• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.5948-5971
• /
• 2019

Estimating loss rates with the packet traces captured from some point in the middle of the network has received much attention within the research community. Meanwhile, existing intermediate-point methods like [1] require the capturing system to capture all the TCP traffic that crosses the border of an access network (typically Gigabit network) destined to or coming from the Internet. However, limited to the performance of current hardware and software, capturing network traffic in a Gigabit environment is still a challenging task. The uncaptured packets will affect the total number of captured packets and the estimated number of packet losses, which eventually affects the accuracy of the estimated loss rate. Therefore, to obtain more accurate loss rate, a method of strengthening packet loss measurement from the network intermediate point is proposed in this paper. Through constructing a series of heuristic rules and leveraging the binomial distribution principle, the proposed method realizes the compensation for the estimated loss rate. Also, experiment results show that although there is no increase in the proportion of accurate estimates, the compensation makes the majority of estimates closer to the accurate ones.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.2
• /
• pp.141-156
• /
• 2009

As the TCP is the protocol designed for the wired network that packet loss probability is very low, because TCP transmitter takes it for granted that the packet loss by the wireless network characteristics is occurred by the network congestion and lowers the transmitter's transmission rate, the performance is degraded. The Snoop Protocol was designed for the wired network by putting the Snoop agent module on the BS(Base Station) that connect the wire network to the wireless network to complement the TCP problem. The Snoop agent cash the packets being transferred to the wireless terminal and recover the loss by resending locally for the error occurred in the wireless link. The Snoop agent blocks the unnecessary congestion control by preventing the dupack (duplicate acknowledgement)for the retransmitted packet from sending to the sender and hiding the loss in the wireless link from the sender. We evaluated the performance in the wired/wireless network and in various TCP versions using the TCP designed for the wired network and the Snoop designed for the wireless network and evaluated the performance of the wired/wireless hybrid network in the wireless link environment that the continuous packet loss occur.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.472-474
• /
• 2019

Because of the difference in network structure and loss function, Verification and identification models have their respective advantages and limitations for person reidentification (re-ID). In this work, we propose a multi-task network simultaneously computes the identification loss and verification loss for person reidentification. Given a pair of images as network input, the multi-task network simultaneously outputs the identities of the two images and whether the images belong to the same identity. In experiments, we analyze the major factors affect the accuracy of person reidentification. To address the occlusion problem and improve the generalization ability of reID models, we use the Random Erasing Augmentation (REA) method to preprocess the images. The method can be easily applied to different pre-trained networks, such as ResNet and VGG. The experimental results on the Market1501 datasets show significant and consistent improvements over the state-of-the-art methods.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.274-285
• /
• 2022

Retransmission in optical burst switching networks is a solution to recover data loss by retransmitting the dropped burst. The ingress node temporarily stores a copy of the complete burst and sends it each time it receives a retransmission request from the core node. Some retransmission schemes have been suggested, but uncontrolled retransmission often increases the network load, consumes more bandwidth, and consequently, increases the probability of contention. Controlled retransmission is therefore essential. This paper proposes a new controlled retransmission scheme for loss recovery, where the available bandwidth of wavelength channels and the burst lifetime are referred to as network conditions to determine whether to transmit a dropped burst. A retrial queue-based analysis model is also constructed to validate the proposed retransmission scheme. The simulation and analysis results show that the controlled retransmission scheme is more efficient than the previously suggested schemes regarding byte loss probability, successful retransmission rate, and network throughput.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4572-4586
• /
• 2019

Mobile Edge Computing (MEC) and Information-Centric Networking (ICN) are essential network architectures for the future Internet. The advantages of MEC and ICN such as computation and storage capabilities at the edge of the network, in-network caching and named-data communication paradigm can greatly improve the quality of video streaming applications. However, the packet loss in wireless network environments still affects the video streaming performance and the existing loss recovery approaches in ICN does not exploit the capabilities of MEC. This paper proposes a Deep Learning based Loss Recovery Mechanism (DL-LRM) for video streaming over MEC based ICN. Different with existing approaches, the Forward Error Correction (FEC) packets are generated at the edge of the network, which dramatically reduces the workload of core network and backhaul. By monitoring network states, our proposed DL-LRM controls the FEC request rate by deep reinforcement learning algorithm. Considering the characteristics of video streaming and MEC, in this paper we develop content caching detection and fast retransmission algorithm to effectively utilize resources of MEC. Experimental results demonstrate that the DL-LRM is able to adaptively adjust and control the FEC request rate and achieve better video quality than the existing approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3150-3171
• /
• 2018

In this paper, a heuristic method that leverages packet traces captured at the entire boarder of an ISP to distinguish and estimate the overall packet loss within an ISP's management domain (Intra_Path_Loss) and that in the outside Internet (Inter_Path_Loss) is proposed. Our method is inspired by that packet losses happened at different locations will cause different TCP sequence number patterns at the border of an ISP. Thereby, we leverage these TCP sequence number patterns to build a series of heuristic rules to estimate Intra_Path_Loss and Inter_Path_Loss, respectively. We do this work with an eye towards showing that the overall packet losses defined and estimated in this paper can provide the operators with some valuable information to help them precisely grasp the overall performance of network paths and narrow down the range of network anomalies. The proposed method is rigorously validated with simulations, and finally the results from a regional academic network JSERNET verify its effectiveness and practicability.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.6
• /
• pp.284-289
• /
• 2002

The transmission networks do not consist of perfect conductors and a percentage of the power generated is therefore lost before it reaches the loads. Since this network loss contributes to the cost of suppling power to consumers, it must be considered that the most efficient dispatch and location of generators and loads are to be achieved. In this paper, marginal loss factors are calculated for 12 load levels that represent the impact of marginal network losses on nodal prices at the transmission network connection points at which generators are located. Based on comparison analysis of marginal loss factors on 12 load levels, we found the MLF characteristics in KOREA.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.451-453
• /
• 2019

Recently, as the use of wireless communication devices has increased, the wireless network usage has increased, and a wired network and a wireless network have been mixed to form a network. Existing TCP algorithms are designed for wired networks. Therefore, in the modern network environment, packet loss can not be accurately distinguished and improper congestion control is performed, resulting in degradation of TCP performance. In this paper, we propose SLDA (Support Vector Machine based Loss Discrimination Algorithm) which can accurately classify the packet loss environment to improve TCP performance and evaluate its performance.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of information and communication convergence engineering
• /
• v.13 no.1
• /
• pp.7-14
• /
• 2015

In a multi-hop wireless network, connectivity is determined by the link that is established by the receiving signal strength computed by subtracting the path loss from the transmission power. Two path loss models are commonly used in research, namely two-ray ground and shadow fading, which determine the receiving signal strength and affect the link quality. Link quality is one of the key factors that affect network performance. In general, network performance improves with better link quality in a wireless network. In this study, we measure the network connectivity and performance in a shadow fading path loss model, and our observation shows that both are severely degraded in this path loss model. To improve network performance, we propose power control schemes utilizing link quality to identify the set of nodes required to adjust the transmission power in order to improve the network throughput in both homogeneous and heterogeneous multi-hop wireless networks. Numerical studies to evaluate the proposed schemes are presented and compared.