A Preferential Attachment Model for Efficient Resources Selection in Distributed Computing Environments
In the last decade, Complex Network theory has been applied in many disciplines to solve a wide range of problems. Most social, biological and technological networks are modelled as complex networks from their topology point of view.
In this regard, an Efficient Resources Selection (ERS) model was proposed in a previous work to solve the resources selection problem in grid environment (i.e. to find a suitable resource set for grid applications). In this model, the infrastructure resources are considered nodes of a complex network that evolves during application execution. On the other hand, the edges represent the interaction between resources during the tasks execution. Besides, within the selection process the Preferential Attachment technique (Barabási and Réka, Science, 286(5439):509–512, 1999) is applied to determine the most efficient resources. This efficiency parameter is calculated using both resources degree and fitness values.
In the present contribution, a summary of this ERS model along with an analysis of its relevance parameters is exposed. The obtained results are also discussed.
KeywordsComplex systems Self-adaptive applications Grid computing Optimization
María Botón-Fernández is supported by the PhD research grant of the Spanish Ministry of Economy and Competitiveness at the Research Centre for Energy, Environment and Technology (CIEMAT). The authors would also like to acknowledge the support of the European Funds for Regional Development.
- 3.Foster I, Kesselman C, Tuecke S (2001) The anatomy of the grid. Enabling scalable virtual organizations. In: Sakellariou R, Keane JA, Gurd JR, Freeman L (eds) Euro-Par 2001. LNCS, vol 2150. Springer, Heidelberg, pp 1–4 Google Scholar
- 4.Botón-Fernández M, Prieto Castrillo F, Vega-Rodríguez MA (2011) Self-adaptive deployment of parametric sweep applications through a complex networks perspective. In: Proceedings of the 2011 international conference on computational science and its applications: Part II. ICCSA’11. LNCS, vol 6783. Springer, Heidelberg, pp 475–489 Google Scholar
- 5.The National Grid Initiative for Spain. http://www.es-ngi.es/