A complex network approach to cloud computing

Cloud computing has become an important means to speed up computing. One problem influencing heavily the performance of such systems is the choice of nodes as servers responsible for executing the users' tasks. In this article we report how complex networks can be used to model such a problem. More specifically, we investigate the performance of the processing respectively to cloud systems underlain by Erdos-Renyi and Barabasi-Albert topology containing two servers. Cloud networks involving two communities not necessarily of the same size are also considered in our analysis. The performance of each configuration is quantified in terms of two indices: the cost of communication between the user and the nearest server, and the balance of the distribution of tasks between the two servers. Regarding the latter index, the ER topology provides better performance than the BA case for smaller average degrees and opposite behavior for larger average degrees. With respect to the cost, smaller values are found in the BA topology irrespective of the average degree. In addition, we also verified that it is easier to find good servers in the ER than in BA. Surprisingly, balance and cost are not too much affected by the presence of communities. However, for a well-defined community network, we found that it is important to assign each server to a different community so as to achieve better performance.

[1]  Carlos A. Ruggiero,et al.  Complex grid computing , 2003, cond-mat/0312603.

[2]  Andre Franceschi de Angelis,et al.  ON THE EFFECTS OF GEOGRAPHICAL CONSTRAINTS ON TASK EXECUTION IN COMPLEX NETWORKS , 2007 .

[3]  Bernardo A. Huberman,et al.  E-Mail as Spectroscopy: Automated Discovery of Community Structure within Organizations , 2005, Inf. Soc..

[4]  Pierre Baldi,et al.  Modeling the Internet and the Web: Probabilistic Methods and Algorithms: Baldi/Probabilistic , 2002 .

[5]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[6]  Alan M. Frieze,et al.  Random graphs , 2006, SODA '06.

[7]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[8]  Hong Liu,et al.  Energy proportional datacenter networks , 2010, ISCA.

[9]  Keqing He,et al.  A qualitative method for measuring the structural complexity of software systems based on complex networks , 2005, 12th Asia-Pacific Software Engineering Conference (APSEC'05).

[10]  Bernardo A. Huberman,et al.  Email as spectroscopy: automated discovery of community structure within organizations , 2003 .

[11]  Luciano da Fontoura Costa,et al.  Predicting efficiency in master-slave grid computing systems , 2012, J. Complex Networks.

[12]  Ahmed El-Mahdy,et al.  Network Topology Identification for Cloud Instances , 2013, 2013 International Conference on Cloud and Green Computing.

[13]  Michalis Faloutsos,et al.  On power-law relationships of the Internet topology , 1999, SIGCOMM '99.

[14]  Francisco Prieto Castrillo,et al.  A Stochastic Process Approach to Model Distributed Computing on Complex Networks , 2014, Journal of Grid Computing.

[15]  Luciano da Fontoura Costa,et al.  Effective networks for real-time distributed processing , 2006, J. Syst. Sci. Complex..

[16]  L. da F. Costa,et al.  Characterization of complex networks: A survey of measurements , 2005, cond-mat/0505185.