a fast speed Internet connection
LOAD BALANCING
WHY?
Resource Utilization
Maximize Throughput
Minimize Response Time
Maintain system stability
Cost effectiveness
Scalability and flexibility
Priority
Classification
Load Balancing
Algorithm
Depending upon
system state
Static Dynamic
Distributed
Cooperative Non-cooperative
Centralized
Depending upon
process initiator
Sender Initiated
Receiver
Initiated
Symmetric
Metrics
Throughput
Fault Tolerance
Migration Time
Response Time
Scalability
Policies
● Information Policy
● Triggering Policy
● Transfer Policy
● Location Policy
● Selection Policy
Honeybee Foraging Behavior
 Nature-inspired algorithm for self-organization.
 Achieves global load balancing through local server
actions.
 Performance of the system is enhanced with
increased system diversity.
 Throughput is not increased with an increase in
system size.
 Best suited for the conditions where the diverse
population of service types is required.
Honeybee Foraging Behavior
Biased Random Sampling
• Distributed and scalable.
• Uses random sampling of the system domain to
achieve self-organization.
• Performance is improved with high and similar
population of resources.
• Performance is degraded with an increase in
population diversity.
Active Clustering
• Self-aggregation algorithm to optimize job
assignments by connecting similar services using local
re-wiring.
• The performance of the system is enhanced with high
resources thereby increasing the throughput.
• Throughput degraded with an increase in system
diversity.
Other Algorithms
1. Opportunistic Load Balancing: Attempt each
node keep busy, therefore does not consider the
present workload of each computer.
2. Compare and Balance: This algorithm is uses to
reach an equilibrium condition and manage
unbalanced systems load.
3. Round Robin: All the processes are divided
between all processors in a round robin order.
4. Randomized: A process can be handled by a
particular node n with a probability p.
Some Other Algorithms
5. Shortest Response Time First: Selects the job
with the shortest (expected) processing time first.
6. Lock-free multiprocessing solution: Improves
performance multicore environment by running
multiple load-balancing processes in one load
balancer.
7. Min-Min Algorithm.
8. Max-Min Algorithm.
Bibliography
● Mell, Peter and Grance, Tim, “The NIST definition of cloud
computing”, National Institute of Standards and
Technology, 2009,vol53, pages50, Mell2009.
● Haozheng Ren, Yihua Lan, and Chao Yin, “The Load
Balancing Algorithm in Cloud Computing Environment”,
IEEE, 2nd International Conference on Computer Science,
China 2012.
● N. S. Raghava and Deepti Singh,” Comparative Study
on Load Balancing Techniques in Cloud Computing”
OPEN JOURNAL OF MOBILE COMPUTING AND CLOUD
COMPUTING, In Press.
Thank You!

Load balancing in cloud

  • 2.
    Cloud Computing • Thepractice of using a network of remote servers hosted on the Internet to store, manage, and process data, rather than a local server or a personal computer.
  • 3.
  • 4.
  • 5.
  • 6.
    Challenges in CloudComputing  Security  Efficient Load Balancing  Performance Monitoring  Consistent and Robust Service abstractions  Resource Scheduling  Scale and QoS management  Requires a fast speed Internet connection
  • 7.
  • 8.
    WHY? Resource Utilization Maximize Throughput MinimizeResponse Time Maintain system stability Cost effectiveness Scalability and flexibility Priority
  • 9.
    Classification Load Balancing Algorithm Depending upon systemstate Static Dynamic Distributed Cooperative Non-cooperative Centralized Depending upon process initiator Sender Initiated Receiver Initiated Symmetric
  • 10.
  • 11.
    Policies ● Information Policy ●Triggering Policy ● Transfer Policy ● Location Policy ● Selection Policy
  • 12.
    Honeybee Foraging Behavior Nature-inspired algorithm for self-organization.  Achieves global load balancing through local server actions.  Performance of the system is enhanced with increased system diversity.  Throughput is not increased with an increase in system size.  Best suited for the conditions where the diverse population of service types is required.
  • 13.
  • 14.
    Biased Random Sampling •Distributed and scalable. • Uses random sampling of the system domain to achieve self-organization. • Performance is improved with high and similar population of resources. • Performance is degraded with an increase in population diversity.
  • 15.
    Active Clustering • Self-aggregationalgorithm to optimize job assignments by connecting similar services using local re-wiring. • The performance of the system is enhanced with high resources thereby increasing the throughput. • Throughput degraded with an increase in system diversity.
  • 16.
    Other Algorithms 1. OpportunisticLoad Balancing: Attempt each node keep busy, therefore does not consider the present workload of each computer. 2. Compare and Balance: This algorithm is uses to reach an equilibrium condition and manage unbalanced systems load. 3. Round Robin: All the processes are divided between all processors in a round robin order. 4. Randomized: A process can be handled by a particular node n with a probability p.
  • 17.
    Some Other Algorithms 5.Shortest Response Time First: Selects the job with the shortest (expected) processing time first. 6. Lock-free multiprocessing solution: Improves performance multicore environment by running multiple load-balancing processes in one load balancer. 7. Min-Min Algorithm. 8. Max-Min Algorithm.
  • 18.
    Bibliography ● Mell, Peterand Grance, Tim, “The NIST definition of cloud computing”, National Institute of Standards and Technology, 2009,vol53, pages50, Mell2009. ● Haozheng Ren, Yihua Lan, and Chao Yin, “The Load Balancing Algorithm in Cloud Computing Environment”, IEEE, 2nd International Conference on Computer Science, China 2012. ● N. S. Raghava and Deepti Singh,” Comparative Study on Load Balancing Techniques in Cloud Computing” OPEN JOURNAL OF MOBILE COMPUTING AND CLOUD COMPUTING, In Press.
  • 19.