• Electronics and Telecommunications Trends
• /
• v.39 no.5
• /
• pp.98-107
• /
• 2024

Applications such as artificial intelligence continue to grow in complexity and scale. Thus, the demand for scalable computing is increasing for achieving faster data processing and improved efficiency. This requirement has led to the development of memory-centric computing and high-speed fabric interconnection technologies. Memory-centric computing reduces the latency and enhances the system performance by shifting the focus from the central processing unit to the memory, whereas high-speed fabric interconnects enable efficient data transfer across various computing resources. Technologies such as Gen-Z, OpenCAPI, and CCIX have been integrated into the CXL (Compute Express Link) standard since 2019 to improve communication and cache coherence. Ethernet-based interconnects such as RoCE, InfiniBand, and OmniXtend also play a crucial role in providing high-speed data transfer and low latency. We explore the latest trends and prospects of these technologies, highlighting their benefits and applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.391-398
• /
• 2018

There are many problems caused by data sharing between general heterogeneous digital devices due to various interfaces. To solve this problem, this paper proposes heterogeneous data sharing with cloud service and mobile through D2D communication that supports communication between different devices. The proposed technique is used to reduce the load on the server to perform data synchronization. Also, in order to minimize data latency caused by data replication between different devices, a technique to enhance the speed of data writing with copying only the modified parts in the chunk list is adopted and cloud service model integrated with mobile environment is realized in order to minimize the network bandwidth consumed for synchronization for data sharing. Therefore, it is possible to share data in different spaces efficiently with maintaining data integrity and minimizing latency in data.

• Journal of Advanced Navigation Technology
• /
• v.18 no.1
• /
• pp.29-34
• /
• 2014

Data fusion techniques combine data from multiple radars and related information to achieve more accurate estimations than could be achieved by a single, independent radar. In this paper, we analyze delay and loss of packets to be processed by multiple radar and minimize data processing interval from centralized data processing operation as fusing multiple radar data. Therefore, we model radar network about central data fusion, and analyze delay and loss of packets inside queues on assuming queues respectively as the M/M/1/K using NS-2. We confirmed average delay time, processing fused multiple radar data, through the analysis data. And then, this delay time can be used as a reference time for radar data latency in fusion center.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.4 s.334
• /
• pp.9-18
• /
• 2005

This paper proposes the novel synchronous segmented bus architecture that has the pipeline bus architecture based on OCP(open core protocol) and the memory-oriented bus for MPEG system. The proposed architecture has bus architectures that support the memory interface for image data processing of MPEG system. Also it has the segmented hi-directional multiple bus architecture for multitasking processing by using multi -masters/multi - slave. In the scheme address of masters and slaves are fixed so that they are arranged for the location of IP cores according to operational characteristics of the system for efficient data processing. Also the bus architecture adopts synchronous segmented bus architecture for reuse of IP's and architecture or developed chips. This feature is suitable to the high performance and low power multimedia SoC systum by inherent characteristics of multitasking operation and segmented bus. Proposed bus architecture can have up to 3.7 times improvement in the effective bandwidth md up to 4 times reduction in the communication latency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.180-186
• /
• 2017

In this paper we propose a traffic aware Demand Wakeup MAC(TADW-MAC) protocol, in which low data delay and high throughput can be achieved, for wireless sensor networks. With the TADW-MAC protocol, the problem of the DW-MAC protocol, which schedules only one packet to deliver during the Sleep period in a multi-hop transmission is resolved. DW-MAC is not adequate for the applications such as object tracking and fire detection, in which busty data should be transmitted in a limited time when an event occurs [6-8]. When an event occurs, duty cycle can be adjusted in the TADW-MAC protocol to get less energy consumption and low latency. The duty cycle mechanism has been widely used to save energy consumption of sensor node due to idle listening in wireless sensor networks. But additional delay in packet transmission may be increased in the mechanism. Our simulation results show that TADW-MAC outperforms RMAC and DW-MAC in terms of energy efficiency while achieving low latency.

• Journal of Communications and Networks
• /
• v.18 no.3
• /
• pp.460-475
• /
• 2016

The existing Proxy Mobile IPv6 suffers from a long handover latency which in turn causes significant packet loss that is unacceptable for seamless realtime services such as multimedia streaming. This paper proposes an OpenFlow-enabled proxy mobile IPv6 (OF-PMIPv6) in which the control of access gateways is centralized at an OpenFlow controller of a foreign network. The proposed OF-PMIPv6 separates the control path from the data path by performing the mobility control at the controller, whereas the data path remains direct between a mobile access gateway and a local mobility anchor in an IP tunnel form. A group of simple OpenFlow-enabled access gateways performs link-layer control and monitoring activities to support a comprehensive mobility of mobile nodes, and communicates with the controller through the standard OpenFlow protocol. The controller performs network-layer mobility control on behalf of mobile access gateways and communicates with the local mobility anchor in the Proxy Mobile IPv6 domain. Benefiting from the centralized view and information, the controller caches the authentication and configuration information and reuses it to significantly reduce the handover latency. An analytical analysis of the proposed OF-PMIPv6 reactive and proactive handover schemes shows 43% and 121% reduction in the handover latency, respectively, for highly utilized network. The results gathered from the OF-PMIPv6 testbed suggest similar performance improvements.

• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.77-81
• /
• 2018

Many studies that improve the efficiency of data collection and a network's lifetime by using a mobile sink have been conducted using wireless sensor networks. If a drone is used as a mobile sink, the drone can collect data more efficiently than can existing mobile sinks operating on the ground because the drone can minimize the effects of obstacles and the terrain. In this paper, we propose a rendezvous node selection scheme which considers estimated drone's trajectory and data collection latency of sensor networks for reliable data collection, when a drone whose trajectory is not predetermined works with terrestrial wireless sensor networks. A selected rendezvous node on the ground collects data from the entire network and it sends then collected data to the drone via direct communication. We also verify that the proposed scheme is more reliable than previous schemes without considering the drone's trajectory and data collection latency.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.1
• /
• pp.78.2-78.2
• /
• 2014

Many techniques for data analysis also based on gaussian noise assumption which is often valid in various situations. However, the sensitivity of gravitational wave searches are limited by their non-gaussian and non-stationary noise. We introduce various on-going efforts to overcome this limitation in Korean Gravitational Wave Group. First, artificial neural networks are applied to discriminate non-gaussian noise artefacts and gravitational-wave signals using auxiliary channels of a gravitational wave detector. Second, viability of applying Hilbert-Huang transform is investigated to deal with non-stationary data of gravitational wave detectors. We also report progress in acceleration of low-latency gravitational search using GPGPU.

• Environmental and Resource Economics Review
• /
• v.12 no.1
• /
• pp.49-74
• /
• 2003

This study used a slightly modified version of contingent valuation questionnaire designed and developed by Krupnick et al.(2000) to estimate the value of mortality risk reduction for environmental policy. Because that environmental policy, especially air pollution policy with some latency main effect on mortality risk reduction of old people with some latency period, respondents were asked about their current WTP for 5/1,000 mortality risk reduction being to take place beginning at 70 over the course of ten years. The annual mean WTP is 233,370 won (standard error 32,570 won) in spike/continuous/interval data model. The implied VSL is 466 million won. The 95% confidence interval is 339 million won~594 million won.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.11
• /
• pp.2980-2991
• /
• 2012

Since wireless sensor networks are broadly used in various areas, there have been a number of protocols developed to satisfy specific constraints of each application. The most important and common requirements regardless of application types are to provide a long network lifetime and small end-to-end delay. In this paper, we propose Early Preamble MAC (EP-MAC) with improved energy conservation and low latency. It is based on CMAC but adopts a new preamble type called 'early preamble'. In EP-MAC, a transmitting node can find quickly when a next receiving node wakes up, so EP-MAC enables direct data forwarding in the next phase. From numerical analysis, we show that EP-MAC improves energy consumption and latency greatly compared to CMAC. We also implemented EP-MAC with NS-2, and through extensive simulation, we confirmed that EP-MAC outperforms CMAC.