Ana Cristina Alves de Oliveira,  Francisco Vilar Brasileiro.  VII Workshop de Testes e Tolerância a Falhas - Curitiba, PR, Brasil - 2006

The computational grids were built to be an infrastructure to increase computing power. They have evolved in the sense of forming free-to-join communities to share computing power over the Internet, and won the title of peer-to-peer (P2P) grids. Note that as any user can freely join and leave a system, it can become susceptible to damages caused by cheater users. A solution to this problem is applying sabotage tolerant schemes, which are generally based on replication to estimate the computation correctness. This work concerns sabotage tolerant scheduling in P2P grids and shows that it is possible to obtain high levels of realiability for the computation results, minimizing the costs of replication through the use of credibility-based fault tolerance in the task scheduling.

http://www.lbd.dcc.ufmg.br:8080/colecoes/wtf/2006/st5_3.pdf

Processando consulta.