• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.161-170
• /
• 2022

Recently, NAND-type flash memory has been regarded to be new promising storage media for large-scale database systems. For flash memory to be employed for that purpose, we need to reduce its expensive update cost caused by the inablity of in-place updates. To remedy such a drawback in flash memory, we propose a new flash-aware buffering scheme that enables virtual flushing of dirty pages. To this end, we slightly alter the tradional algorithms used for the logging scheme and buffer management scheme. By using the mechanism of virtual flushing, our proposed buffering scheme can efficiently prevent the frequenct occureces of page updates in flash storage. Besides the advantage of reduced page updates, the proposed viurtual flushing mechanism works favorably for shorneing a recocery time in the presense of failure. This is because it can reduce the time for redo actions during a recovry process. Owing to those two benefits, we can say that our scheme couble be very profitable when it is incorporated into cutting-edge flash-based database systems.

• Journal of Power Electronics
• /
• 제18권4호
• /
• pp.1111-1126
• /
• 2018

In modern power systems, distributed generators (DGs) result in high stress on system frequency stability. Apart from the intermittent nature of DGs, most DGs do not contribute inertia or damping to systems. As a result, a new control method referred to as a virtual synchronous machine (VSM) has been proposed, which brought new characteristics to inverters such as synchronous machines (SM). DGs employing an energy storage system (ESS) provide inertia and damping through VSM control. Meanwhile, energy storage presents some physical constraints in the VSM implementation level. In this paper, a VSM mathematical model is built and analyzed. The dynamic responses of the output active power are presented when a step change in the frequency occurs. The influences of the inertia constant, damping factor and operating point on the ESS volume margins are investigated. In addition, physical constraints are proposed based on these analyses. The proposed physical constraints are simulated using PSCAD/EMTDC software and tested through RTDS experiment. Both simulation and RTDS test results verify the analysis.

• 한국정보기술학회 영문논문지
• /
• 제10권2호
• /
• pp.91-101
• /
• 2020

Recently, the demand for high penetration of variable renewable energy (VRE) penetration in a power system is increased. In consequence, distribution systems including microgrids confront the increased installation of VRE-based distributed generation. Despite of the high demand of VRE-based distributed generation in a distribution system, the installation of photovoltaic (PV) system in a distribution system has been restricted by various problems. In other words, the hosting capacity for high VRE penetration in a distribution system is limited. This paper analyzes the improvements of hosting capacity VRE penetration of stand-alone microgrid (SAMG) with energy storage system (ESS) by considering virtual-slack (VS) control based on power sensitivity. With the pre-defined power sensitivity, the ESS operates as virtual slack in the SAMG by controlling its bus voltage and phase angle indirectly. Therefore, the ESS enables the increase of VRE penetration in the SAMG. The proposed VS control is realized by analyzing the ESS as a virtual slack in power flow analysis based on power sensitivity. Then its validity is demonstrated with the case study on the SAMG in South Korea with practical data.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제3권12호
• /
• pp.433-442
• /
• 2014

분산 파일시스템의 클라이언트 측에 SSD 장치를 캐시 장치로 사용하여 분산 파일시스템의 읽기 성능을 향상시키고, Back-end 데이터 서버의 부하를 줄일 수 있다. 이러한 성능 향상을 통하여 기존의 대용량 스토리지 지원만이 가능했던 분산 파일시스템의 적용 분야를 고성능이 필요한 분야로 확장할 수 있다. 본 논문은 국내에서 개발된 분산 파일시스템인 MAHA-FS에 클라이언트 측의 SSD 캐시를 적용하여 가상 데스트톱의 입출력 성능을 향상시킬 수 있음을 보여준다. 실험 결과 NFS에 비해 가상 머신 이미지 배포 시간은 2배 이상, 부팅 시간은 3배 이상 향상시킬 수 있음을 알 수 있다.

• 한국인터넷방송통신학회논문지
• /
• 제22권3호
• /
• pp.93-98
• /
• 2022

최근 옵테인 등 고속 스토리지의 출현으로 하드디스크에 적합하게 설계된 메모리 시스템 설정에 대한 재고가 필요한 시점에 이르렀다. 본 논문에서는 고속 스토리지의 탑재에 따라 페이지 크기가 메모리 시스템의 성능에 어떠한 영향을 미치는지를 분석하고, 가상화 환경에서 워크로드 상황에 맞게 페이지 크기를 설정할 수 있는 모델을 설계하였다. 전통적인 시스템의 경우 워크로드 별로 페이지 크기를 설정하는 것이 쉬운 일이 아니지만 최근 클라우드 환경의 활성화로 개별 워크로드 수행을 위해 별도의 가상머신이 생성되므로 가상머신이 시작될 때 해당 가상머신의 페이지 크기를 결정할 수 있어 제안한 모델의 효용이 높을 것으로 기대된다. 다양한 가상머신 시나리오에 대한 시뮬레이션 실험을 통해 제안한 모델이 워크로드 상황에 맞게 페이지 크기를 설정하여 메모리 접근 시간을 크게 개선함을 보인다.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.280-286
• /
• 2018

A sensorless active damping scheme for LCL filters in grid-connected parallel inverters for battery energy storage systems is proposed. This damping method is superior to the conventional notch filter and virtual damping methods with respect to robustness against the variation of the resonance of the filter and unnecessary additional current sensors. The theoretical analysis of the proposed damping method is explained in detail, along with the characteristic comparison to the conventional active damping methods. The performance verification of the proposed sensorless active damping method shows that its performance is comparable to that of the conventional virtual damping method, even without additional current sensors. Finally, simulation and experimental results are provided to examine the overall characteristics of the proposed method.

• 한국컴퓨터정보학회논문지
• /
• 제20권10호
• /
• pp.91-97
• /
• 2015

In this paper, we propose a MCFQ I/O scheduler that is implemented by modifying the existing Linux CFQ I/O scheduler. MCFQ observes whether the user requested I/O bandwidth weight is well distributed. Based on the I/O bandwidth observation, we improved I/O performance of the existing bandwidth distribution ability by dynamically controlling the I/O time-slice of the virtual machine. The use of SSDs as storage has been increasing dramatically in recent computer systems due to their fast performance and low power usage. As the usage of SSD increases and prices fall, virtualized system administrators can take advantage of SSDs. However, studies on guaranteeing SLA(Service Level Agreement) services when multiple virtual machines share the SSD is still incomplete. In this paper was conducted to improve performance of the bandwidth distribution when multiple virtual machine are sharing a single SSD storage in a virtualized environment. In particular, it was observed that the performance of the bandwidth distribution varied widely when garbage collection occurs in the SSD. In order to reduce performance variance, we add a MoTS(Manager of Time Slice) on existing CFQ I/O scheduler.

• Imaging Science in Dentistry
• /
• 제50권4호
• /
• pp.331-337
• /
• 2020

Purpose: As cone-beam computed tomography (CBCT) has become the most widely used 3-dimensional (3D) imaging modality in the dental field, storage space and costs for large-capacity data have become an important issue. Therefore, if 3D data can be stored at a clinically acceptable compression rate, the burden in terms of storage space and cost can be reduced and data can be managed more efficiently. In this study, a deep learning network for super-resolution was tested to restore compressed virtual CBCT images. Materials and Methods: Virtual CBCT image data were created with a publicly available online dataset (CQ500) of multidetector computed tomography images using CBCT reconstruction software (TIGRE). A very deep super-resolution (VDSR) network was trained to restore high-resolution virtual CBCT images from the low-resolution virtual CBCT images. Results: The images reconstructed by VDSR showed better image quality than bicubic interpolation in restored images at various scale ratios. The highest scale ratio with clinically acceptable reconstruction accuracy using VDSR was 2.1. Conclusion: VDSR showed promising restoration accuracy in this study. In the future, it will be necessary to experiment with new deep learning algorithms and large-scale data for clinical application of this technology.

• 한국정보통신학회논문지
• /
• 제13권2호
• /
• pp.267-276
• /
• 2009

최근들어 다양한 인터넷 서비스들이 개인 컴퓨터뿐만 아니라 무선 네트워크 환경에서의 모바일 기기에서도 자주 사용되고 있으며 서비스 컨텐츠의 양이 점점 증가함에 따라 모바일 기기의 스토리지 한계가 큰 문제가 되고 있다. 본 논문에서는 이러한 문제를 해결하기 위해 iATA라는 새로운 블록-레벨 스토리지 네트워크 프로토콜을 제안하며 iATA 프로토콜의 개념, 설계 및 고려사항들을 포함한다. iATA는 TCP/IP 네트워크상에서 ATA 블록-레벨 데이터와 명령어를 전달하게 되며 이를 통해 모바일 기기는 원격의 ATA 저장장치를 마치 모바일 기기 자신의 스토리지로 이용할 수 있게 된다. 벤치마킹 실험과 시험을 통해 제안된 iATA 프로토콜은 기존의 제안한 스토리지를 가지고 있는 모바일 기기상에서 효율적이며 경량의 가상 스토리지 프로토콜로서 사용될 수 있음을 보여주고 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 춘계학술발표대회
• /
• pp.1167-1170
• /
• 2007

This paper introduces a data storage transport protocol internet Advanced Technology Attachment (iATA) for ATA storage devices that can be accessed over (TCP/IP) networks. As the access speed of Advanced Technology Attachment (ATA) type storage is increasing, the importance of sharing the ATA type storages over internet is also increasing. We are proposing a protocol in which we have implemented the basic ATA command set to access the ATA type remote storage devices over the TCP/IP networks.In this paper, we give basic details of the protocol and discuss the existing storage protocols which are mainly used for accessing block storage like internet Small Computer System Interface (iSCSI) Hyper Small Computer System Interface (HyperSCSI) and ATA over Ethernet (AoE).