Self-Adaptive Deployment of Parametric Sweep Applications through a Complex Networks Perspective

Botón-Fernández, María; Prieto‐Castrillo, Francisco; Vega‐Rodríguez, Miguel A.

doi:10.1007/978-3-642-21887-3_37

Cited by 5 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, step 5.3 includes the particular AI rules, which are described in the following subsections (these rules are applied to all resources ∈ R P α ). Specifically, we have developed three ERS versions: the first one is based on preferential attachment (ERS‐PA) , the second one is based on the variable neighborhood search (ERS‐VNS), and the third one is based on cellular automata (ERS‐CA).…”

Section: Modeling An Intelligent Resources Selection Solutionmentioning

confidence: 99%

Intelligent self‐adaptive resources selection for grid applications

Botón-Fernández¹,

Vega‐Rodríguez

Prieto‐Castrillo³

2014

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

SUMMARYGrid computing is considered a promising trend, which enables the sharing of a wide variety of computational and storage resources geographically distributed. Despite the advantages of such paradigm, several problems have emerged during the last decade; most of them caused by an inefficient utilization of grid resources. The present contribution proposes an approach to improve the grid resources selection process. An optimization model for choosing grid resources in an intelligent way has been designed. A mathematical formulation to monitor the resources efficiency has also been established. Furthermore, the model provides a self-adaptive capability to grid applications, enhancing them for dealing with the changing environmental conditions. The model applies an artificial intelligence algorithm for ensuring an efficient selection. In particular, three different versions have been implemented. Each of them uses a different algorithm. Finally, during the evaluation phase of the model, the experimental tests were performed in a real grid infrastructure. The results show that the model improves the infrastructure throughput, by increasing the finished tasks rate and by reducing the applications execution time.

show abstract

Section: Modeling An Intelligent Resources Selection Solutionmentioning

confidence: 99%