• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.11
• /
• pp.549-560
• /
• 2001

Cluster system provides attractive scalability in terms of compution power and memory size. With the advances in high speed computer network technology, cluster systems are becoming increasingly competitive compared to expensive MPPs (massively parallel processors). Load balancing is very important issue since an inappropriate scheduling of tasks cannot exploit the true potential of the system and can offset the gain from parallelization. In parallel processing program, it is difficult to predict the load of each task before running the program. Furthermore, tasks are interdependent each other in many ways. The dynamic load balancing algorithm, which evaluates each processor's load in runtime, partitions each task into the appropriate granularity and assigns them to processors in proportion to their performance in cluster systems. However, if the communication cost between processing nodes is expensive, it is not efficient for all nodes to attend load balancing process. In this paper, we restrict a processor that attend load balancing by the communication cost and the deviation of its load from the average. We simulate various models of the cluster system with parameters such as communication cost, node number, and range of workload value to compare existing load balancing methods with the proposed dynamic algorithms.

• Journal of Digital Convergence
• /
• v.6 no.2
• /
• pp.117-125
• /
• 2008

High-volume web sites often use clusters of servers with load balancing as a way to increase the performance, scalability, and availability of the sites. Load balancing, usually performed by load balancer in front of such clusters, is a technique to spread workload between several computers or resources, in order to get optimal resource utilization or response time. In this paper we examine the performance for several configurations of cluster-based web servers using a simulation approach. We investigate two types of buffering scheme (common and local) for web clusters and three load balancing policies (uniformly random, round robin, and least queue first), using response time as a performance measure. We also examine two basic approaches of scaling web clusters: adding more servers of same type or upgrading the capacity of the servers in the clusters.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.6
• /
• pp.1016-1026
• /
• 1994

In this paper, we have studied load balancing problems in distributed systems. The nodes of distributed systems exchange periodically system state information each other. The information is stored in history. Based on the information, we compute an expected load index(ELI) using a five-degree interpolation polynomial in Newton`s backward difference interpolation formula. A new location policy of dynamic load balancing systems makes use of the ELI. We show that its performance is better than that of the existing load balancing algorithm through a simulation study.

• Journal of Communications and Networks
• /
• v.10 no.1
• /
• pp.38-43
• /
• 2008

In this paper, adaptive channel borrowing approach fuzzy neural networks for load balancing (ACB-FNN) is presented to maximized the number of served calls and the depending on asymmetries traffic load problem. In a wireless network, the call's arrival rate, the call duration and the communication overhead between the base station and the mobile switch center are vague and uncertain. A new load balancing algorithm with cell involved negotiation is also presented in this paper. The ACB-FNN exhibits better learning abilities, optimization abilities, robustness, and fault-tolerant capability thus yielding better performance compared with other algorithms. It aims to efficiently satisfy their diverse quality-of-service (QoS) requirements. The results show that our algorithm has lower blocking rate, lower dropping rate, less update overhead, and shorter channel acquisition delay than previous methods.

• Journal of the Optical Society of Korea
• /
• v.18 no.5
• /
• pp.466-471
• /
• 2014

An asynchronous optical packet-switching (AOPS) node with load-balancing capability can achieve better performance in reducing the high packet-loss ratio (PLR) and time delay caused by unbalanced traffic. This paper proposes a novel dynamic load-balancing algorithm for an AOPS node with limited buffer and without wavelength converters, and considering the data flow distribution and service levels. By calculating the occupancy state of the output ports, load state of the input ports, and priorities for data flow, the traffic is balanced accordingly. Simulations demonstrate that asynchronous variant data packets and output traffic can be automatically balanced according to service levels and the data flow distribution. A PLR of less than 0.01% can be achieved, as well as an average time delay of less than 0.46 ns.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.1053-1057
• /
• 2005

현재 IETF (Internet Engineering Task Force)의 SHIM6 (Site Multihoming by IPv6 Intermediation) 워킹그룹에서는 Network layer Shim (L3shim)이라는 새로운 IPv6 스택을 정의하여IPv6 환경에서 멀티호밍을 지원하는 방법에 대해 표준을 제정하고 있다. 이 Multihoming은 redundancy, load sharing과 같은 멀티호밍 장점을 지원할 수 있다. 본 논문은 이와 같이 새롭게 정의된 L3shim이 단말에 있을 경우, 단말에서 효과적인 Policy 정책을 통한 load sharing 및 balancing 통한 traffic engineering 방법을 제시한다. 현재 SHIM6 워킹그룹에서는 L3shim을 이용한 load balancing 부분은 다루고 있지 않다. 그러나 멀티호밍의 장점 줌 하나는load balancing이며 실제 load balancing이 지원 됐을 경우 응용 차원에서 많은 장점을 가질 것으로 여겨진다. 따라서 이와 관련한 메커니즘이 필요하며, 이를 위한 선행적인 연구가 필요로 되어진다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.8
• /
• pp.1360-1366
• /
• 2007

In this paper, the load balancing which is one of the distribution power system's operation purposes was studied. Reconfiguration of Distribution power system presents that the configuration is changed by changing the switch on/off status which exists in the system according to the mentioned purpose. Through this method, the load of distribution power system is shown to be balanced. As a characteristic of complicated distribution power system, system is designed by being applied by OOP(Object Oriented Programming) method which connected more flexibly than existing Procedural Programming method, and the process of calculating the distflow and the loss of configurated system is shown. In addition, this paper suggests more efficient method compared by the results of reconfiguration on the purpose of the loss minimization and by the result of distribution power system reconfiguration on the purpose of load balancing. Moreover, it searches for the method to approach the global optimal solution more quickly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.249-251
• /
• 2014

This paper proposes a channel diversity based load-balancing cross-layer routing scheme for Wireless Mesh Networks (WMNs). The proposed scheme deals with channel diversity phase and load balancing phase in WMNs. Channel diversity factor $metric_{ch-d}$ and load balancing factor $f_{load}$ are defined and employed cooperatively as a combined path selection policy.

• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.218-223
• /
• 2021

Pervasive enhancement and required enforcement of the Internet of Things (IoTs) in a distributed massively multiplayer online architecture have effected in massive growth of Big-Data in terms of server over-load. There have been some previous works to overcome the overloading of server works. However, there are lack of considered methods, which is commonly applicable. Therefore, we propose a combing Sparse Auto-Encoder and Load-Balancing, which is ProGReGA for Big-Data of server loads. In the process of Sparse Auto-Encoder, when it comes to selection of the feature-pattern, the less relevant feature-pattern could be eliminated from Big-Data. In relation to Load-Balancing, the alleviated degradation of ProGReGA can take advantage of the less redundant feature-pattern. That means the most relevant of Big-Data representation can work. In the performance evaluation, we can find that the proposed method have become more approachable and stable.

• ETRI Journal
• /
• v.45 no.3
• /
• pp.433-447
• /
• 2023

Critical issues such as connection congestion, long transmission delay, and packet loss become even worse during epidemic, disaster, and so on. In this study, a link load balancing method is proposed to address these issues on the data plane, a plane of the software-defined network (SDN) architecture. These problems are NP-complete, so a meta-heuristic approach, discrete particle swarm optimization, is used with a novel hybrid cost function. The superiority of the proposed method over existing methods in the literature is that it provides link and switch load balancing simultaneously. The goal is to choose a path that minimizes the connection load between the source and destination in multipath SDNs. Furthermore, the proposed work is dynamic, so selected paths are regularly updated. Simulation results prove that with the proposed method, streams reach the target with minimum time, no loss, low power consumption, and low memory usage.