• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제1권3호
• /
• pp.137-148
• /
• 2012

사용자들은 자신의 작업을 처리하기 위해 자신에게만 한정된 가상 컴퓨팅 자원을 클라우드 서비스 제공자로부터 할당 받아 타 사용자로부터 독립된 환경에서 작업을 처리하게 된다. 이를 자동화된 방법으로 최적화를 대신 수행해주기 위한 모델로 브로커 미들웨어가 제시되었고 마감시간을 만족하는 이내에서 자원 이용률을 높이는 접근법으로 필요 가상 머신의 숫자를 줄여 비용을 절약한다. 이를 다루는 많은 논문들에서 작업 스케줄링은 기존 사용자들간의 독립을 보장하여 하나의 가상 머신이 하나의 작업에 한정된 가상 머신에서 처리하는 방식으로 다루어지고 있다. 하지만 기존의 SRSV 방식에서는 높은 정도의 다중 프로그래밍 작업이 아닐 경우 시스템을 효율적으로 사용하지 못한다. 이에 본 논문에서는 해당 자원을 마감시간과 스래싱(thrashing), 문맥 전환(context switching)에 따른 성능 저하를 고려한 상태에서 다중 프로그래밍 정도를 높여 낭비되는 자원을 최소화하여 비용을 절약하려고 한다. 실험 결과를 통해 제안하는 방법이 제약조건 이내에서 기존의 방식에 비해 좀 더 좋은 가격 대비 성능을 가지는 것을 보인다.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권9호
• /
• pp.315-320
• /
• 2015

클라우드 컴퓨팅에서 서버 가상화는 한 대의 물리적인 서버를 다수의 가상머신으로 분할하여 다양한 운영체제 및 애플리케이션을 구동하는 기술이다. 가상머신의 마이그레이션은 현재 실행 중인 가상머신을 소스 호스트에서 다른 물리적인 장치인 타깃 호스트로 이동하는 것이다. 가상머신의 라이브 마이그레이션은 작업 수행 성능의 최적화와 저전력 지원 및 에너지 절감, 결함포용, 노드들 간의 부하 균형을 제공하기 위한 필수적인 요소이다. 본 논문에서는 오픈소스 기반의 적응적 VM 라이브 마이그레이션 기법을 제안한다. 이를 위해 적응적 VM 마이그레이션 시점을 결정하는 VM 모니터링 모듈을 제안하고 오픈소스 기반 전가상화를 지원하는 하이퍼바이저를 설계하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권11호
• /
• pp.5419-5436
• /
• 2016

Enhancing the performance of computing systems has been an important topic since the invention of computers. The leading-edge technologies of multicore and virtualization dramatically influence the development of current IT systems. We study performance attributes of response time (RT), throughput, efficiency, and scalability of a virtualized Web system running on a multicore server. We build virtual machines (VMs) for a Web application, and use distributed stress tests to measure RTs and throughputs under varied combinations of virtual cores (VCs) and VM instances. Their gains, efficiencies and scalabilities are also computed and compared. Our experimental and analytic results indicate: 1) A system can perform and scale much better by adopting multiple single-VC VMs than by single multiple-VC VM. 2) The system capacity gain is proportional to the number of VM instances run, but not proportional to the number of VCs allocated in a VM. 3) A system with more VMs or VCs has higher physical CPU utilization, but lower vCPU utilization. 4) The maximum throughput gain is less than VM or VC gain. 5) Per-core computing efficiency does not correlate to the quality of VCs or VMs employed. The outcomes can provide valuable guidelines for selecting instance types provided by public Cloud providers and load balancing planning for Web systems.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권6호
• /
• pp.562-571
• /
• 2007

많은 연구들을 통해 수행 속력, 효율성, 용이성, 안전성을 위하여 메모리 관리 기법들을 개선시켰다. 그러한 방법들 중에서 지역별 메모리 관리 기법은 각각의 객체 할당 위치에서 따라 정해진 지역에 할당 시키고 그 지역이 제거된다면 그 곳에 할당된 모든 객체의 메모리를 반환하는 방법이다. 본 논문에서는 메모리 제약적인 환경에서 힙 메모리 사용량을 줄이기 위해 로컬 지역을 재사용하는 방법을 제시한다. 기본 아이디어는 현재 함수가 수행될 동안 사용하지 않는 상위 로컬 지역을 재사용하는 것이다. 이러한 방법을 사용함으로써 메모리 제약적인 환경에서 메모리의 한계를 극복할 수 있을 것이다.

• 한국의류학회지
• /
• 제28권1호
• /
• pp.88-99
• /
• 2004

The purpose of this study is to observe the significance and symbolic meaning of fashion design which is combined with machines, and to develop excellent designs in aesthetic aspects. The method of this study analyzed the related documents and journal, fashion magazines. The results is as follows. The cyborg discourse and virtual human body in virtual world predict the existence of new human. In present times, up-to-date equipments such as wearable computer have begun to be built-in clothing based on technology, and these dress and ornaments influence on human's life gradually in practicality and ability. These equipments are divided as military affairs, medical treatment equipment, leisure, information access and communication, guard, and business assistance. And according to the kind of item, they are divided by headwear, clothing and accessory. The significance of clothing combined with machine is practical viewpoint, economical viewpoint and aesthetic viewpoint. And the symbolic meaning of these fashion combined machine with technology is dis-identity in digital society, dis-borderness between human and machine and the uncertainty of human being. Like this, the clothing which is combined with high-technology shapes its own unique and individual system. But, this must escape from the limit of medium system itself that is technology to become a future clothing for human, suggest new agenda about human and society, and confirm the human being's existence and identity continually.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1501-1518
• /
• 2016

This paper presents an effective management of VM (Virtual Machine) for heterogeneous cloud using Common Deployment Model (CDM) brokering mechanism. The effective utilization of VM is achieved by means of task scheduling with VM placement technique. The placements of VM for the physical machine are analyzed with respect to execution time of the task. The idle time of the VMis utilized productively in order to improve the performance. The VMs are also scheduled to maintain the state of the current VM after the task completion. CDM based algorithm maintains two directories namely Active Directory (AD) and Passive Directory (PD). These directories maintain VM with proper configuration mapping of the physical machines to perform two operations namely VM migration and VM roll back. VM migration operation is performed from AD to PD whereas VM roll back operation is performed from PD to AD. The main objectives of the proposed algorithm is to manage the VM's idle time effectively and to maximize the utilization of resources at the data center. The VM placement and VM scheduling algorithms are analyzed in various dimensions of the cloud and the results are compared with iCanCloud model.

• 한국기계가공학회지
• /
• 제12권6호
• /
• pp.175-181
• /
• 2013

The primary element of machining automation is to maximize the utilization of machine tools, which determines the output and lead-time. In particular, 95% of raw materials for wing ribs are cut into chips and 0.6 ton of chips are generated every hour from each machine tool. In order to verify the chip recycling system that controls the chips from the machines in five-axis FMS line, a simulation of the virtual model is constructed using the QUEST simulation program. The optimum speed of the chip conveyor and its operating conditions that directly affect the efficiency of the FMS line are presented including the chip conveyor speed, the maximum capacity of the hopper, and the number of chip compressors.

• 정보보호학회논문지
• /
• 제27권3호
• /
• pp.579-589
• /
• 2017

클라우드 환경은 하이퍼바이저 기반으로 다수의 가상머신들이 상호 연결된 형태로 악성코드의 전파가 용이하기 때문에 다른 환경에 비해 악성코드에 감염될 경우 그 피해규모가 상대적으로 크다. 본 논문에서는 이러한 문제점을 해결하기 위해 안전한 클라우드 환경을 위한 악성트래픽 동적 분석 시스템을 제안한다. 제안하는 시스템은 클라우드 환경에서 발생하는 악성트래픽을 판별하여 악성행위를 격리된 가상네트워크 환경에서 지속적으로 모니터링 및 분석한다. 또한, 분석된 결과를 추후 발생하는 악성트래픽의 판별과 분석에 반영한다. 본 논문에서 제안하는 시스템은 클라우드 환경에서 발생하는 신 변종 악성트래픽 탐지 및 대응을 목적으로 클라우드 환경에서의 악성트래픽 분석환경을 구축함으로써 안전하고 효율적인 악성트래픽 동적 분석을 제공한다.

• Journal of Information Processing Systems
• /
• 제16권1호
• /
• pp.132-144
• /
• 2020

Cloud computing is an emerging technology based on the concept of enabling data access from anywhere, at any time, from any platform. The exponential growth of cloud users has resulted in the emergence of multiple issues, such as the workload imbalance between the virtual machines (VMs) of data centers in a cloud environment greatly impacting its overall performance. Our axis of research is the load balancing of a data center's VMs. It aims at reducing the degree of a load's imbalance between those VMs so that a better resource utilization will be provided, thus ensuring a greater quality of service. Our article focuses on two phases to balance the workload between the VMs. The first step will be the determination of the threshold of each VM before it can be considered overloaded. The second step will be a task allocation to the VMs by relying on an improved and faster version of the meta-heuristic "simulated annealing (SA)". We mainly focused on the acceptance probability of the SA, as, by modifying the content of the acceptance probability, we could ensure that the SA was able to offer a smart task distribution between the VMs in fewer loops than a classical usage of the SA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.6098-6122
• /
• 2018

Cache-based side-channel attacks have achieved more attention along with the development of cloud computing technologies. However, current host-based mitigation methods either provide bad compatibility with current cloud infrastructure, or turn out too application-specific. Besides, they are defending blindly without any knowledge of on-going attacks. In this work, we present CacheSCDefender, a framework that provides a (Virtual Machine Monitor) VMM-based comprehensive defense framework against all levels of cache attacks. In designing CacheSCDefender, we make three key contributions: (1) an attack-aware framework combining our novel dynamic remapping and traditional cache cleansing, which provides a comprehensive defense against all three cases of cache attacks that we identify in this paper; (2) a new defense method called dynamic remapping which is a developed version of random permutation and is able to deal with two cases of cache attacks; (3) formalization and quantification of security improvement and performance overhead of our defense, which can be applicable to other defense methods. We show that CacheSCDefender is practical for deployment in normal virtualized environment, while providing favorable security guarantee for virtual machines.