The Grid provides facilities that support the coordinated use of diverse resources, and consequently, provides new opportunities for wide-area query processing. However, Grid resources, as well as being heterogeneous, may also exhibit unpredictable, volatile behaviour. Thus, query processing on the Grid needs to be adaptive, in order to cope with evolving resource characteristics, such as machine load. To address this challenge, an architecture is proposed that has been empirically evaluated over a prototype Grid-enabled adaptive query processor instantiating it.
Anastasios Gounaris, Jim Smith, Norman W. Paton, R