Semantic caching for pervasive grids

Abstract

Recently, grids and pervasive systems have been drawing increasing attention in order to coordinate large-scale resources enabling access to small and smart devices. In this paper, we propose a caching approach enabling to improve querying on pervasive grids. Our proposal, called semantic pervasive dual cache, follows a semantics oriented approach. It is based on the one hand on a clear separation between the analysis and the evaluation process, and on the other hand on the cooperation between client caches considering light analysis and proxy caches including evaluation capabilities. Such an approach helps load balancing, making the system more scalable. We have validated semantic pervasive dual cache using analytic models and simulations. Results obtained show that our approach is quite promising.