• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.1
• /
• pp.158-163
• /
• 2003

When the number of disks array systems that contain multiple disk drives, system performance is limited by a bottleneck at a centralized controller at a communication path than uses a bus. A redundant array of inexpensive disks(RAID) consists of many disks to enable high performance and large capacity. We evaluate a scalable architecture called Autonomous network, in which the controller functions are distributed to all disk drives and each disk has autonomy in processing its tasks. Disks drives enable better scalability and more effective utilization of system resources than with a hierarchical system. Autonomous network provided high read/write performance throughput in proportion to the number of disks.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.3
• /
• pp.46-58
• /
• 1998

Multi-disk data allocation problem examined in this paper is to find a method to distribute a Binary Cartesian Product File on multiple disks to maximize parallel disk I/O accesses for partial match retrieval. This problem is known to be NP-hard, and heuristkc approaches have been applied to obtain sub-optimal solutions. Recently, efficient methods have been proposed with a restriction that the number of disks in which files are stored should be power of 2. In this paper, we propose a new disk Allocation method based on Genetic Algorithm(GA) to remove the restriction on the number of disks to be applied. Using the schema theory, we prove that our method can find a near-optimal solutionwith high probability. We compare the quality of solution derived by our method with General Disk Modulo, Binary Disk Modulo, and Error Correcting Code methods through the simulation. The simulation results show that proposed GA is superior to GDM method in all cases and provides comparable performance to the BDM method which has a restriction on the number of disks.

• Journal of Korea Multimedia Society
• /
• v.2 no.1
• /
• pp.22-29
• /
• 1999

In video-on-demand systems, movies are striped across the disks of the array in a video server to support multiple access. The blocks of the movies have to be placed carefully on the disks of the array in a video server in order to avoid load imbalance across these disks as well as to achieve maximum utilization of both space and bandwidth of these disks. This paper proposes a movie placement method called the GARR (group-alternation round-robin) that is based on the dynamic disk striping method considering the popularity of movie. The GARR uses group-alternation as movie selection policy and round-robin as data placement policy, where group-alternation allocates popular movie and unpopular movie groups to disks alternately. The performance of the GARR is evaluated by simulations.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.15-21
• /
• 1996

This paper describes data placement schemes that provide uniform and balanced to multiple disks load for retrievals of VBR (variable bit rate) video at varying retrieval speeds. To support maximum concurent users at arbitrary-speed playbacks in a disk-arry based system, the hot spot disks should be carefully avoided. In this paper, we extend the proposed scheme, prime round-robin(PRR), for VBR video. In addition, we have compared the performance of PRR and PRR (PRR extension).

• Laser Solutions
• /
• v.7 no.2
• /
• pp.11-18
• /
• 2004

We propose a novel application of optical coherence tomography (OCT) to monitor pit formation in laser irradiated optical storage materials. A multilayer optical storage recordable compact disk, is composed of multiple layers, each of different structure. Disks were irradiated with aQ-Switched Nd:YAG laser with an energy of 373 mJ. Post-irradiated disks were evaluated by OCT and those images were compared with optical microscopy. Our results indicate that OCT is a useful instrument to investigate pit formation in multilayer optical storage disks and might also provide information to optimize optical memory technology.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.15-27
• /
• 2003

Recently, the volume of data is increasing rapidly in server for multimedia service, according to development of multimedia application environment. In recent research for storage technology the technology like of the SAN(Storage Area Network) advantages in scalibility of storage devices, and can read data from multiple disk arrays through RAID 0, 5. The RAID 0 and 5 translate to logical address to physical address using equation, but in case of adding disks at the system with equation -based mapping, the problem that we must rearrange the whole data in the previous disks happens. We use the mapping table to solve this problem in recent, but we can not load the whole mapping table in main memory because it occupies too large space. Therefore the extra I/Os are demanded to evaluate real physical address of data, so total performance of the system is degraded. In this paper, we propose the mapping method that supports the scalibility in RAID 0 or 5 system. The proposing method applies small metadata, so- called SZIT and simple equation, so it is possible that we make translate logical address to physical address rapidly and it is scalable in disk extending simultaneously Our suggesting method, if we add disks to the striping system for expanding of storage capacity, has an advantage of never stop service. So, SZlT-based mapping method can do online-disk-expanding in real-time service.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.7
• /
• pp.624-628
• /
• 2008

This paper is concerned with multiple motor control using a distributed network control method. Speed and position of multiple motors are synchronized using clock synchronized distributed controllers. CAN (controller area network) is used and a new clock synchronization algorithm is proposed and implemented. To verify the proposed control algorithm, two disks which are attached on two motor shafts are controlled to rotate at the same speed and phase angle with the same time base using network clocks.

• Journal of Korea Spatial Information System Society
• /
• v.7 no.2 s.14
• /
• pp.81-89
• /
• 2005

Declustering and parallel index structures are important research areas to improve a performance of databases. Previous researches proposed several distribution schemes for parallel R-trees, however there is no search schemes to be suitable for the index. In this paper, we propose schemes to improve the performance of range queries for distribute parallel indexes. The proposed schemes use the features that a parallel disk can read multiple nodes from various disks. The proposed schemes are verified using various implementations and performance evaluations. We propose new schemes which can read multiple nodes from multiple disks in contrast that to the previous schemes which can read a node from disk. The experimental evaluation shows that the proposed schemes give us the performance improvement by 40% from the previous researches.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.140.2-140.2
• /
• 2012

The silicate carbon star IRAS 09425-6040 shows very conspicuous crystalline silicate dust features and excessive emission at far infrared. To investigate properties of dusty envelopes around the object, we use radiative transfer models for axisymmetric and sphericallly symmetric dust distributions. We perform model calculations for various possible combinations of dust shells and disks with various dust species. We compare the model results with the observed spectral energy distributions (SEDs) including the IRAS, ISO, AKARI, MSX and 2MASS data. We find that a model with multiple disks of amorphous and crystalline silicate and multiple spherical shells of carbon dust can reproduce the observed SED fairly well. This supports the scenario for the origin of silicate carbon stars that oxygen-rich material was shed by mass loss when the primary star was an M giant and the O-rich material is stored in a circumbinary disk. Highly (about 75 %) crystallized forsterite dust in the disk can reproduce the conspicuous crystalline features of the ISO observational data. This object looks to have a detached silicate and H2O ice shell with a much higher mass-loss rate. It could be a remnant of the chemical transition phase. The last phase of stellar winds of O-rich materials looks to be a superwind.

• The Journal of Society for e-Business Studies
• /
• v.14 no.1
• /
• pp.143-160
• /
• 2009

In determining the performance of OLAP database applications, the structure and the effective access methods to the underlying disk system is a significant factor. In recent years, hard disks are designed with multiple physical zones where seek times and data transfer rates vary across the zones. However, there is little consideration of multi-zone disks in previous works. Instead, they assumed a traditional disk model that comes with many simplifying assumptions such as an average seek-time and a single data transfer rate. In this paper, we propose a technique storing a set of materialized views into the multi-zoned disks in OLAP environment dealing with large sets of data. We first present the disk zoning algorithm of materialized views according to the access probabilities of each views. Also, we address the problem of storing views in the dynamic environment where data are updated continuously. Finally, through experiments, we prove the performance improvement of the proposed algorithm against the conventional methods.