• The KIPS Transactions:PartC
• /
• v.14C no.2
• /
• pp.155-162
• /
• 2007

WFQ (Weighted Fair Queuing) is the most popular fair queuing algorithm, but it had the inherent drawback of a poor bandwidth utilization, particularly under the traffic requiring a low rate but tight delay bound such as internet phone, It was recently identified that the poor utilization is mainly due to non optimized latency of a flow and then LOFQ(Latency-Optimized Fair Queuing) to overcome the drawback was introduced, LOFQ was also improved through introducing an occupied resource optimization function and the implementation complexity of recursive resource transformation was reduced with revising the transformation scheme. However, the performance of LOFQ has been evaluated by means of simulation, so that there are some difficulties in evaluating the performance in the terms of the accuracy and evaluation time, In this paper, we develop how to analytically compute the bandwidth utilization in LOFQ.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1091-1096
• /
• 2015

In this paper, WiMedia Distributed-MAC protocol is adopted for development of multi-hop N-screen wireless services. Furthermore, to provide the multi-hop OSMU (One Source Multi Use) N-screen service through P2P streaming in the D-MAC protocol, a new multi-hop resource reservation scheme is proposed and analyzed to reduce end to end delay. For this Multi-hop resource reservation scheme, a new MSCDRP (Multi-Stage Cooperative DRP) IE is proposed. Simulation results show that our multi-hop MSCDRP scheme reduces the end to end delay and increases throughput at various multi-hop N-screen network environment.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.12a
• /
• pp.121-129
• /
• 1999

When continuous media are transmitted over the communication networks, asynchrony which can not maintain temporal relationships among packets may occur due to a random transit delay. There exist two types of synchronization schemes ; for guaranteed or non-guaranteed resource networks. The former which applies a resource reservation technique maintains delay characteristics, however, the latter supply a best-effort service. In this paper, I propose a intra-media synchronization scheme to transmit continuous media on general networks not guaranteeing a bounded delay tome. The scheme controls transmission times of the packets by estimating next delay time with the delay distribution. So, the arriving packets may be maintained within a limited delay boundary, and playout will be performed after buffering to smoothen small delay variations. The continually increasing delay due to network overload causes buffer underflow at the receiver. To solve it, the transmitter is required to speed up instantaneously. Too much increase of transmission-rate may cause network congestion. At that time, the transmitter drops the current packet when informed excessive delay from the receiver.

• International journal of advanced smart convergence
• /
• v.13 no.3
• /
• pp.109-116
• /
• 2024

With the advent of serverless computing, cloud customers no longer needed to maintain and manage server environments directly. Instead, cloud service providers took on that role, managing and maintaining the server environment according to customer requests, a concept known as Function as a Service (FaaS). This service demonstrated improvements in operational costs and resource utilization over traditional cloud computing, offering various advantages such as enhanced scalability. However, a delay occurred in processing and returning results to user requests, a phenomenon referred to as the cold start problem. This paper proposed the Time Warming Allocation Engine (TWAE) to improve resource management and mitigate the cold start problem in Function as a Service. The proposed engine comprised a collection module, a learning module, a classification module, and an allocation module. Additionally, it utilized a list called Pre-Warming. Through this approach, it suggested directions for improving cold start issues and resource utilization according to different time periods.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.2
• /
• pp.1-9
• /
• 2020

Many cryptographic and error control coding algorithms rely on finite field GF(2m) arithmetic. Hardware implementation of these algorithms needs an efficient realization of finite field arithmetic operations. Finite field multiplication is complicated among the basic operations, and it is employed in field exponentiation and division operations. Various algorithms and architectures are proposed in the literature for hardware implementation of finite field multiplication to achieve a reduction in area and delay. In this paper, a low area and delay efficient semi-systolic multiplier over finite fields GF(2m) using the modified Montgomery modular multiplication (MMM) is presented. The least significant bit (LSB)-first multiplication and two-level parallel computing scheme are considered to improve the cell delay, latency, and area-time (AT) complexity. The proposed method has the features of regularity, modularity, and unidirectional data flow and offers a considerable improvement in AT complexity compared with related multipliers. The proposed multiplier can be used as a kernel circuit for exponentiation/division and multiplication.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.166-167
• /
• 2012

High packet loss rate and impatience of messages passing through optical switches are essential characteristics in Optical Burst Switching system equipped with Optic Delay Lines buffer, which have not been solved efficiently yet by current existing models. In order to capture both effects, this paper introduces an analytical model from the viewpoint of classical queuing theory with impatient customers. We then apply it to evaluate and compare two wavelength-sharing cases, (1) all delay lines share a common wavelength resource and (2) each wavelength is associated with a number of delay lines. Our numerical results suggest to implement the first case because of lower packet loss rate for a fairly broad range of traffic load.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2020

This paper proposes acoustic model training using self-attention for low-resource speech recognition. In low-resource speech recognition, it is difficult for acoustic model to distinguish certain phones. For example, plosive /d/ and /t/, plosive /g/ and /k/ and affricate /z/ and /ch/. In acoustic model training, the self-attention generates attention weights from the deep neural network model. In this study, these weights handle the similar pronunciation error for low-resource speech recognition. When the proposed method was applied to Time Delay Neural Network-Output gate Projected Gated Recurrent Unit (TNDD-OPGRU)-based acoustic model, the proposed model showed a 5.98 % word error rate. It shows absolute improvement of 0.74 % compared with TDNN-OPGRU model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2B
• /
• pp.146-153
• /
• 2006

It is required to have researches on efficient resource allocation schemes in an integrated voice and data CDMA system with the spreading of high-speed wireless internets. In this paper, we proposed a efficient resouce allocation scheme for providing a high speed data service in an integrated CDMA system. In an integrated voice/data CDMA system, resources for voice users are allocated with high priority and residual resources are allocated to the data service. In this case, it is necessary to use a resource allocation scheme for minimizing interference. In this paper, we first explain about a interference minimizing method and define QoS requirements. Based on the method, we proposed a efficient resource allocation scheme which satisfy the QoS requirements. The proposed scheme controls the transmission rate and delay of data users with a priority information such as the number of packets in a queue. From the simulation results, we show that the proposed scheme reduce the blocking probability and delay and improve the performance.

• ETRI Journal
• /
• v.22 no.1
• /
• pp.30-37
• /
• 2000

Existing tree construction mechanisms are classified into source-based trees and center-based trees. The source-based trees produce a source-rooted tree with a low delay. However, for the applications with multiple senders, the management overheads for routing tables and resource reservations are too high. The center-based trees are easy to implement and manage, but a priori configuration of candidate center nodes is required, and the optimization mature such as tree cost and delay is not considered. In this paper, we propose a new multicast tree building algorithm. The proposal algorithm basically builds a non-center based shared tree. In particular, any center node is not pre-configured. In the purposed algorithm, a multicast node among current tree nodes is suitably assigned to each incoming user: Such a node is selected in a fashion that tree cost and the maximum end-to-end delay on the tree are jointly minimized. The existing and proposed algorithms are compared by experiments. In the simulation results, it is shown that the proposed algorithm approximately provides the cost saving of 30% and the delay saving of 10%, compared to the existing approaches. In conclusion, we see that the cost and delay aspects for multicast trees can be improved at the cost of additional computations.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.8
• /
• pp.937-949
• /
• 1988

This paper proposes a code optimization algorithm for dealing with hazards which are occurred in pipelined architecture due to resource dependence between executed instructions. This algorithm solves timing hazard which results from resource conflict between concurrently executing instructions, and sequencing hazard due to the delay time for branch target decision by reconstructing of instruction sequence without pipeline interlock. The reconstructed codes can be generated efficiently by considering timing hazard and sequencing hazard simultaneously. And dynamic execution time of program is improved by considering structral hazard which can be existed when pipeline is controlled dynamically.