• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.48-59
• /
• 2024

As functions that support virtualization on their own in hardware are developed, user applications having various workloads are operating efficiently in the virtualization system. SR-IOV is a virtualization support function that takes direct access to PCI devices, thus giving a high I/O performance by minimizing the need for hypervisor or operating system interventions. With SR-IOV, network I/O acceleration can be realized in virtualization systems that have relatively long I/O paths compared to bare-metal systems and frequent context switches between the user area and kernel area. To take performance advantages of SR-IOV, network resource management policies that can derive optimal network performance when SR-IOV is applied to an instance such as a virtual machine(VM) or container are being actively studied.This paper evaluates and analyzes the network performance of SR-IOV implementing I/O acceleration is compared with Virtio in terms of 1) network delay, 2) network throughput, 3) network fairness, 4) performance interference, and 5) multi-network. The contributions of this paper are as follows. First, the network I/O process of Virtio and SR-IOV was clearly explained in the virtualization system, and second, the evaluation results of the network performance of Virtio and SR-IOV were analyzed based on various performance metrics. Third, the system overhead and the possibility of optimization for the SR-IOV network in a virtualization system with high VM density were experimentally confirmed. The experimental results and analysis of the paper are expected to be referenced in the network resource management policy for virtualization systems that operate network-intensive services such as smart factories, connected cars, deep learning inference models, and crowdsourcing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.156-159
• /
• 2015

최근 콘텐츠 전송 네트워크(content delivery network, CDN)와 클라우드 컴퓨팅(cloud computing)을 결합하여 효과적으로 콘텐츠를 전달하기 위한 방법이 대두되고 있으며 이와 같이 클라우드 컴퓨팅과 결합하여 서비스되는 CDN을 클라우드 CDN 이라고 칭한다. 본 논문에서는 클라우드 CDN 환경에서의 효과적인 가상 머신 (virtual machine, VM) 관리를 위한 캐시서버(caching server)로써의 VM의 네트워크 I/O 성능 분석을 다룬다. 해당 성능 분석은 엔드 유저(end-user)들과 캐시서버 간 동영상 스트리밍(streaming)을 통하여 이루어졌으며 해당 캐시 서버의 네트워크 I/O 성능에 영향을 주는 다양한 경우에 대하여 진행되었다. 본 논문에서의 성능 분석은 클라우드 CDN 환경에서의 데이터센터(datacenter) 선택 및 요청 라우팅(routing) 등에 적용될 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.4
• /
• pp.24-32
• /
• 2002

Recent advances in Telecommunication and Internet have how made it possible to break the space-time barriers and allow physicians to deliver health care to patients at any time and any place, having led to a new branch of computer applications called Telemedicine System. In Telemedcine, Network and I/O performance requirements are generally more important than computing capability. Accordingly, this thesis is aimed at inquiring into how to satisfy QoS guarantee of network to compensate for the defects of the existing best-effort services and suggesting how to solve network bottleneck problem. using DiffServ in Telemedicine service system through Internet.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.702-706
• /
• 2010

In this paper, we propose a framework to change local devices to networked devices by using web browser. Network devices will be used in the virtual desktop. Management software maintains a pool of devices to manage network devices. Whenever user's request is occured, virtual desktop s/w which manages desktop's I/O access device pool. Then virtual desktop s/w selects proper device and forwards I/O to desktop. In this paper, we choose RIA solution for install-free environment. Consequently, user easily enrolls and revokes their devices. User easily commands virtual desktop s/w. In the second half of this paper, we explain usage scenario and evaluate our framework to show efficiency and flexibility of the framework.

• Journal of the Economic Geographical Society of Korea
• /
• v.10 no.1
• /
• pp.19-43
• /
• 2007

The purpose of this study is to distinguish industrial clusters in Korea. Based on I/O table in 2000, coefficient matrix was calculated and factor analysis was performed on the matrix. Among 38 derived industrial clusters, 5 of them were unreported clusters, which were indistinguishable. Once these 38 industrial clusters were differentiated according to I/O table, final results of clusters were produced as I/O table was converted into KSIC (Korean Standard Industry Code). Since existing studies on industrial cluster have been focused on qualitative methods such as case studies and interviews, it is expected that this study could contribute to carry out more systematic and efficient methodology.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.6
• /
• pp.809-814
• /
• 2011

The major resource problem in sensor networks is energy efficiency. There are two major access methods to efficiently use energy. The first is to use dynamic power management (DPM). The second is to use energy efficient protocols. In DPM methods, the OS, the power manager, is responsible for managing the proper power state of CPU and each I/O with respect to the events, but the OS is not largely concerned about the internal operation of each network protocols. Also, energy efficient protocols are mainly focused on the power saving operation of the radio PHY. In addition, in wireless sensor network most of tasks are connected to communication. In such a situation, traditional power managers can waste unpredicted power. In this paper, we introduce an efficient power manger that can reduce a lot of unwanted power consumption through cooperative power management (CPM) in communication-related tasks between each units, such as radio, sensing unit, and CPU, for ad hoc wireless sensor nodes.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.379-388
• /
• 2014

We noted that substituting hard disk with high-performance storage device on SAN did not immediately result in getting high performance. Investigating the reason behind this leaded us to propose optimization schemes for high-performance storage system. We first got rid of the latency in the I/O process which is unsuitable for the high-performance storage device, added parallelism on the storage server, and applied temporal merge to Superhigh speed network protocol for improving the performance with small random I/O. The proposed scheme was implemented on the SAN with high-performance storage device and we verified that there were about 30% reduction on the I/O delay latency and 200% improvement on the storage bandwidth.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.147-147
• /
• 2021

A partition of water distribution network (WDN) into district metered areas (DMAs) brings the efficiency and efficacy for water network operation and management (O&M), especially in monitoring pressure and leakage. Traditionally, the DMA configurations (i.e., number, shape, and size of DMAs) are permanent and cannot be changed occasionally. This leads to changes in water quality and reduced network redundancy lowering network resilience against abnormal conditions such as water demand variability and mechanical failures. This study proposes a framework to automatically divide a WDN into dynamic DMA configurations, in which the DMA layouts can self-adapt in response to abnormal scenarios. To that aim, a complex graph theory is adopted to sectorize a WDN into multiscale DMA layouts. Then, different failure-based scenarios are investigated on the existing DMA layouts. Here, an optimization-based model is proposed to convert existing DMA layouts into dynamic layouts by considering existing valves and possibly placing new valves. The objective is to minimize the alteration of flow paths (i.e., flow direction and velocity in the pipes) while preserving the hydraulic performance of the network. The proposed method is tested on a real complex WDN for demonstration and validation of the approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1826-1829
• /
• 2005

Recent advancement in wireless communications and electronics has enabled the development of low power sensor network. Wireless sensor network are often used in remote monitoring control applications, health care, security and environmental monitoring. Wireless sensor networks are an emerging technology consisting of small, low-power, and low-cost devices that integrate limited computation, sensing, and radio communication capabilities. Sensor network platform for health care has been designed, fabricated and tested. This system consists of an embedded micro-controller, Radio Frequency (RF) transceiver, power management, I/O expansion, and serial communication (RS-232). The hardware platform uses Atmel ATmega128L 8-bit ultra low power RISC processor with 128KB flash memory as the program memory and 4KB SRAM as the data memory. The radio transceiver (Chipcon CC1000) operates in the ISM band at 433MHz or 916MHz with a maximum data rate of 76.8kbps. Also, the indoor radio range is approximately 20-30m. When many sensors have to communicate with the controller, standard communication interfaces such as Serial Peripheral Interface (SPI) or Integrated Circuit ($I^{2}C$) allow sharing a single communication bus. With its low power, the smallest and low cost design, the wireless sensor network system and wireless sensing electronics to collect health-related information of human vitality and main physiological parameters (ECG, Temperature, Perspiration, Blood Pressure and some more vitality parameters, etc.)

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7B
• /
• pp.411-421
• /
• 2007

It is well known that the biggest problem of wireless sensor networks is power conservation. There have been two major approaches to efficiently use energy in wireless sensor networks. One is to use a dynamic power management scheme and the other is to use energy efficient protocols. In the former, the power manager is responsible for managing the proper power state of CPU and each I/O with respect to the events, but the power manager does not concern about the internal operation of the underlying network protocols. Thus such conventional power managers can waste unpredicted power during communication period. On the other hand, the energy efficient protocols are just focused on the power saving operation of the radio PHY. In this paper, we introduce an energy-efficient power saving mechanism that can significantly reduce unwanted power consumption of wireless sensor nodes through the communication event-driven power management. We show that our scheme improves the energy conservation in the entire network through simulations.