Predicate-Oriented Query of RDF Data Based on a Distributed Storage Model

2016 ◽  
Author(s):  
Xuling Luo ◽  
Bin Wu
Keyword(s):  
Distributed Storage ◽  
Storage Model ◽  
Rdf Data

A Dynamic Partitioning Scheme for Distributed Storage of Large-Scale RDF Data

2014 ◽  
Vol 41 (12) ◽  
pp. 1126-1135
Author(s):  
Cheon Jung Kim ◽  
Ki Yeon Kim ◽  
Jong Hyeon Yoo ◽  
Jong Tae Lim ◽  
Kyoung Soo Bok ◽  
...  
Keyword(s):  
Large Scale ◽  
Distributed Storage ◽  
Dynamic Partitioning ◽  
Rdf Data

A data-check based distributed storage model for storing hot temporary data

2017 ◽  
Vol 73 ◽  
pp. 13-21 ◽  
Author(s):  
Jianjiang Li ◽  
Peng Zhang ◽  
Yuance Li ◽  
Wei Chen ◽  
Yajun Liu ◽  
...  
Keyword(s):  
Distributed Storage ◽  
Storage Model

scholarly journals A Novel Parallel Transmission Strategy for Data Grid

2011 ◽  
Vol 6 (4) ◽  
pp. 681
Author(s):  
QU Ming-Cheng ◽  
WU Xiang-Hu ◽  
Yang Xiao-Zong
Keyword(s):  
Network Traffic ◽  
Data Transmission ◽  
Distributed Storage ◽  
Storage Space ◽  
Parallel Transmission ◽  
Storage Model ◽  
Transmission Strategy ◽  
Wide Range ◽  
Space Saving ◽  
Parallel Transfer

<p>Creation of multi-copies accelerates data transmission and reduces network traffic, but it causes overhead storage and additional network traffic. A variety of parallel transmission algorithms based on GridFTP and multi-copy can be used to accelerate data transmission further, but they can not adapt to a wide range of network, and they can not be used to solve the problems of storage space and network traffic waste. GridTorrent combined with BitTorrent and GridFTP has compatibility with grid and has flexible scalability, but the speed is very slow when there are few peers, to solve this problem multicopy is needed also. To achieve multiple optimization objectives of storage space saving, suitable for two kinds of application modes(i.e. parallel transfer based on GridFTP and BitTorrent), adaptability for wide range of network and higher performance when there are fewer peers, based on the idea of GridTorrent, a distributed storage model, parallel transfer algorithm and virtual peer strategy are proposed. In experiments the performance is compared among the verification system VPG-Torrent and original parallel transfer algorithm<br />(DCDA) only based on GridfTP &amp; multi-copy and GridTorrent. When the same amount of data is deployed VPG-Torrent has better performance than DCDA, and when there are fewer peers VPG-Torrent also exceed GridTorrent, which prove the effectiveness of VPG-Torrent.</p>

scholarly journals Temporal RDF(S) Data Storage and Query with HBase

2020 ◽  
Vol 27 (4) ◽  
pp. 17-30
Author(s):  
Li Yan ◽  
Zheqing Zhang ◽  
Dan Yang
Keyword(s):  
Information Management ◽  
Data Storage ◽  
Temporal Information ◽  
Storage Model ◽  
Web Resources ◽  
Metadata Model ◽  
Query Efficiency ◽  
Rdf Data ◽  
Description Framework ◽  
Resource Description

Resource Description Framework (RDF) is a metadata model recommended by World Wide Web Consortium (W3C) for describing the Web resources. With the arrival of the era of Big Data, very large amounts of RDF data are continuously being created and need to be stored for management. The traditional centralized RDF storage models cannot meet the need of largescale RDF data storage. Meanwhile, the importance of temporal information management and processing has been acknowledged by academia and industry. In this paper, we propose a storage model to store temporal RDF based on HBase. The proposed storage model applies the built-in time mechanism of HBase. Our experiments on LUBM dataset with temporal information added show that our storage model can store large temporal RDF data and obtain good query efficiency.

Modified Raptor Code for Distributed Storage Systems

2010 ◽  
Vol 20-23 ◽  
pp. 52-57
Author(s):  
Zheng Chen ◽  
Xiao Jing Wang
Keyword(s):  
Distributed Storage ◽  
Storage System ◽  
Ldpc Code ◽  
Prototype System ◽  
Storage Model ◽  
New Class ◽  
Distributed Storage Systems ◽  
Dimension 2 ◽  
Raptor Code ◽  
Original Information

We provide a prototype system for a distributed storage model, the goal of this system is to store information in a p2p network of n nodes, and the original information could be recovered later in a computationally simple way from (1+e)k of nodes for some small e>0. For solving this problem, we employ a class of B-J codes with dimension 2 as base code and obtain a new class of LDPC code by using q-tuples to substitute the elements of , to modify and improve Raptor code. The improved Raptor Code has many advantages such as high decoding rate, flexibility in choices of the code length and rate of. As the benefits of the above characters, the storage system based on modified Raptor code has great improvement in decoding probability and parameter flexibility, and a simulation is also illustrated to prove our assumption.

Sign in / Sign up

Export Citation Format

Share Document