WARP: Workload-aware replication and partitioning for RDF

Hose, Katja; Schenkel, Ralf

doi:10.1109/icdew.2013.6547414

Cited by 82 publications

(79 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will begin by quickly reviewing the fundamental standards of semistructured information [20,27], a general idea spearheading many takes a shot at complex information administration in the database group. The objective is to position RDF as a standout amongst the most famous models for semistructured information administration as of now around, while additionally recognizing the commitments already laid out for the more broad model to which it can be followed.…”

Section: Related Work Semistructured Data and Rdfmentioning

confidence: 99%

“…These frameworks advantage from the effi-cient and fine-grained capacity and recovery of the key-esteem stores, however endure in more unpredictable functionalities, for example, joins. Inside the third classification, brought together RDF stores disseminated among different hubs are utilized to misuse the parallelization offered by the various RDF store cases, for example, in [22,27,28]. At long last, in [10,18] a blended approach is utilized with crude information living in Amazon's stockpiling administration (S3), a record list worked in Amazon's key-esteem store and the inquiry offering an explanation to be finished by a unified RDF store.…”

Section: State-of-the-art Cloud-based Rdf Systemsmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient and Scalable Management of Distributed RDF Data in Cloud Storage

2018

IJMTER

View full text Add to dashboard Cite

Abstract-Circulated figuring is the use of handling resources (gear and programming) that are passed on as an organization over a framework (ordinarily the Internet). The disseminated processing uses frameworks of tremendous social occasions of servers normally running insignificant exertion purchaser PC development with specific relationship with spread dataprocessing errands across finished them. Buyer orchestrated applications, for instance, cash related portfolios to pass on altered information, to give data storage.Speculate that far reaching scaledata examination assignments, decision sincerely strong systems, and application specific data shops will presumably misuse circulated registering stages than operation. A scattered system is a model in which parts arranged on masterminded PCs pass on and sort out their exercises by passing messages. Beneficial RDF data organization is one of the establishments in understanding the Semantic Web vision. Some time recently, different RDF storing pushed frameworks like gathering or vertical allocating the predicates.RDF truly encodes rich and complex graphs mixing both event and mapping level data. Sharding such data using built up techniques or distributing graph using ordinary min-cut counts prompts to a great degree inefficient flowed operations and to a high number of joins. In this paper, we depict DiploCloud, a powerful and flexible passed on RDF data organization structure for the cloud. Despite past philosophies, DiploCloud runs a physiological examination of both event and diagram information before allotting the data. In this paper, we portray the outline of DiploCloud, its essential data structures, and moreover the new computations we use to divide pass on data. We moreover show an expansive evaluation of DiploCloud exhibiting that our system is frequently two solicitations of enormity speedier than best in class structures on standard workloads.

show abstract

Section: Related Work Semistructured Data and Rdfmentioning

confidence: 99%

Section: State-of-the-art Cloud-based Rdf Systemsmentioning

confidence: 99%

An Efficient and Scalable Management of Distributed RDF Data in Cloud Storage

2018

IJMTER

View full text Add to dashboard Cite

show abstract

“…Single-machine RDF systems, like RDF-3X [53] and gStore [37], do not scale well to complex queries on web-scale RDF data [29,33]. To overcome this problem, many distributed SPARQL query engines [29,33,47,41,32,48,30,28,36,25,46,18,15,38,16] have been introduced. They utilize shared-nothing computing clusters and are either built on top of distributed data processing frame-works, such as MapReduce, or implement proprietary distributed computation approaches.…”

Section: Introductionmentioning

confidence: 99%

A survey and experimental comparison of distributed SPARQL engines for very large RDF data

et al. 2017

View full text Add to dashboard Cite

Distributed SPARQL engines promise to support very large RDF datasets by utilizing shared-nothing computer clusters. Some are based on distributed frameworks such as MapReduce; others implement proprietary distributed processing; and some rely on expensive preprocessing for data partitioning. These systems exhibit a variety of trade-offs that are not well-understood, due to the lack of any comprehensive quantitative and qualitative evaluation. In this paper, we present a survey of 22 state-of-the-art systems that cover the entire spectrum of distributed RDF data processing and categorize them by several characteristics. Then, we select 12 representative systems and perform extensive experimental evaluation with respect to preprocessing cost, query performance, scalability and workload adaptability, using a variety of synthetic and real large datasets with up to 4.3 billion triples. Our results provide valuable insights for practitioners to understand the trade-offs for their usage scenarios. Finally, we publish online our evaluation framework, including all datasets and workloads, for researchers to compare their novel systems against the existing ones.

show abstract

“…[9] applies a graph partitioning approach for streaming RDF data. Query driven partitioning [3] leverages query knowledge to partition data so as to answer queries by single node computations.…”

Section: Introductionmentioning

confidence: 99%

Incremental Data Partitioning of RDF Data in SPARK

Agathangelos

Troullinou

Kondylakis

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Significant efforts have been dedicated recently to the development of architectures for storing and querying RDF data in distributed environments. Several approaches focus on data partitioning, which are able to answer queries efficiently, by using a small number of computational nodes. However, such approaches provide static data partitions. Given the increase on the continuous and rapid flow of data, nowadays there is a clear need to deal with streaming data. In this work, we propose a framework for incremental data partitioning by exploiting machine learning techniques. Specifically, we present a method to learn the structure of a partitioned database, and we employ two machine learning algorithms, namely Logistic Regression and Random Forest, to classify new streaming data.

show abstract

WARP: Workload-aware replication and partitioning for RDF

Cited by 82 publications

References 9 publications

An Efficient and Scalable Management of Distributed RDF Data in Cloud Storage

An Efficient and Scalable Management of Distributed RDF Data in Cloud Storage

A survey and experimental comparison of distributed SPARQL engines for very large RDF data

Incremental Data Partitioning of RDF Data in SPARK

Contact Info

Product

Resources

About