Evaluating Conjunctive Triple Pattern Queries over Large Structured Overlay Networks

Abstract

We study the problem of evaluating conjunctive queries composed of triple patterns over RDF data stored in distributed hash tables. Our goal is to develop algorithms that scale to large amounts of RDF data, distribute the query processing load evenly and incur little network traffic. We present and evaluate two novel query processing algorithms with these possibly conflicting goals in mind. We discuss the various tradeoffs that occur in our setting through a detailed experimental evaluation of the proposed algorithms. This work was supported in part by the European Commission project Ontogrid (http://www.ontogrid.net/).

Approximate Semantic Matching over Linked Data Streams

“…Similar to [14,15], triple patterns are adopted as the basic units of user queries in our system. A triple pattern is an expression of the form (s, p, o) where s and p are URIs or variables, and o is a URI, a literal or a variable.…”

Scalable distributed indexing and query processing over Linked Data

“…Query processing is based on so-called query chains, which mainly resemble a sequential processing strategy. In [54], the authors also propose a variant that exploits the values of matching triples found while processing the query incrementally by constructing multiple chains for each query. This introduces some limited degree of parallelism into query processing.…”

Atlas: Storing, updating and querying RDF(S) data on top of DHTs

“…), researchers have also studied parallel and distributed solutions for RDF(S) reasoning and query processing. Recent proposals in this area have been based on distributed hash tables (DHTs) [14,15,16,17,9,18], distributed computing platforms based on powerful clusters [19,20,21,22] and cloud computing platforms using MapReduce [23].…”

“…Research in Atlas has resulted in novel distributed RDFS reasoning algorithms [18], and efficient strategies for RDF query processing on top of DHTs which cover one-time [15,9] and continuous queries [28]. We call one-time queries the standard queries asked in a typical RDF store (or a typical DBMS in general).…”

“…This paper gives a system-level description of Atlas. Details of algorithms and other results presented only briefly can be found in our publications [18,15].…”