• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.321-328
• /
• 2008

In this paper, we analyze web response time depending on queue managements and transmission latencies in highly congested network situation. Under FIFO scheme, the response times are for three different sizes of queue are almost the same, but the response time increases as traffic intensity increases. The performance between different queue sizes shows more different in 90% and 98% traffic intensity than in 80% traffic intensity. Especially the difference becomes bigger in short latency case than long latency case. Under RED scheme, three differently tunned RED schemes do not impact on the response time when the size of queue is relatively large. When the queue size becomes smaller, the response time of the differently tunned RED schemes becomes different for short latency case while the response times are almost same for long latency case. When comparing FIFO and RED schemes under same size of queue, RED scheme shows less response time than that of FIFO for the long latency case in high traffic intensity.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• 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.

• Journal of the Korea Society for Simulation
• /
• v.7 no.1
• /
• 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
• /
• v.20 no.1
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• 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
• /
• v.2 no.1
• /
• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.70-77
• /
• 2015

In this paper, we present experimental results evaluating the performance of the Multipath TCP over shared bottleneck path in series of benchmark tests. In summary, we find that the Multipath TCP's fairness as well as its competitive responds to the change of network conditions such as latency, loss rate${\cdots}$ MPTCP is extremely unfair and powerful with regular TCP in ideal network conditions but its throughput decreases clearly even less than regular TCP in worse network conditions with very high latency, higher packet loss rate.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.591-593
• /
• 2022

This paper proposes a partial offloading system for minimizing application service processing latency in an FEC (Fog/Edge Computing) environment, and it analyzes the offloading effect of the proposed system against local-only and edge-server-only processing based on network load. A partial offloading algorithm based on reconstruction linearization of multi-branch structures is included in the proposed system, as is an optimal collaboration algorithm between mobile devices and edge servers [1,2]. The experiment was conducted by applying layer scheduling to a logical CNN model with a DAG topology. When compared to local or edge-only executions, experimental results show that the proposed system always provides efficient task processing strategies and processing latency.

• KNOM Review
• /
• v.22 no.3
• /
• pp.13-19
• /
• 2019

Network anomaly detection is a technology that collects information about flows on a network and detects malicious attacks occurring in a network in real time. In-band Network Telemetry (INT) technology provides more detailed information in real time, that is not provided by existing networks, such as hop latency and queue occupancy. In this paper, we propose the method to implement an anomaly detection system with higher performance by using INT as an input feature of machine learning and verify it through experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.4
• /
• 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.