• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.30-32
• /
• 2017

낸드 플래시 메모리는 데이터 용량의 급격한 증가로 인해서 저장장치로 널리 사용되게 되었으나, 마찬가지로 급격히 증가하는 에러 발생률에 의해서 저장장치의 신뢰성에 문제가 되고 있다. 일반적으로 에러 발생에 대한 보정을 위해서 낸드 플래시 메모리는 ECC 기법을 사용하는데, 본 논문에서는 압축기법을 활용하여 줄어든 유효 데이터에 대한 적응적 ECC 기법을 적용함으로써 에러 발생시 에러 보정능력을 향상시켜줄 수 있는 기법을 제안하였다. 이러한 에러 보정방법을 통해서 낸드 플래시 메모리 기반의 저장 시스템에 대한 에러 발생률이 낮아짐을 보여주고 있다.

• KIISE Transactions on Computing Practices
• /
• 제23권8호
• /
• pp.473-480
• /
• 2017

In recent years, semiconductor-based storage devices such as flash memory (SSDs) have been developed to high performance. In addition, a trend has been observed of optimally utilizing resources such as the central processing unit (CPU) and memory of the internal controller in the storage device according to the needs of the application. This concept is called In-Storage Processing (ISP). In a storage device equipped with the ISP function, it is possible to process part of the operation executed on the host system, thus reducing the load on the host. Moreover, since the data is processed in the storage device, the data transferred to the host are reduced. In this paper, we propose a method to optimize graph query processing by utilizing these ISP functions, and show that the optimized graph processing method improves the performance of the graph 500 benchmark by up to 20%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제23권6호
• /
• pp.1247-1257
• /
• 2013

The security vulnerabilities of cloud storage virtualization environments are different from those of the existing computer system and are difficult to be protected in the existing computer system environment. Therefore we need some technical measures to address this issue. First of all, the technology used in cloud storage virtualization environment needs to be thoroughly analyzed, and also, we should understand those security requirements of various stakeholders in the view of cloud storage service and perform the research on security guidelines of the research security requirements. In this paper, we propose security requirements based on layers and roles of cloud storage virtualization. The proposed security requirements can be a basement for development of solution of cloud storage virtualization security.

• Journal of KIISE:Computing Practices and Letters
• /
• 제9권6호
• /
• pp.718-731
• /
• 2003

SAN(Storage Area Network) was developed in response to the requirements of high availability of data, scalable growth, and system performance. In order to use the SAN more efficiently, most of the SAN operating software supports storage virtualization concepts that allow users to view physical storage devices of the SAN as a large volume. A logical volume manager plays a key role in storage virtualization. It realizes the storage virtualization by mapping logical addresses to physical addresses. In this paper, we design and implement an efficient and flexible mapping method for the logical volume manager. Additionally we also design and implement a free space management method for flexible mapping. Our mapping method supports a snapshot that preserves a volume image at certain time and on-line reorganization to allow users to add or remove storage devices to and from the SAN even while the system is running. To justify our mapping method, we compare it with the mapping method of the GFS (Global File System) through various experiments.

• KIPS Transactions on Computer and Communication Systems
• /
• 제3권9호
• /
• pp.273-278
• /
• 2014

Recent use of electricity during peak hours electricity supply-demand imbalance is inevitable that limit power use force. Therefore, in this paper, a circuit of parallel power operation equipment for peak power reduction which saves the power to electricity storage device during the non-peak power time and supply from the storage power during the expected power shortages time is designed Through this circuitry, the peak power of the commercial power supply with the parallel operation and connection of the commercial power supply and the power supply of the inverter from electricity storage that is a key feature of PRS(Peak power Reduction System) can be controlled. In addition, in order to increase the efficiency, a Transless Power Circuit DC-AC inverter is developed. Moreover, a variable impedance control is applied to the storage of electric power of an Uninterruptible Power Supply associated with a commercial power source.

• KIISE Transactions on Computing Practices
• /
• 제21권10호
• /
• pp.639-644
• /
• 2015

The capacity of flash-based storage such as Solid State Drive(SSD) and embedded Multi Media Card(eMMC) is ever-increasing because of the needs from the end-users. However, if a flash-based storage crashes, such as during power failure, the flash translation layer(FTL) is responsible for the crash recovery based on the entire flash memory. The recovery time increases as the capacity of the flash-based storages increases. We propose O1FTL with O(1) crash recovery time that is independent of the flash capacity. O1FTL adopts the working area technique suggested for the flash file system and evaluates the design on a real hardware platform. The results show that O1FTL achieves a crash recovery time that is independent of the capacity and the overhead, in terms of I/O performance, and achieves a low P/E cycle.

• Journal of Internet of Things and Convergence
• /
• 제10권2호
• /
• pp.109-114
• /
• 2024

Enterprise storage systems that require high data reliability are applying RAID (Redundant Array of Independent Disks) systems to recover from data loss and failure. In particular, RAID 5 ensures space efficiency and reliability by distributing parity across multiple storage devices. However, when storage devices have different capacities, RAID is built based on the smallest capacity storage device, resulting in wasted storage space. Therefore, research is needed to solve this resource management problem. In this paper, we propose a method for RAID grouping of each independent NAND flash memory block in a RAID consisting of SSD (Solid State Disk) with external SSDs as well as internal SSDs. This method is divided into a policy for delivering block information inside SSDs to the RAID system and a policy for RAID grouping of physical addresses delivered from the RAID system. This method allows us to maintain a RAID that does not waste resources when SSDs of different capacities are grouped into RAID5. Finally, we demonstrate the effectiveness of the proposed method through experiments.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제54권6호
• /
• pp.17-21
• /
• 2017

Since holographic data storage has the advantage of high recording density and data transfer rate, it is a candidate for the next generation storage systems. However, Holographic data storage system is affected by interpage interference and two dimensional intersymbol interference. Also, burst error occurs by physical impact. In this paper, we propose an LDPC product code using modified log-likelihood ratio and extrinsic information to correct burst error and improve performance of holographic data storage. The performance of proposed LDPC product code is 0.5dB better than that of the conventional LDPC code.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2005년도 추계학술대회
• /
• pp.169-174
• /
• 2005

위치기반서비스(LBS)에서는 사람, 차량과 같은 이동체의 위치 정보를 획득하며, 이동객체 DBMS의 개발로 이동체가 움직인 궤적 정보를 효율적으로 저장 관리할 수 있다. 이동객체 DBMS에 저장된 이동체가 실제 움직인 과거 궤적정보는 다양한 형태로 가공되어 활용이 가능하다. 본 논문에서는 이동체의 과거 궤적정보를 이용하여 경로 안내를 위한 경로 산출 방법에 대하여 제안한다. 기존의 경로 안내는 교통정보 수집 장치를 통해 획득한 교통 정보를 이용하여 경로를 산출하는 방식이 많이 사용되고 있어, 교통 정보가 없는 곳에서는 단순 초행길 안내 수준이다. 그러나, 본 논문에서 제안하는 방법은 고비용이 소요되는 교통정보수집장치가 없는 곳에 대해서도 과거 차량의 움직인 궤적정보를 이용하여 보다 효율적인 경로 안내를 할 수 있는 장점이 있다.

• 한국지형공간정보학회:학술대회논문집
• /
• 한국지형공간정보학회 2003년도 창립 10주년 기념 국제학술대회 논문집
• /
• pp.89-94
• /
• 2003

이동통신기술의 발전과 무선인터넷 사용자의 급증 및 휴대 단말기 장치의 성능 향상으로 인하여 사용자의 위치 정보를 활용하여 부가 정보 서비스를 받을 수 있는 위치기반서비스(LBS : Location Based Service)에 대한 관심이 급증하고 있다. 위치기반 서비스를 제공하기 위해서는 사용자의 위치정보를 관리하는 이동객체 관리 기술이 필수적으로 요구된다. 이에 본 논문에서는 기존의 시공간데이터베이스시스템 연구와 이동객체 관리 시스템을 간략히 살펴보고, 이동객체 객체 관리 시스템 중 이동객체를 저장하는 서브시스템을 설계 및 구현하고자 한다. 이를 위해서 단일 RDBMS 기반에 위치정보를 저장, 검색하는 컴포넌트와 수많은 이동객체의 계속적인 저장 및 검색의 과부하를 조절하고 대용량의 위치정보를 효율적으로 관리하기 위해 분산 데이터베이스에 저장하는 컴포넌트를 제안하고자 한다.