A Self-Optimizing Cloud Computing System for Distributed Storage and Processing of Semantic Web Data

Clouds are dynamic networks of common, off-the-shell computers to build computation farms. The rapid growth of databases in the context of the semantic web requires efficient ways to store and process this data. Using cloud technology for storing and processing Semantic Web data is an obvious way to overcome difficulties in storing and processing the enormously large present and future datasets of the Semantic Web. This paper presents a new approach for storing Semantic Web data, such that operations for the evaluation of Semantic Web queries are more likely to be processed only on local data, instead of using costly distributed operations. An experimental evaluation demonstrates the performance improvements in comparison to a naive distribution of Semantic Web data.