• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.939-948
• /
• 1997

In this paper, we propose the new rate-based transmission rates control algorithm that allocates the fair band-width for ABR service in ATM network. In the traditional ABR service, bandwidth is allocated with constant rate increment or decrement, but in the proposed algorithm, it is allocated fairly to the connected calls by the fuzzy inference of the available bandwidth. The fuzzy inference uses buffer state and the buffer variant rate as the input variables, and uses the total transmission rate as a output variable. This inference a bandwidth is fairly distributed over all ABR calls in service. By simmulation, we showed that the proposed method improved 0.17% in link effectiveness when RIF, RDF is 1/4, 38.6% when RIF, RDF 1/16, and 82.4% when RIF, RDF 1/32 than that of the traditional EFPCA.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.697-708
• /
• 1996

In this paper, we study reactive congestion control with priority in ATM network. The priority schemes for buffer access, partial buffer sharing have been investigated in order to improve the utilization of ATM network resources the network and to satisfy the most demanding traffic class. We consider in this paper a discrete-time queueing model for partial buffer sharing with two Markov modulated Poisson inputs. This model can be used to analyze the the effects of the partial buffer sharing priority scheme on system performance for realistic cases of bursty services. Explicit formulae are derived for the number of cells in the system and the loss probabilities for the traffic. Congestion may still occur because of unpredictable statistical fluctuation of traffic sources even when preventive control is performed in the network. In this Paper, we study reactive congestion control, in which each source changes its cell emitting rate a daptively to the traffic load at the switching node. Our intention is that,by incorporating such a congcstion control method in ATM network,more efficient congsestion control is established. We develope an analytical model,and carry out an approximateanalysis of reactive congestion con-trol with priority.Numerical results show that several orders of magnitude improvement in the loss probability can be achieved for the high priority class with little impact on the low priority class performance.And the results show that the reactive congestion control with priority are very effective in avoiding congestion and in achieving the statistical gain.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.2
• /
• pp.90-102
• /
• 2010

Flash memory has been widely used as an important storage device for consumer electronics. For the flash memory-based storage systems, FTL (Flash Translation Layer) is used to handle the mapping between a logical page address and a physical page address. Especially, log buffer-based FTLs provide a good performance with small-sized mapping information. In designing the log buffer-based FTL, one important factor is to determine the mapping structure between data blocks and log blocks, called associativity. While previous works use static associativity fixed at the design time, we propose a new log block mapping scheme which adjusts associativity based on the run-time workload. Our proposed scheme improves the I/O performance about 5~16% compared to the static scheme by adjusting the associativity to provide the best performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.105-112
• /
• 2011

We propose an adaptive load balancing scheme to transport real-time video streams efficiently in this paper. The playback buffer level of a video requesting client is high or low temporarily in mobile environment. This scheme attempts to allocate more network bandwidth to serve a video request with the lower buffer level preferentially. In this scheme, the amount of network bandwidth is dynamically allocated to the requesting clients according to their playback buffer levels in a distributed mobile system. In order to improve the quality of service and real-time performance of individual video playback, the proposed load balancing scheme tries to maximize the number of frames that are transported successfully to the client prior to their playback times. Fair services can also be provided to all the concurrent clients by making their playback situation more adaptive. The performance of this load balancing scheme is compared with that of other static load balancing scheme through extensive simulation experiments, resulting in the higher ratio of frames transmitted successfully within given deadlines.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.21-29
• /
• 2020

The use of NAND flash memory is continuously increased with the demand of mobile data in the IT industry environment. However, the erase operations in flash memory require longer latency and higher power consumption, resulting in the limited lifetime for each cell. Therefore, frequent write/erase operations reduce the performance and the lifetime of the flash memory. In order to solve this problem, management techniques for improving the performance of flash based storage by reducing write and erase operations of flash memory with using disk buffers have been studied. In this paper, we propose a CPWL to minimized the number of write operations. It is a disk buffer management that separates read and write pages according to the characteristics of the buffer memory access patterns. This technique increases the lifespan of the flash memory and decreases an energy consumption by reducing the number of writes by arranging pages according to the characteristics of buffer memory access mode of requested pages.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.4
• /
• pp.1076-1088
• /
• 1997

Data repliciation techniques of distributed database a allocation methods occures to overhead to change together all repkicas for consistency maintenance at updates .In case of data migration horizontal or vertical fragment migration has caused to caused to increase data communication.In this paper we purpose batch proxessing method groups the associated items of table and stores temporary table assciated with file relication and migrations.This method increase the usagility of system buffer in distributed trancsaction processing with a number of data inputs and updates.After all,it improved the perform-ance of distributed transaction system by reducing disk I\O processing time and the cost of data cimmunication among local sites.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9B
• /
• pp.813-821
• /
• 2008

In recent year, several types of PON(Passive Optical Networks) have been adopted into the subscriber loops for the high speed subscriber lines to meet the needs of some applications based on the Internet and the rapid increase of the Internet users. GPON(Gigabit PON) is a typical access network technology of these PONs which adopt the DBA(Dynamic bandwidth Allocation) scheme in order to transmit upstream traffic efficiently. In this paper, we introduce the gated polling system with a two-stage queue in order to analyze the delay performance of the DBA scheme in a GPON. We use a continuous time queueing model for deriving the mean cycle time and for obtaining the mean packet delay. We give some numerical results to investigate the delay performance for the symmetric polling system with statistically identical stations.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.81-89
• /
• 2014

The heterogeneous LTE-Advanced networks comprising a macrocell and femtocells can provide an efficient solution not only to extend macrocell coverage but also to deal with packet traffics increasing explosively within macrocells. Efficient resource management schemes are necessary to maintain the QoS requirements of versatile multimedia applications in LTE-Advanced networks because their service-continuity may be defected by some delay and information loss. In this paper, we propose a resource allocation method for the heterogeneous LTE-Advancedl networks overlaid with femtocells. Performances are analyzed by simulation.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.2 s.302
• /
• pp.11-20
• /
• 2005

In previous video conference system, when the number of participants in video conference increases by n, the bandwidth and memory of n2 is required. And also, it brings about increase in traffic and problem of a say during a conference in aspect of transmission of voice data. In this paper, we propose an algorithm of remote video conference using silence detection algerian to resolve the questions such as buffering method of video data in server and heavy traffic detection algorithm to the increase in participants. Video data buffering algorithm is not a method of broadcasting to other client in the server, but this algorithm uses two other methods; the buffering method of receiving compressed video data from clients and the indexing method for acquiring the video data of other participants in clients according to clients' bandwidth and network transmission speed. We apply a voice transmission algerian and a channel management algorithm to the remote video conference system. The method used in the voice transmission algorithm is a silence detection algorithm which does not send silent participants' voice data to the server. The channel management algorithm is a method allocating a say to the participants who have priority. In consideration of average 20 frames and 30ms regardless of a number of participants, we can safely conclude that the transmission of video and voice data is stable.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.304-313
• /
• 2016

We present a novel memory-efficient parallel ray casting algorithm for unstructured grid volume rendering on multi-core CPUs. Our method is based on the Bunyk ray casting algorithm. To solve the high memory overhead problem of the Bunyk algorithm, we allocate a fixed size local buffer for each thread and the local buffers contain information of recently visited faces. The stored information is used by other rays or replaced by other face's information. To improve the utilization of local buffers, we propose an image-plane based ray grouping algorithm that makes ray groups have high coherency. The ray groups are then distributed to computing threads and each thread processes the given groups independently. We also propose a novel hash function that uses the index of faces as keys for calculating the buffer index each face will use to store the information. To see the benefits of our method, we applied it to three unstructured grid datasets with different sizes and measured the performance. We found that our method requires just 6% of the memory space compared with the Bunyk algorithm for storing face information. Also it shows compatible performance with the Bunyk algorithm even though it uses less memory. In addition, our method achieves up to 22% higher performance for a large-scale unstructured grid dataset with less memory than Bunyk algorithm. These results show the robustness and efficiency of our method and it demonstrates that our method is suitable to volume rendering for a large-scale unstructured grid dataset.