• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2230-2237
• /
• 2015

Inspired by the synchronization phenomena observed in the Nature, we propose an autonomous load balancing method for a wireless network. We model the load balancing problem of cells providing wireless access services as a synchronization problem in the Nature and design an algorithm for each cell to distribute loads in a self-determining way based on the load differences among its neighbor cells. Through simulations, we verify the feasibility of the proposed method in that cell loads can be balanced efficiently eve if cells make decision autonomously using their local information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.386-393
• /
• 2004

In order to maintain load balancing in distributed systems in a decentralized manner, every node should obtain workload information from all the nodes on the network. It requires $Ο({v^2})$ traffic overheads, where v is the number of nodes. This paper presents a new synchronous dynamic distributed load balancing algorithm for a ( v,k+1,1)-configured network topology, which is a kind of 2k regular graph, based on symmetric balanced incomplete block design, where v equals ${k^2}+k+1$. Our algorithm needs only Ο(v√v) message overheads and each node receives workload information from all the nodes without redundancy. And load balancing in this algorithm is maintained so that every link has same amount of traffic by √v for transferring workload information.

• Journal of KIISE:Information Networking
• /
• v.28 no.2
• /
• pp.196-206
• /
• 2001

네트워크의 보편화와 개인용 컴퓨터의 고급화를 통한 가용 자원의 확장은 분산 컴퓨팅환경에서 작업 부하 균형의 성능 향상을 기대할수 있게 되었다. 하지만 이를 현실화시키기 위해서 다음과 같은 제약 사항을 극복해야 한다. 첫째 네트워크 연결된 각각의 시스템은 이질적인 하드웨어와 운영체제로 구성되어있다. 둘째 네트웍 대역폭의 격심한 변화가 존재하며 상이한 시스템 성능 차이가 존재한다. 셋째 어플리케이션의 요구조건이 상이하다. 본 논문에서는 작업부하 균형에 이동 에이전트 패러다임을 적용하며 위의 문제점을 해결하기 위하여세가지의 사항을 추가한다. 1)이질적인 분산 컴퓨팅 환경에 어플리케이션을 동적으로이식하기 위하여 분산 객체 지향 미들웨어인 CORBA[1] 기반 MASIF[2]를 이용한다. 2)유휴 자원정보에 기반한 어플리케이션의 동적배치를 위하여 지원 감지 모니터링을 실행한다. 3) 다양한 어플리케이션의 요구 조건을 만족시키기 위하여 다양한 모니터링 알고리즘을 동적으로 로드하는 자바 객체, MonitorHandler를 제안한다. 제안한 프레임워크의 실효성을 검증하기 위하여 프로토타입 어플리케이션을 구현하였다. 실험 결과 유휴 자원을 고려한 동적 배치가 정적배치나 초기 정보에 의한 단 한번의 배치보다 각각 57% 와 26%의 성능 향상을 보였다. 제안하는 프레임워크는 작업부하 균형 어플리케이션의 개발을 용이하게 하며 범용성과 확장성을 제공한다.

• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.37-47
• /
• 2011

Current researches in the Cloud focus on the appropriate interactions of cloud components in a large-scale system implementation. However, the current designs do not include intelligent methods like grouping the similar service providers based on their properties and integrating adaptive schemes for load distribution which can promote effective sharing of resource. This paper proposes an efficient virtualization of services by grouping the cloud providers to improve the service provisioning. The grouping of cloud service providers based on a cluster analysis collects the similar and related services in one group. The adaptive load balancing supports the service provisioning of the cloud system where it manages the load distribution within the group using an adaptive scheme. The proposed virtualization mechanism (GRALB) showed good results in minimizing message overhead and throughput performance compared to other methods.

• Journal of Internet Computing and Services
• /
• v.11 no.3
• /
• pp.65-74
• /
• 2010

In the ubiquitous healthcare, automated diagnosis is commonly achieved by an agent system to provide intelligent decision support and fast diagnosis result. Mobile agent technology is used for efficient load distribution by migrating processes to a less loaded node which is considered in our design of a ubiquitous healthcare system. This paper presents a framework for ubiquitous healthcare technologies which mainly focuses on mobile agents that serve the on-demand processes of an automated diagnosis support system. Considering the efficient utilization of resources, a balanced clustering for the load distribution of processes within nodes is proposed. The proposed algorithm selects overloaded nodes to migrate processes to near nodes until the load variance of the system is minimized. Our proposed balanced clustering efficiently distributes processes to all nodes considering message overheads by performing the migration to the near nodes.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1209-1218
• /
• 2017

A variety of sensors is widely used these days, and it has become much easier to acquire spatial big data streams from various sources. Since spatial data streams have inherently skewed and dynamically changing distributions, the system must effectively distribute the load among workers. Previous studies to solve this load imbalance problem are not directly applicable to processing spatial data. In this research, we propose Adaptive Spatial Key Grouping (ASKG). The main idea of ASKG is, by utilizing the previous distribution of the data streams, to adaptively suggest a new grouping scheme that evenly distributes the future load among workers. We evaluate the validity of the proposed algorithm in various environments, by conducting an experiment with real datasets while varying the number of workers, input rate, and processing overhead. Compared to two other alternative algorithms, ASKG improves the system performance in terms of load imbalance, throughput, and latency.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.1-14
• /
• 2006

Sort-last parallel rendering using a cluster of GPUs has been widely used as an efficient method for visualizing large- scale volume datasets. The performance of this method is constrained by load balancing when data parallelism is included. In previous works static partitioning could lead to self-balance when only task level parallelism is included. In this paper, we present a load balancing scheme that adapts to the characteristic of volume dataset when data parallelism is also employed. We effectively combine the hierarchical data structures (octree and BSP tree) in order to skip empty regions and distribute workload to corresponding rendering nodes. Moreover, we also exploit a 3D clustering method to determine visibility order and save the AGP bandwidths on each rendering node. Experimental results show that our scheme can achieve significant performance gains compared with traditional static load distribution schemes.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.12
• /
• pp.568-575
• /
• 2008

Server consolidation by sever virtualization can make one physical machine(PM) to run several virtual machines simultaneously. Although It is attractive in cost, it has complex workload behaviors. For that reason, efficient resource management method is required. Dynamic relocation of virtual machine(VM)[3,4] by live migration[1,2] is one of resource management methods. We proposed SCOA(Server Consolidation Optimizing Algorithm) : a fine-grained load balancing mechanism worked on this dynamic relocation mechanism. We could obtain accurate resource distribution information through pointed physical machines on multi dimensional resource usage coordination, so we could maintain more balanced resource state. In this paper, we show the effectiveness of our algorithm by comparison of experimental results between SCOA and sandpiper[3] by software simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.7
• /
• pp.1524-1531
• /
• 2004

This study analyzes a load balancing technique using Round Robin Algorithm. The study uses two software packages (Packet Capture and Round Robin Test Package) to check packet volume from Virtual Network structure (data generator, virtual server, Server1,2,3), and finds out traffic distribution toward Server1,2 and 3. The functions of implemented Round Robin Load Balancing Monitoring System include round robin testing, system monitoring, and graphical indication of data transmission and packet volume. As the result of the study shows, Round Robin Algorithm allows servers to ensure definite traffic distribution, unless incoming data loads differ much. Although error levels are high in some cases, they were eventually alleviated by repeated tests for a long period of time.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1620-1632
• /
• 1998

This paper presents a fast parallel algorithm for volume rendering and its implementation using C language and MPI MasPar Programming Language) on the 4,096 processor MasPar MP-2 machine. This parallel algorithm is a parallelization hased on the Lacroute' s sequential shear - warp algorithm currently acknowledged to be the fastest sequential volume rendering algorithm. This algorithm reduces communication overheads by using the sheared space partition scheme and the load balancing technique using load estimates from the previous iteration, and the number of voxels to be processed by using the run-length encoded volume data structure.Actual performance is 3 to 4 frames/second on the human hrain scan dataset of $128\times128\times128$ voxels. Because of the scalability of this algorithm, performance of ]2-16 frames/sc.'cond is expected on the 16,384 processor MasPar MP-2 machine. It is expected that implementation on more current SIMD or MIMD architectures would provide 3O~60 frames/second on large volumes.