• ETRI Journal
• /
• 제38권3호
• /
• pp.529-539
• /
• 2016

Recently, a product-matrix (PM) framework was proposed to construct optimal regenerating codes for homogeneous distributed storage systems (DSSs). In this paper, we propose an extended PM (EPM) framework for coding of heterogeneous DSSs having different repair bandwidths but identical storage capacities. Based on the EPM framework, an explicit construction of minimum remote-repair bandwidth regenerating (MRBR) codes is presented for a specific heterogeneous DSS, where two geographically different datacenters with associated storage nodes are deployed. The data reconstruction and regeneration properties of the MRBR code are proved strictly. For the purpose of demonstration, an example implementation of MRBR code is provided. The presented MRBR code is the first optimal strict-regenerating code for heterogeneous DSSs. In addition, our proposed EPM framework can be applied to homogeneous systems also.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1182-1199
• /
• 2023

Fractional repetition (FR) codes can achieve exact uncoded repair for multiple failed nodes, with lower computational complexity and bandwidth overhead, and effectively improve repair performance in distributed storage systems (DSS). The actual distributed storage system is dynamic, that is, the parameters such as node storage overhead and number of storage nodes will change randomly and dynamically. Considering that traditional FR codes cannot be flexibly applied to dynamic distributed storage systems, a new construction scheme of adaptive-and-resolvable FR codes based on hypergraph coloring is proposed in this paper. Specifically, the linear uniform regular hypergraph can be constructed based on the heuristic algorithm of hypergraph coloring proposed in this paper. Then edges and vertices in hypergraph correspond to nodes and coded packets of FR codes respectively, further, FR codes is constructed. According to hypergraph coloring, the FR codes can achieve rapid repair for multiple failed nodes. Further, FR codes based on hypergraph coloring can be generalized to heterogeneous distributed storage systems. Compared with Reed-Solomon (RS) codes, simple regenerating codes (SRC) and locally repairable codes (LRC), adaptive-and-resolvable FR codes have significant advantages over repair locality, repair bandwidth overhead, computational complexity and time overhead during repairing failed nodes.

• 한국컴퓨터정보학회논문지
• /
• 제14권4호
• /
• pp.9-17
• /
• 2009

본 논문에서는 운영체제 수준에서 에너지 절감과 함께 I/O 성능 개선을 목적으로 하여 소형 하드 디스크와 플래시 메모리를 이종의 저장 장치로 가지는 모바일 시스템에 대해 동적 부하 분산 기법을 제안한다. 제안 기법은 부하가 에너지 및 성능 효율적인 방법으로 하드디스크와 플래시 메모리의 이종성의 저장 장치 구성에 대해서 어떻게 효율적으로 분산될 수 있을 것인지를 발견하기 위하여 파일 배치 기법과 버퍼 캐시 관리 기법을 결합하는 접근법을 취한다. 제안한 기법은 폭넓은 시뮬레이션을 통해서 기존의 기법들과 비교하여 이종의 모바일 저장장치들에 대해서 더 개선된 실험 결과를 보이는 것으로 나타났다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2001년도 디지털 방송기술 워크샵
• /
• pp.335-354
• /
• 2001

.Next Generation Multimedia Streaming Technology Massive Scale Support $\rightarrow$ Clustered Solution Adaptive to Heterogeneous Network daptive to Heterogeneous Terminal Capability Presentation Technique .SMART Server Architecture .HERMES File System .Clustered Solution . High Speed Storage Interconnect .' Content Partitioning . Load Management . Support for Heterogeniety . Adaptive End to End Streaming Transport: Unicast vs. Multicast '. Scalable Encoding

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권9호
• /
• pp.4063-4086
• /
• 2016

Cloud computing is a robust technology, which facilitate to resolve many parallel distributed computing issues in the modern Big Data environment. Hadoop is an ecosystem, which process large data-sets in distributed computing environment. The HDFS is a filesystem of Hadoop, which process data blocks to the cluster nodes. The data block placement has become a bottleneck to overall performance in a Hadoop cluster. The current placement policy assumes that, all Datanodes have equal computing capacity to process data blocks. This computing capacity includes availability of same storage media and same processing performances of a node. As a result, Hadoop cluster performance gets effected with unbalanced workloads, inefficient storage-tier, network traffic congestion and HDFS integrity issues. This paper proposes a storage-tier-aware Robust Data Placement (RDP) scheme, which systematically resolves unbalanced workloads, reduces network congestion to an optimal state, utilizes storage-tier in a useful manner and minimizes the HDFS integrity issues. The experimental results show that the proposed approach reduced unbalanced workload issue to 72%. Moreover, the presented approach resolve storage-tier compatibility problem to 81% by predicting storage for block jobs and improved overall data block placement by 78% through pre-calculated computing capacity allocations and execution of map files over respective Namenode and Datanodes.

• 한국정보처리학회논문지
• /
• 제7권4호
• /
• pp.1050-1061
• /
• 2000

This paper presents a new object model, LOM(Lightweight Object Model) and an implementation method for the distributed trader in heterogeneous distributed computing environment including mobile network. Trader is third party object that enables clients to find suitable servers, which provide the most appropriate services to client in distributed environment including dynamic reconfiguration of services and servers. Trading service requires simpler and more specific object model than genetic object models which provide richer multimedia data types and semantic characteristics with complex data structures. LOM supports a new reference attribute type instead of the relationship, inheritance and composite attribute types of the general object oriented models and so LOM has simple data structures. Also in LOM, the modelling step includes specifying of the information about users and the access right to objects for security in the mobile environment and development of the distributed storage for trading service. Also, we propose and implementation method of the distributed trader, which integrates the LOM-information object model and the OMG (object Management Group) computational object model.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.95-102
• /
• 2024

In distributed computing, accessible encryption strategy over Auditable data is a hot research field. Be that as it may, most existing system on encoded look and auditable over outsourced cloud information and disregard customized seek goal. Distributed storage space get to manage is imperative for the security of given information, where information security is executed just for the encoded content. It is a smaller amount secure in light of the fact that the Intruder has been endeavored to separate the scrambled records or Information. To determine this issue we have actualize (CBC) figure piece fastening. It is tied in with adding XOR each plaintext piece to the figure content square that was already delivered. We propose a novel heterogeneous structure to evaluate the issue of single-point execution bottleneck and give a more proficient access control plot with a reviewing component. In the interim, in our plan, a CA (Central Authority) is acquainted with create mystery keys for authenticity confirmed clients. Not at all like other multi specialist get to control plots, each of the experts in our plan deals with the entire trait set independently. Keywords: Cloud storage, Access control, Auditing, CBC.

• 디지털융복합연구
• /
• 제19권3호
• /
• pp.211-216
• /
• 2021

분산 클라우드 환경에서는 다양한 이기종 장치의 정보들이 꾸준하게 증가하고 있다. 이 같은 이유는 고속의 네트워크의 속도와 대용량의 멀티미디어 데이터가 사용되고 있기 때문이다. 그러나, 이기종의 장치에서 송·수신되는 빅데이터의 정보 오류를 최소화하기 위한 방법은 여전히 연구가 진행되고 있다. 본 논문에서는 클라우드 환경에서 송·수신되는 정보들에 의해 발생되는 네트워크의 대역폭과 데이터 오류 최소화를 위한 딥러닝 기반의 비대칭적 저장 관리기법을 제안한다. 제안 기법은 각각의 디바이스에서 생성되는 빅 데이터정보를 비대칭적으로 해시 처리한 후 로드 밸런스를 최적화하기 위해서 딥러닝 기술을 적용하고 있다. 제안 기법은 각 디바이스에서 수집된 빅 데이터의 오류를 허용하는 동시에 빅 데이터의 연계 정보를 n개의 클러스터 그룹으로 그룹핑함으로써 빅 데이터의 연결성을 확보한 것이 특징이다. 특히, 제안 기법은 빅 데이터간의 유사 값을 시드로 추출한 손실 함수를 사용하였기 때문에 비대칭적으로 빅 데이터를 저장 관리 할때의 정보 오류를 최소화하였다.

• 디지털산업정보학회논문지
• /
• 제8권1호
• /
• pp.99-105
• /
• 2012

Given the numbers of smartphones, tablets and other mobile devices shipped every day, more and more users are relying on the cloud as the main driver for satisfying their computing needs, whether it is data storage, applications or infrastructure. Mobile cloud computing is simply cloud computing in which at least some of the devices involved are mobile. Each node is owned by a different user and is likely to be mobile. Using mobile hardware for cloud computing has advantages over using traditional hardware. These advantage include computational access to multimedia and sensor data without the need for large network transfer, more efficient access to data stored on other mobile devices and distributed ownership and maintenance of hardware. It is important to predict job execution time in mobile cloud computing because there are many mobile nodes with different capabilities. This paper analyzes the job execution time for mobile cloud computing in terms of network environment and heterogeneous mobile nodes using a mathematical model.

• 한국콘텐츠학회논문지
• /
• 제5권1호
• /
• pp.189-199
• /
• 2005

그리드 컴퓨팅은 과학기술 분야의 큰 문제들을 해결하기 위해 네트워크 상에 분산된 수많은 컴퓨터들의 컴퓨팅 파워와 대용량 저장장치를 공유하여 문제들을 해결할 수 있는 기술이다. 그리드 컴퓨팅의 환경은 WAN으로 구성된 각기 다른 성능과 이질적인 네트워크 상태들로 구성된다. 그래서, 이러한 이질적인 성능요소들을 고려하여 계산 작업에 반영시키는 것이 무엇보다 중요하다. 본 논문에서는 네트워크 상태정보를 고려한 노드별 작업 프로세스 수를 결정하는 효율적인 방법을 제안한다. 네트워크 상태정보는 latency, bandwidth, latency-bandwidth 혼합정보를 고려한다. 먼저, 측정된 네트워크 상태정보를 이용하여 노드별 성능비율을 구하고 이를 통해 작업 프로세스 수를 결정한다. 마지막 단계에서는, 결정된 노드별 작업 프로세스 수를 기반으로 자동으로 RSL 파일을 생성하여 작업을 수행한다. 네트워크 성능정보는 NWS(Network Weather Service)에 의해 수집된다. 실험결과에 따르면, 네트워크 성능정보를 고려한 방법이 그렇지 않은 기존의 균등방식보다 작업량, 작업 프로세스 수, 노드 수 관점에서 각각 23%, 31%, 57% 성능이 향상되었다.