• 정보처리학회논문지C
• /
• 제15C권4호
• /
• pp.321-328
• /
• 2008

본 논문에서는, 혼잡 망에서의 큐 제어 방식과 전송 지연 시간에 대한 웹 반응 시간을 분석하였다. FIFO 방식에서는, 웹 반응 시간이 큐 크기에 대해서 거의 일정한 성능을 보여주었으나, 트래픽 부하가 높아질수록 웹 반응 시간은 길어졌다. 80%의 트래픽 부하보다, 90%와 98%의 트래픽 부하일 경우에, 큐 크기가 달라짐에 따라 웹 반응 시간이 더 뚜렷하게 다르게 나타났다. 특히 전송 지연 시간이 짧을 경우, 웹 반응 시간의 차이가 더욱 뚜렷하게 나타났다. RED 방식에서는, 상대적으로 큰 큐 크기일 경우, 3가지 서로 다른 설정의 RED 방식이 웹 반응 시간에 뚜렷한 영향을 미치지 못하였다. 큐 크기가 작아졌을 경우, 짧은 전송 지연에 대하여 각 RED 방식의 웹 반응 시간이 서로 뚜렷하게 다르게 나타났다. FIFO와 RED의 비교에서, 긴 전송 지연 시간일 경우, RED 방식이 FIFO보다 작은 웹 반응 시간을 보여주었다.

• 한국멀티미디어학회논문지
• /
• 제8권6호
• /
• pp.798-806
• /
• 2005

In this paper, we suggest a game system that can support network modules for multi-platform based video games, and built a system that can convert from a single-user game to multi-user game. In this system, we bring in an initial delay buffering scheme on clients to handle any periods of latency occurring from the load fluctuation in a network, when a real-time game is played, and shows that stable play for a game is achieved as the result of the scheme. This paper also presents a retransmission algorithm based on the history of game commands to handle drawbacks of UDP mechanism. And, we evaluate the network delay and packet loss using the simulation tool NS2, and shows the case of 0.3 second buffer delay is the most suitable for recovery.

• 한국시뮬레이션학회논문지
• /
• 제7권1호
• /
• pp.1-14
• /
• 1998

In this paper, we propose an efficient network communication scheme tailored to the network virtual reality(NVR) system. We first present the architecture and implementation of CVRAT (collaborative virtual reality authoring tool). The design goal of CVRAT is to provide consistent and scalable shared virtual environments. To achieve this goal, we classify the network messages according to their reliability and latency requirements. These conflicting requirements lead us to conceive a heterogeneous communication scheme which provides the unicast and three different multicast transport services; unreliable multicast, receiver-driven reliable multicast, fast reliable multicast. Each protocol has trade-offs in reliability, latency and bandwidth usage. The characteristics are analyzed by several experiments. Finally, applying this communication method to multi-participant battle-field tank simulation, we show the efficacy of proposed heterogeneous transport mechanism.

• Journal of information and communication convergence engineering
• /
• 제20권1호
• /
• pp.8-15
• /
• 2022

The new 5G radio technology (NR) can provide ultra-reliable low latency communications. The supporting 5G network infrastructure will move away from the previous point-to-point network architecture to a service-based architecture. 5G can provide three new things, i.e., wider channels, lower latency and more bandwidth. These will allow 5G to support three main types of connected services, including enhanced mobile broadband, mission-critical communications, and the massive Internet of Things (IoT). In 2015, the 5th generation (5G) mobile communication was officially approved by the International Telecommunication Union (ITU) as IMT-2020. Since then, 3GPP, the international organization responsible for 5G standards, is actively developing specifications for 5G technologies. 3GPP Release 15 provides the first full set of 5G standards, and the evolution and expansion of 5G are now being standardized in Release 16 and 17, respectively. This paper provides an overview of 3GPP 5G technologies and key services.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.878-879
• /
• 2021

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.

• Journal of Information Processing Systems
• /
• 제2권1호
• /
• pp.39-43
• /
• 2006

In this paper, we proposed TASL-MAC, a medium-access control (MAC) protocol for wireless sensor networks. In wireless sensor networks, sensor nodes are usually deployed in a special environment, are assigned with long-term work, and are supported by a limited battery. As such, reducing the energy consumption becomes the primary concern with regard to wireless sensor networks. At the same time, reducing the latency in multi-hop data transmission is also very important. In the existing research, sensor nodes are expected to be switched to the sleep mode in order to reduce energy consumption. However, the existing proposals tended to assign the sensors with a fixed Sleep/Listening schedule, which causes unnecessary idle listening problems and conspicuous transmission latency due to the diversity of the traffic-load in the network. TASL-MAC is designed to dynamically adjust the duty listening time based on traffic load. This protocol enables the node with a proper data transfer rate to satisfy the application's requirements. Meanwhile, it can lead to much greater power efficiency by prolonging the nodes' sleeping time when the traffic. We evaluate our implementation of TASL-MAC in NS-2. The evaluation result indicates that our proposal could explicitly reduce packet delivery latency, and that it could also significantly prolong the lifetime of the entire network when traffic is low.

• 한국통신학회논문지
• /
• 제40권1호
• /
• pp.70-77
• /
• 2015

본 논문에서는 TCP와 병목 링크(bottleneck link)를 공유하는 MPTCP(Multipath TCP)의 성능을 실험을 통해서 측정하고 결과를 제시하였다. 실험을 통해서 MPTCP의 공정성(fairness)과 성능은 지연, 패킷 손실 등과 같은 전체 네트워크의 조건에 크게 영향을 받는다는 것을 알 수 있었다. 이상적인 일반적인 네트워크 조건에서 MPTCP는 TCP보다 상대적으로 성능이 높아서 TCP와 불공정(unfair) 하지만, 네트워크의 지연이 증가하고 패킷 손실이 증가함에 따라 처리율(throughput)이 감소하며 TCP보다도 처리율이 감소하는 것을 알 수 있었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.591-593
• /
• 2022

본 논문은 FEC 환경에서 응용 서비스의 처리 지연시간 최소화를 위하여 선행연구 제안한 부분 오프로딩 시스템의 네트워크 부하에 따른 오프로딩의 효과를 분석한다. 모바일 장치와 FEC 서버 간의 2계층 협력 컴퓨팅 시스템으로 구성된 제안 시스템을 로컬 전용 및 에지 서버 전용 처리와 비교한다. 제안 시스템은 다중 분기구조의 재구성 선형화를 통한 부분 오프로딩 알고리즘[1]과 두 계층 간의 최적 협업 알고리즘[2]을 포함한다. 실험은 다중 분기구조의 DAG 토폴로지를 갖는 논리적 CNN 모델을 대상으로 계층 스케줄링을 적용하여 수행하였으며, 실험 결과 제안 시스템은 로컬이나 에지 전용 실행과 비교하여 항상 효율적인 작업 처리 전략 및 처리 지연시간을 제공함을 입증하였다.

• KNOM Review
• /
• 제22권3호
• /
• pp.13-19
• /
• 2019

네트워크 이상 상태 탐지는 네트워크 상의 플로우에 대한 정보를 수집하여 네트워크에서 발생하는 악의적인 공격을 실시간으로 탐지하는 기술이다. 실시간으로 패킷 단위의 세부적인 네트워크 정보를 제공하는 INT (In-band Network Telemetry) 기술을 이용하면 네트워크 홉 단위 지연 (hop latency)과 큐 점유율 (queue occupancy) 등 기존 네트워크에서 제공하지 않는, 보다 세부적인 정보를 실시간으로 수집 가능하여 네트워크 이상 상태 탐지에 활용할 수 있다. 본 논문에서는 INT를 이용하여 추출한 네트워크 상태 정보를 머신 러닝의 입력특징으로 사용하여 더 높은 성능을 가진 이상 상태 탐지 시스템을 구현하는 방법을 제안하고 이를 실험을 통해 검증한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.748-766
• /
• 2013

In this paper, we consider an infrastructure-vehicle-vehicle (I2V2V) based Vehicle Ad-hoc Networks (VANETs), where one base station multicasts data to d vehicular users with the assistance of r vehicular users. A Distributed Luby Transform (DLT) codes based transmission scheme is proposed over lossy VANETs to reduce transmission latency. Furthermore, focusing on the degree distribution of DLT codes, a Modified Deconvolved Soliton Distribution (MDSD) is designed to further reduce the transmission latency and improve the transmission reliability. We investigate the network behavior of the transmission scheme with MDSD, called MDLT based scheme. Closed-form expressions of the transmission latency of the proposed schemes are derived. Performance simulation results show that DLT based scheme can reduce transmission latency significantly compared with traditional Automatic Repeat Request (ARQ) and Luby Transform (LT) codes based schemes. In contrast to DLT based scheme, the MDLT based scheme can further reduce transmission latency and improve FER performance substantially, when both the source-to-relay and relay-to-sink channels are erasure channels.