• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1290-1298
• /
• 2000

Multimedia Systems such as VOD(Video On Demand) and MOD (Multimedia On Demand) need to support continuous media operations which are randomly called by concurrent users and require that stored media be accessed in real-tim. To satisfy such a requirements, disk arrays consisting of multiple disks are generally used as storage systems. Under the real-time environments to provide users with accessing continuous media in the parallel and concurrent manner, storage systems should be able to deal with user requests independently. In this paper, we present a new fault-tolerant continuous media storage system called PADA(PRR\ulcorner bAsed Disk Array), which is based on a PRR\ulcorner (Prime Round Robin with Grouped Parties) disk placement scheme with enhanced reliability nd load-balancing. We have compared and evaluated the storage space overhead for fault-tolerance, the reliability of diks array systems, the degree of disk load0-balancing, the demanded buffer space, the maximum number of users being capable of supporting and the fault recovery overhead for PADA, RAID 5 and Declustered storage systems. According to the results, PADA is the best among them in that PADA satisfies load-balancing more effectively and servces more user in case of arbitrary-rate retrievals.

• Journal of KIISE:Information Networking
• /
• v.28 no.3
• /
• pp.406-416
• /
• 2001

Single path routing schemes using dynamic routing metric amy find out the dynamic network status and recompute paths to keep the traffic from the highly loaded regions of the network. This type of routing approach, however, may lead to a routing oscillation, and further, it cannot exploit multi-paths that may frequently exist in the real network. We propose a multipath routing scheme with dynamic load balancing, called MP-DLB, which is capable of reducing the overhead incurred by the multipath routing with dynamic load balancing approach while taking advantage of the high routing performance provided by the approach. According to the analysis of Internet packet traces which show that a high percentage of network traffic is destined for a small number of networks, MP-DLB applies the multipath routing with dynamic load balancing only to a limited subset of all the destinations in the network. For the rest of the destinations, it applies traditional single path routing scheme. This approach may reduce overall routing overheads by limiting the number of destinations to apply the more complicated routing scheme while it can keep the routing performance high by providing efficient routing for the most significant traffic in the routing performance. A series of simulations are done to analyze the performance of MP-DLB. The simulation results show that MP-DLB may effectively cope with the congestion and achieve high routing performance by distributing traffic streams that are generated from varying sources and heading toward a specific hot destination over multi-paths.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.21-24
• /
• 2001

For very large multimedia traffic to be supported successfully in wireless network environment, it is necessary to provide Quality-of-Service(QoS) guarantees between mobile hosts(clients). In order to guarantee the Qos, we have to keep the call blocking probability below target value during handoff session. However, the QoS negotiated between the client and the network may not be guaranteed due to lack of available channels for traffic in the new cell, since mobile clients should be able to continue their on-going sessions. In this paper we propose a efficient load-balancing algorithm based on the adaptive bandwidth reservation scheme for enlarging available channels in a cell. We design a new method to predict the mobility of clients using MPT(mobility profile table). This method is then used to reserve a part of bandwidths for handoff calls to its adjacent cells and this reserved bandwidth can be used for handoff call prior to new connection requests. If the number of free channels is also under a low threshold value, our scheme use a load-balancing algorithm with a adaptive bandwidth reservation. In order to evaluate the performance of our algorithm, we measure the metrics such as the blocking probability of new calls and dropping probability of handoff calls, and compare with other existing schemes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.9
• /
• pp.2340-2349
• /
• 2009

In this paper we proposed a hopping routing scheme to resolve the hot spot problem for periodic monitoring services in wireless sensor networks. Our hopping routing scheme constructs load balanced routing path, where an amount of energy consumption of all nodes in the sensor networks is predictable. Load balanced routing paths can be obtained from horizontal hopping transmission scheme which balances the load of the sensor nodes in the same area, and also from vertical hopping transmission scheme which balances the load of the sensor nodes in the other area. The direct transmission count numbers as load balancing parameter for vertical hopping transmission are derived using the energy consumption model of the sensor nodes. The experimental results show that the proposed hopping scheme resolves the hot spot problem effectively. The efficiency of hopping routing scheme is also shown by comparison with other routing scheme such as multi-hop, direct transmission and clustering.

• The KIPS Transactions:PartC
• /
• v.16C no.4
• /
• pp.417-422
• /
• 2009

Implementation of DPI(Deep Packet Inspection) system on a general purpose multiprocessor platform is an attractive option from the implementation cost point of view, since it does not require high-cost customized hardware. Load balancing has been considered as a primary means to achieve high performance in multi processor systems. We claim, however, that in case of DPI system design simply balancing the load of each processor does not necessarily yield the highest system performance. Instead, we propose a method in which tasks are allocated to processors based on their functions. We implemented the proposed method in dual processor Linux system and compare its performance with the existing load balancing methods. Under the proposed method, one processor is dedicated to deal with interrupt handling and generic packet processing, while another processor is dedicated to DPI processing. According to experimental results, the proposed scheme outperforms the existing schemes by 60%, mainly because of the reduction of cache miss and spin lock occurrences.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.201-204
• /
• 2003

At a consequence of WWW large popularity, the internet has suffered from various performance problems, such as network congestion and overloaded servers. These days, it is not uncommon to find servers refusing connections because they are overloaded. Web server performance has always been a key issue in the design and operation of on-line systems. With regard to Internet, performance is also critical, because users want fast and easy access to all objects (e.g., documents, graphics, audio, and video) available on the net. To solve this problem, a number of companies are exploring the benefits of having multiple geographically or locally distributed Internet sites. This requires a comprehensive scheme for traffic management, which includes the principle of an optimal load balancing of client requests across multiple clusters of real servers. This paper focuses on the performance analysis of Web server and we apply these results to load balancing in clustering web server. It also discusses the mam steps needed to carry out a WWW performance analysis effort and shows relations between the workload characteristics and system resource usage. Also, we will introduce an optimal load balancing algorithm base on the RTSM (Real-Time Server Monitor) and Fuzzy Inference Engine for the local status of a real server, and the benefits is provided with of the suggested method.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.06a
• /
• pp.59-60
• /
• 2014

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.45-52
• /
• 2008

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-Performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.1
• /
• pp.22-37
• /
• 2013

Content distribution to a large number of concurrent clients stresses both server and network. While the server limitation can be circumvented by deploying server clusters, the network limitation is far less easy to cope with, due to the difficulty in measuring and balancing network load. In this paper, we use two useful network load metrics, the worst link stress (WLS) and the degree of interference (DOI), and formulate the problem as partitioning the clients into disjoint subsets subject to the server capacity constraint so that the WLS and the DOI are reduced for each session and also well balanced across the sessions. We present a network load-aware partition algorithm, which is practicable and effective in achieving the design goals. Through experiments on PlanetLab, we show that the proposed scheme has the remarkable advantages over existing schemes in reducing and balancing the network load. We expect the algorithm and performance metrics can be easily applied to various Internet applications, such as media streaming, multicast group member selection.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.337-340
• /
• 2014

클라우드 시스템이 큰 이슈로 떠오르면서 그 기반이 되는 분산 파일 시스템에 관한 연구가 계속되고 있다. 최근 제안된 분산파일 시스템은 대부분 확장 가능하며 신뢰성이 있는 시스템으로 구성되어 있으며 내고장성(Fault tolerance)과 높은 가용성을 위해 데이터 복제 기법을 사용하며 하둡 분산 파일 시스템에서는 블락의 복제수를 기본3개로 지정한다. 그러나 이 정책은 복제수가 많아지면 많아질수록 가용성은 높아지지만 스토리지 또한 증가한다는 단점이 있다. 본 논문에선 이러한 문제점을 해결하기 위해 최소한의 블락 복제수와 복제된 블락을 효율적으로 배치하여 더 좋은 성능과 부하분산(Load Balancing)하기 위한 기법을 제안한다.