• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3B
• /
• pp.171-182
• /
• 2003

In this paper, we propose an efficient and simple fair queueing algorithm, called Minimum Possible Virtual Start Time Fair Queueing (MPSFQ), which has O(1) complexity for the virtual time computation while it has good delay and fairness properties. The key idea of MPSFQ is that it has an easy system virtual time recalibration method while it follows a rate-proportional property. MPSFQ algorithm recalibrates system virtual time to the minimum possible virtual start time of all backlogged sessions. We will show our algorithm has good delay and fairness properties by analysis.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2608-2617
• /
• 1999

One of the most important functionality that commercial video storage servers should provide is to maximize the number of concurrent streams and to minimize the initial latency of new requests. In this paper, we propose a data placement scheme whose disk read unit size can be twice large than that of conventional striping methods. The proposed scheme can significantly increase the number of concurrent streams, since the ratio of rotational latency time is decreased and the disks are effectively utilized. The disk scheduling scheme we propose guarantees constant initial latency time. We also propose a procedural design method for a storage server by introducing the concept of allowed initial latency. The comparison with previous research shows that the proposed scheme provides better performance.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1781-1787
• /
• 1997

Future high speed networks are expected to use the Asynchronous Transfer Mode(ATM), which provides desired quality of service for the various traffic types(e.g., voice, video and data). Proper traffic control scheme helps ensure efficient and fair operation of networks. In this paper, we analyze various related traffic-control strategies and propose a new traffic control scheme and ATM control architecture with an integrated buffer management method and multi-thresholds in order to solve the problem of each class's cell loss ratio and cell delay in ATM networks. In addition, we evaluate the performance improvement of the proposed traffic control scheme through simulation. As shown in the result, the proposed traffic control scheme improves cell loss ratio in proportion to the buffer size.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3113-3118
• /
• 2000

A framework proposed in this paper includes representations of multi-objectives rule-basd constraint satisfaction problem(RCSP) and especially, flexible structure of RCSP which provides adequate solution sithin an expectation time and adaptively considers some change of constratraints on the RCSP. In this study, the power system implemented by above framework is entirely programmed by using a modeling system for the quantitative model and a rule-based constraint programming tool for the qualitative model. The results of an exemplary cse show how the structure that involves the problem representation gives the scheduler an effective decision and what are the advantages of the easy and diverse representation for considering the techmical characteristics of the units on the RCSP over the traditional problem.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2779-2789
• /
• 1999

In this paper, we propose a new neural Buffered Leaky Bucket algorithm for preventing the degradation of network performance caused by congestion and dealing with the traffic congestion in ATM networks. We networks. We justify the validity of the suggested method through performance comparison in aspects of cell loss rate and mean transfer delay under a variety of traffic conditions requiring the different QoS(Quality of Service). also, the cell scheduling algorithms such as DWRR and DWEDF used for multiplexing the incoming traffics are induced to get the delay time of the traffics fairly. The network congestion information from cell scheduler is used to control the predicted traffic loss rate of Neural Leaky Bucket, and token generation rate is changed by the predicted values. The prediction of traffic loss rate by neural networks can effectively reduce the cell loss rate and the cell transfer delay of next incoming cells and be applied to other traffic control systems. Computer simulation results performed for traffic prediction show that QoSs of the various kinds of traffics are increased.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12C
• /
• pp.181-189
• /
• 2001

In this thesis, a policing algorithm is proposed, which is one of the traffic management function in ATM networks. The proposed algorithm minimizes CLR(Cell Loss patio) of high priority cells and solves burstiness problem of the traffic caused by multiplexing and demultiplexing process. The proposed algorithm has been implemented with VHDL and is divided into three parts, which are an input module, an UPC module, and an output module. In implementation of the UPC module\`s memory access, memory address is assigned according to VCI\`s LSB(Lowest Significant Byte) of ATM header for convenience. And the error of VSA operation from counter\`s wrap-around can be recovered by the proposed method. ANAM library 0.25 $\mu\textrm{m}$ and design compiler of Synopsys are used for synthesis of the algorithm and Synopsys VSS tool is used for VHDL simulation of it

• The KIPS Transactions:PartC
• /
• v.12C no.2 s.98
• /
• pp.183-190
• /
• 2005

In this thesis, first, we propose I-frame encryption techniques of video data for video data itself encryption and propose license agent that processing user's certification and decryption in client system automatically when user execute encrypted video data in system server. License agent runs user's certification, encryption and decryption of video data based on PID(Public Key Infrastructure) using shared key-pool when execute of video data. Also, compose duplex buffer control and propose real time decryption method using efficient buffer scheduling to reduce much playing delay times that happen processing decryption when execute of videoa data of high-capacity.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.2
• /
• pp.497-511
• /
• 1999

Recently, many parallel processing technologies were developed, ILP(Instruction level Parallelism) processor's performance have been growed very rapidly. especially, EPIC(Explicitly Parallel Instruction computing) architectures attempt to enhance the performance in the predicated execution and speculative execution with the hardware. In this paper to improve the code scheduling possibility by applying to the characteristics of EPIC architectures, a new register allocation algorithm is proposed. And we proves that proposed register allocation algorithm is more efficient scheme than the conventional scheme when predicated execution is applied to our scheme by experiments. In experimental results, it shows much more performance enhancement, about 19% in proposed scheme than the conventional scheme. So, our scheme is verified that it is an effective register allocation method.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2008.05a
• /
• pp.285-287
• /
• 2008

AAO(Anodic Aluminum Oxidation) method has been known that it is practically useful for the fabrication of nano-structures and makes it possible to fabricate the highly ordered nano masters on large surface and even on the 2.5 or 3D surface at low cost comparing to the expensive e-beam lithography or the conventional silicon processing. In this study, by using the multi-step anodizing and etching processes, highly ordered nano patterned master with concave shapes was fabricated. By varying the processing parameters, such as initial matter and chemical conditions; electrical and thermal conditions; time scheduling; and so on, the size and the pitch of the nano pattern can be controlled. Consequently, various alumina/aluminum nano structures can be easily available in any size and shape by optimized anodic oxidation in various aqueous acids. In order to replicate nano patterned master, the resulting good filled uniform nano molded structure through electro-forming process shows the validity of the fabricated nano pattern masters.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.3
• /
• pp.379-390
• /
• 2005

Intensive studies have been made in the area of VOD server Multimedia files in the VOD sever are characterized with the large volume of data, the requirements of synchronization and real-time playback of streams. The basic goal of the study is to find an efficient mechanism to allow maximum number of users under the limited resources such as Buffer size and disk bandwidth. we propose a efficient $pre\_fetching$ policy for multimedia services with dynamic monitoring and management of VOD sever resources. Simulation results show that the rate of buffer usage and service time of proposed scheme are about $28\%$ performance improved than that of traditional methods. This implies that our method can allow much more users for given resources.