• Journal of the Korea Society for Simulation
• /
• v.3 no.2
• /
• pp.49-56
• /
• 1994

Performance measurement and analysis for computer systems has been studied for a long time. However, little attention has been focused on how to distribute a given budget to each part of a computer system for enhancing system performance maximally. In traditional approaches, performance enhancement is achieved by identifying a dominant system bottleneck and enhancing the bottleneck's performance. These approaches, however, often bring problems since the removal of a bottleneck may result in other bottlenecks. This paper proposes an approximated method for such budget distribution problem. For budget distribution, a critical set is defined. The set contains the servers of which performance changes affect the overall system performance significantly. Then, the given budget is distributed properly to every server in the critical set. To verify the proposed method, two benchmark experiments are carried out I SLAM environments. The experimental results show that the proposed method provides better results than the traditional method does in many cases.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.798-801
• /
• 2002

This paper proposes unsupervised classification of multiple attributes via five-layer autoassociative neural network with bottleneck layer. In the conventional methods, high dimensional data are compressed into low dimensional data at bottleneck layer and then feature extraction is performed (Fig.1). In contrast, in the proposed method, analog data is compressed into digital data. Furthermore bottleneck layer is divided into two segments so that each attribute, which is a discrete value, is extracted in corresponding segment (Fig.2).

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.51-54
• /
• 2000

Due to the emerging of high-speed network, lots of interests of access to remote data have increased. Those interests motivate using of Cooperative Caching that uses remote cache like local cache by sharing other clients' cache. The conventional algorithm like GMS(Global Memory Service) has some disadvantages that occurred bottleneck and decreasing performance because of exchanges of many messages to server or manager. On the other hand, Hint-based algorithm resolves a GMS's server bottleneck as each client has hint information of all blocks. But Hint-based algorithm also causes some problems such as inaccurate information in it, if it has too old hint information. In this paper, we offer the policy that supplement bottleneck and inaccuracy； by using file identifier that can search for the lookup table and by exchanging oldest block information between each client periodically.

• ETRI Journal
• /
• v.20 no.4
• /
• pp.301-326
• /
• 1998

In this paper, we have modeled and evaluated a new parallel processing system called Scalable Parallel computer Architecture based on Xbar (SPAX) for commercial applications. SMP systems are widely used as servers for commercial applications; however, they have very limited scalability. SPAX cost-effectively overcomes the SMP limitation by providing both scalability and application portability. To investigate whether the new architecture satisfies the requirements of commercial applications, we have built a system model and a workload model. The results of the simulation study show that the I/O subsystem becomes the major bottleneck. We found that SPAX can still meet the I/O requirement of the OLTP workload as it supports flexible I/O subsystem. We also investigated what will be the next most important bottleneck in SPAX and how to remove it. We found that the newly developed system network called Xcent-Net will not be a bottleneck in the I/O data path. We also show the optimal configuration that is to be considered for system tuning.

• Journal of Korean Society for Quality Management
• /
• v.23 no.3
• /
• pp.156-166
• /
• 1995

Job shop scheduling problem is a complex system and an NP-hard problem. Thus it is natural to look for heuristic method. We consider the multi-part production scheduling problem for quality level in a job shop scheduling under the existence of alternative routings. The problem is more complex if the processing time is imprecision. It requires suitable method to deal with imprecision. Fuzzy set theory can be useful in modeling and solving scheduling problems with uncertain processing times. Li-Lee fuzzy number comparison method will be used to compare processing times that evaluated under fuzziness. This study presents heuristic method for quality level in bottleneck-based job shop scheduling under fuzzy environment. On the basis of the proposed method, an example is presented.

• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1475-1482
• /
• 2015

In network routers, buffers are used to resolve congestion and reduce packet loss rate whenever congestion occurs at bottleneck link. Most of the existing methods to manage such buffers focus only on queue-length-based control as one loop which have some issues of low link utilization and system stability. In this paper, we propose a novel framework which exploits two-loop control method, e.g. queue-length and congestion window size, combined with optimal margin method to facilitate parameter choices. Simulation results in ns-2 demonstrate that bottleneck link performance can be improved with higher link utilization (85%) and shorter queue length (22%) than the current deployed scheme in commercial routers (RED and DropTail).

• IE interfaces
• /
• v.14 no.4
• /
• pp.385-393
• /
• 2001

In this paper, a scheme of scheduling a bottleneck operation is presented for production planning of make-to-order. We focus on the problem of capacity-dependent processing time in which processing time of the bottleneck operation is not fixed, but varies with job sequence or equipment capacity. For this, a genetic algorithm is applied for job sequencing with an objective function of mean square of weighted deviation. An experimental study is implemented in power transformer plant and results are compared with those of the EDD rule. It shows that the genetic algorithm is relatively good for most cases.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.423-428
• /
• 2010

최근에는 사회구조가 복잡해 짐에 따라 각 분야의 전문성이 두드러지고 있다. 이러한 흐름은 음식점에도 영향을 주어 기존의 형식에서 벗어난 자신들만의 독특하고 차별성 있는 요리 메뉴의 개발을 가속화시켰다. 그로 인해 한식, 중식, 양식으로 구분하는 전통적인 음식점 분류 방식이 한계를 보였고, 기존의 분류를 포함하면서도 새로이 등장하는 음식점들을 다룰 수 있는 방식이 필요하다. 본 논문에서는 최근 폭발적으로 늘어나는 음식점 추천 웹 사이트의 데이터를 토대로 자동적으로 음식점 분류를 수행하는 방법을 제안한다. 본 연구에서는 각 음식점이 갖고 있는 특징을 메뉴 정보를 통해 파악하려 하였다. 음식점 사이트에서 수집한 2 천개의 음식점, 6 만개의 메뉴 정보를 미리 정의된 필터로 정제한 후 Sequential Information Bottleneck Clustering 알고리즘을 적용하여 구분해 보았다. 실험결과 제안한 방법이 다른 Clustering 방법에 비해 높은 성능을 보였으며 음식점주가 수동적으로 음식점 분류를 입력하는 수고를 줄일 수 있는 가능성을 보였다.

• Journal of Korean Society for Quality Management
• /
• v.21 no.2
• /
• pp.224-231
• /
• 1993

This paper propose a procedure to form the cell and part family using both of similarity coefficient method and mathematical programming in order to slove the exceptional part and bottleneck machine problems. In the procedure proposed by this paper, the machine duplication and subcontracting are considered to slove the bottleneck machine and intercellular moving part problems An example is given to show how this procedure works.

• The Journal of Information Technology
• /
• v.3 no.2
• /
• pp.115-126
• /
• 2000

When a terminal frequently crosses a RA or a call originate in a boundry cell, HLR should be updated or queried. Frequent DB accesses and message transfers may cause the HLR bottleneck and degrade the system performance. This paper propose scheme to solve the HLR bottleneck problem and reduce to call registration cost and call tracking cost in wirless networks.