A Graph-Based Mathematical Model for an Efficient Load Balancing and Fault Tolerance in Cloud Computing

All the Cloud Data Centers (CDC) provision service ranging from compute to storage. The rate of service accessed by the end users increases drastically. Hence, to deal with an ondemand dynamic loads, an efficient load balancing of resources such as hosts and virtual machines in the CDC becomes necessary. This paper proposes a load balancing technique based on a graph structure called weighted complete graph augmented with dominating set concept for the CDC is proposed. A mathematical model is devised and the proposed method improves utilization of resources in CDC by load balancing and also enables fault tolerance.

[1]  Kang-Won Lee,et al.  Minimum Congestion Mapping in a Cloud , 2015, SIAM J. Comput..

[2]  Gaochao Xu,et al.  A Load Balancing Model Based on Cloud Partitioning for the Public Cloud , 2013 .

[3]  Robert Shorten,et al.  Stratus: Load Balancing the Cloud for Carbon Emissions Control , 2013, IEEE Transactions on Cloud Computing.

[4]  Stefano Battiston,et al.  From Graph Theory to Models of Economic Networks. A Tutorial. , 2008 .

[5]  Yacine Rezgui,et al.  A broker based consumption mechanism for social clouds , 2014, CloudCom 2014.

[6]  Ling Liu,et al.  Efficient data partitioning model for heterogeneous graphs in the cloud , 2013, 2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC).

[7]  R. Kanniga Devi,et al.  A graph and connected dominating set-based mathematical model for task mapping in cloud computing , 2016, 2016 International Conference on Information Communication and Embedded Systems (ICICES).

[8]  Mohammad S. Obaidat,et al.  A cluster-based load balancing algorithm in cloud computing , 2014, 2014 IEEE International Conference on Communications (ICC).

[9]  Narander Kumar,et al.  Self regulatory graph based model for managing VM migration in cloud data centers , 2014, 2014 IEEE International Advance Computing Conference (IACC).