• Journal of the Korea Society of Computer and Information
• /
• v.19 no.6
• /
• pp.81-92
• /
• 2014

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.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.39-48
• /
• 2014

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.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.12
• /
• pp.31-36
• /
• 2005

In this paper, we propose a new optical switching system as a infrastructure of the BcN, in which the high traffic volume will be expected due to the multimedia service, like P2P services. Because the JET protocol, the most popular protocol in OBS (Optical Burst Switching) research area, has high blocking probability for burst, it prevents commercialization in real network for its low throughput in TCP layer. To improve high blocking rate in OBS network, we segment large network into small network and perform burst scheduling to avoid burst loss. By using proposed scheme, Internet provider can reduce network deployment cost in Metro network as well as large mesh core networks

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.4
• /
• pp.40-46
• /
• 2011

Wireless Sensor Networks(WSNs) have shown a lot of good outcomes in providing a various functions depending on industrial expectations by deploying ad-hoc networking with helps of light loaded and battery powered sensor nodes. In particular, it is strongly requested to develop an algorithm of cross-layer control between 2-layer and 3-layer to deriver the sensing data from the end node to the sink node on time. In this paper, based on the above observation we have proposed an IEEE802.15.4 based self priority routing scheme under UC Berkely TinyOS platform. The proposed beacon based priority routing (BPR) algorithm scheme utilizes beacon periods in sending message with embedding the high priority data and thus provides high quality of service(QoS) in the given criteria. The performance measures are the packet Throughput, delivery, latency, total energy consumption. Simulation results under TinyOS Simulator(TOSSIM) have shown the proposed scheme outcome the conventional Ad hoc On-Demand Distance Vector(AODV) Routing.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.12
• /
• pp.54-62
• /
• 2007

Mobile IPv6 is the representative standard protocol proposed to offer mobility of mobile hosts, but it has drawbacks such as high handover latency and packet loss during handover. To complement these drawbacks, several protocols have been proposed and they can support faster handover than the Mobile IPv6, but there still exists inevitable packet loss during handover in those protocols. In this paper, we propose a new handover procedure of mobile host who has a dual link for minimizing packet loss rate during micro handover to improve mobility capability of Cellular Ethernet system that supports mobility at layer 2. And we derive the superiority of proposed scheme by comparing in terms of packet loss rate, handover latency and throughput of proposed scheme with those of Hierarchical Mobile IPv6 which is the representative IP-layer micro mobility protocol by simulation.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.411-422
• /
• 2017

Current policies for sharing bandwidth increase average throughput and improve utilization of the bandwidth in the local network. However, with these policies, a central administer, which is responsible for allocating bandwidth to each network flow, cannot allocate resources based on user characteristics. Thus, it leads to unfair bandwidth allocation because it does not guarantee services based on user characteristics. Therefore, we propose a novel negotiation method to share the bandwidth in a limited bandwidth network, in which, a user negotiates with other users to gain more resource. Ideally, we use a fuzzy system to infer and determine whether a device will request bandwidth or not based on the current usage of the given device. We conduct two experiments consisting of a video streaming simulation in OPNET and a real-time video streaming in WebRTC. The results of the experiment indicate that the proposed method can flexibly share the bandwidth utilization based on user's requirement in the network.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.8
• /
• pp.75-84
• /
• 2004

In this paper, we proposed an efficient hardware architecture of line-based lifting algorithm for Motion JPEG2000. We proposed a new architecture of a lifting-based filtering cell which has an optimized and simplified structure. It was implemented in a hardware accommodating both (9,7) and (5,4) filter. Since the output rate is linearly proportional to the input rate, one can obtain the high throughput through parallel operation simply by adding the hardware units. It was implemented into both of ASIC and FPGA The 0.35${\mu}{\textrm}{m}$ CMOS library from Samsung was used for ASIC and Altera was the target for FRGA. In ASIC, the proposed architecture used 41,592 gates for the lifting arithmetic and 128 Kbit memory. For FPGA it used 6,520 LEs(Logic Elements) and 128 ESBs(Embedded System Blocks). The implementations were stably operated in the clock frequency of 128MHz and 52MHz, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4B
• /
• pp.153-161
• /
• 2005

In a multi-channel network based of wavelength division multiplexing (WDM) technology, an efficient protocol is needed in order for the transmitter and receiver to be tuned to the same wavelength during message transmission time. This paper proposes a priority-based reservation protocol that can efficiently support variable-length messages that require different QoS requirements. In this proposed protocol, high-priority nodes can reserve the data channel before low-priority nodes. However, once a node reserves a data channel successfully, it can persistently use the reserved channel till message transmission is finished regardless of the priority of the node. Moreover, the protocol can operate independently of the number of nodes, and any new node can join the network anytime without requiring network re-initialization. The protocol is analyzed with a finite population model and the throughput-delay characteristics are investigated as performance measures.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2A
• /
• pp.80-89
• /
• 2005

In IEEE 802.11 and 802.11e for ad hoc networks, DCF and EDCA use a contention-based protocol called CSMA/CA, which is simple to implement efficient when the system is light loaded. But the performance of CSMA/CA decreases dramatically when the system load is heavy because of increasing collisions. In PCF and HCF modes, stations are controlled by a base station by polling, no collision ever occurs. However, when the system load is light, the performance is poor because few stations have data to transfer. More important, PCF and HCF can not be used in the ad hoc networks. In this paper, we address a priority-based distributed polling mechanism (PDPM) that implements polling scheme into DCF or EDCA modes for ad hoc networks by adding a polling approach before every contention-based procedure. PDPM takes the advantages of polling mechanism that avoids most of collisions in a high load condition. At the same time, it also keeps the contention-based mechanism for a light loaded condition. PDPM provides quality of service (QoS) with fewer collisions and higher throughput compared with IEEE 802.11e.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.315-323
• /
• 2001

The concept of vertical partitioning has been discussed so far in an objective of improving the performance of query execution and system throughput. It can be applied to the areas where the match between data and queries affects performance, which includes partitioning of individual files in centralized environments, data distribution in distributed databases, dividing data among different levels of memory hierarchies, and so on. In general, a vertical partitioning algorithm should support n-ary partitioning as well as a globally optimal solution for the generation of all meaningful fragments. Most previous methods, however, have some limitations to support both of them efficiently. Because the vertical partitioning problem basically includes the fuzziness property, the proper management is required for the fuzziness problem. In this paper we propose an efficient vertical $\alpha$-partitioning algorithm which is based on the fuzzy theory. The method can not only generate all meaningful fragments but also support n-ary partitioning without any complex mathematical computations.