• The KIPS Transactions:PartD
• /
• v.13D no.6 s.109
• /
• pp.755-764
• /
• 2006

In recent, data streams are generated in various application fields such as a ubiquitous computing and a sensor network, and various algorithms are actively proposed for processing data streams efficiently. They mainly focus on the restriction of their memory usage and minimization of their processing time per data element. However, in the algorithms, if data elements of a data stream are generated in a rapid rate for a time unit, some of the data elements cannot be processed in real time. Therefore, an efficient load shedding technique is required to process data streams effcientlv. For this purpose, a load shedding technique over a data stream is proposed in this paper, which is based on the predicting technique of the frequency of data element considering its current frequency. In the proposed technique, considering the change of the data stream, its threshold for tuple alive is controlled adaptively. It can help to prevent unnecessary load shedding.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.3
• /
• pp.288-298
• /
• 1995

Load balancing attempts to improve the performance of a distributed computing system by transferring some of the workload of a congested site to others. A load balancing scheme that supports both the source-initiated and the server- initiated load balancing is proposed in this paper. It can model both the m/m/1 queue(no load balancing) and the m/m/n queue(perfect load balancing) as the extreme State variables are replicated into every site, and copy consistency constraints are relaxed more weakly. We propose weak copy consistency constraints which correlate the outdated state information to that of the current state. We also derive sufficient conditions under which each scheduler can guarantee the load balancing without communication Using this model, the problem of load balancing is converted to that of maintaining the consistency of states and communication overhead becomes less than that of the bidding algorithm. The scheme is simulated by event tracing, compared to the two extreme cases and the bidding algorithm. The results show that the mean response time and the number of messages are reduced by 0-35% and 40-100% respectively, compared with the bidding algorithm. Finally the effects of some system parameters are described.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1047-1054
• /
• 2022

With the advent of SDN, a next-generation network technology that separates the hardware and software areas of network equipment and defines the network using open source-based software, it solves the problems of complexity and scalability of the existing network system. It is now possible to configure a custom network according to the requirements. However, it has a structural disadvantage that a load on the network may occur due to a lot of control communication occurring between the controller and the switch, and many studies on network load distribution to effectively solve this have been preceded. In particular, in previous studies of load balancing techniques related to flow tables, many studies were conducted without consideration of flow entries, and as the number of flows increased, the packet processing speed decreased and the load was increased. To this end, we propose a new network load balancing technique that monitors flows in real time and applies dynamic flow management techniques to control the number of flows to an appropriate level while maintaining high packet processing speed.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.1-5
• /
• 2006

Finding a valid timing constraint is one of the most important issues in the real-time monitoring area. To get the valid timing constraint, a developer executes a real-time process and changes the constraint on a regular basis. This is an exhaustive and time-consuming process. To improve this approach, we propose a timing constraint search technique. This technique uses two load models and one condition proposed in this paper to support the developer in determining the valid timing constraint range in an easy and systematic manner.

• Annual Conference of KIPS
• /
• 2003.11a
• /
• pp.427-430
• /
• 2003

작업관리 시스템인 배치처리 시스템은 한정된 공유자원을 동시에 요구하는 사용자들에게 시스템의 자원을 효율적으로 배분하여 주며, 제시된 다수의 작업들을 순차적으로 수행시켜 준다. 이러한 작업관리 시스템을 시스템 규모 사용자의 요구 조건에 맞게 최적화함으로써 시스템의 자원을 최대한 이용할 수 있게 하며, 다양한 사용자 요구에 적절한 자원 배분할 수 있도록 정의되어야 한다. NQS방식을 개선시켜 이종 모델로 구성된 NEC SX-5 및 SX-6을 단일시스템처럼 관리할 수 있도록 하였으며 다수의 연동 계산을 원활히 수행키 위한 큐 차등화 서비스방식을 적용시켜 사용자 대기 시간을 최소화시켰다. 본 논문에서는 NQS를 사용하여 이종 다중 노드의 연동 구성 방법과 이것의 최적화 방법 그리고, 노드간 load balancing을 최적 수행 방법 등을 소개한다.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.609-614
• /
• 2010

In this paper, the structural integrity and fatigue strength for the bogie frame of Monorail being developed in domestic was evaluated. Presently, the standard of evaluation for the bogie frame of monorail was not regulated. Therefore, the evaluation of the structural integrity and fatigue strength for the bogie frame was performed on the basis of the UIC 615-4 standard. The structural integrity of the designed bogie frame was evaluated by displacement and Von-Mises stress under each load conditions. And the fatigue strength was evaluated by combined main in-service load conditions specified at UIC 615-4 standard and it was compared with result of fatigue analysis using winLIFE v3.1 with the function of batch processing. The results shows that the structural integrity and fatigue strength of the designed bogie frame was satisfied, and the fatigue analysis using batch processing was more effective than conventional fatigue analysis using combined load conditions.

• Annual Conference of KIPS
• /
• 2000.10a
• /
• pp.187-190
• /
• 2000

전형적인 멀티미디어 시스템은 클라이언트-서버 구조로 이루어지고 있다. 사용자의 요청에 따라 요청된 데이터를 갖고 있는 적절한 서버를 찾는 방법을 확장성 있게 지원하기 위해 계층적 관리 구조가 제시되었다. 이 접근방법에서는 중간 계층에서 영역 관리자가 사용자의 요청을 전달해 줌으로 인해서, 사용자 요청에 대한 거부 확률을 효과적으로 줄일 수 있다. 그러나 load balancing 을 이루기 위한 계층적 관리 구조에서는 정적 복제 방식을 사용함으로 인해서 사용자 요청에 대한 거부 확률이 최소화되지 못하였다. 따라서, 본 연구에서는 계층적 관리구조에 멀티미디어 데이터가 요청되는 패턴에 따라 동적으로 변화하는 동적 복제 방식을 도입할 것을 제안하고, 실험을 통하여 제안된 방법은 기존의 방법과 비교하였다.

• Journal of Information Processing Systems
• /
• v.9 no.3
• /
• pp.489-498
• /
• 2013

In this paper, we propose a common simulation model that can be reused for different performance evaluations of networked virtual environments. To this end, we analyzed the common features of NVEs, in which multiple regions compose a shared space, and where a user has his/her own interest area. Communication architecture can be client-server or peer-server models. In usual simulations, users move around the world while the number of users varies with the system. Our model provides various simulation parameters to customize the region configuration and user movement pattern. Furthermore, our model introduces a way to mimic a lot of users in a minimal experiment environment. The proposed model is integrated with our network framework, which supports various scalability approaches. We specifically applied our model to the interest management and load distribution schemes to evaluate communication overhead. With the proposed simulation model, a new simulation can be easily designed in a large-scale environment.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2007.04a
• /
• pp.327-332
• /
• 2007

An engineering design problem involving Multi-Disciplinary Analysis(MDA) generally requires a large amounts of CPU time for the entire design process, and therefore Multiple Processing System (MPS) are essential to reduce the completion time. However, when applying conventional parallel processing techniques, all of the CAE S/W required for the MDA should be installed on all the servers making up NIPS because of characteristic of MDA and it would be a great expense in CAE S/W licenses. To solve this problem, we propose a Weight-based Multiqueue Load Balancing algorithm for a heterogeneous MPS where performance of servers and CAE S/W installed on each server are different of each other. To validate the performance, a computational experiments comparing the First Come First Serve algorithm and our proposed algorithm was accomplished.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.48 no.9
• /
• pp.503-509
• /
• 1999

This paper proposes a new speed and tension control algorithm for multi-span continuous strip processing line. In this algorithm the speed reference of each roll is adjusted to make the output force follow the load balance reference using an outer loop controller in cascade. Using the information of the output force of the adjacent roll, it is shown that the strip tension between two rolls can be controlled as the desired value without tension sensor. An experimental set-up which consists of 4 driven and 3 measuring rolls is designed and built for the multi-span speed and tension control. The experimental result reveals conspicuous improvement of tension control performance by the proposed algorithm comparing to the conventional tension feedback controller.