• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.539-551
• /
• 2010

Low scalability and power efficiency of the shared bus in SoCs is a motivation to use on chip networks instead of traditional buses. In this paper we have modified the Orion power model to reach an analytical model to estimate the average message energy in K-Ary n-Cubes with focus on the number of virtual channels. Afterward by using the power model and also the performance model proposed in [11] the effect of number of virtual channels on Energy-Delay product have been analyzed. In addition a cycle accurate power and performance simulator have been implemented in VHDL to verify the results.

• Journal of Computing Science and Engineering
• /
• v.8 no.3
• /
• pp.173-179
• /
• 2014

In an opportunistic network, one of the most challenging issues is the equilibrium of the network traffic and transmission delay for forwarding messages. To resolve this problem, we propose a new forwarding scheme, called the direction entropy-based forwarding scheme (DEFS), using the main direction and direction entropy based on the information collected about the directions of the nodes in the network. Since each node sends a message to another node with a different location and less direction entropy, DEFS utilizes those nodes that are more likely to travel to various locations to forward the messages to the destination nodes. Experiments were performed on the network simulator NS-2. The results show that DEFS provides better balance than the typical forwarding schemes, such as Epidemic, PRoPHET, and WAIT.

• Journal of the Korea Society for Simulation
• /
• v.3 no.1
• /
• pp.115-124
• /
• 1994

In this paper, we have developed a performance analysis tool for communication networks called COMNAS. COMNAS analyses the performance of wide area networks such as Korea Educational Network and Korea Research Environment Open Network which include local area networks such as Ethernet and Token Ring. COMNAS consists of model constructor, simulation implementor, output analyzer and user interface. Attributes of communication networks for modeling either have default values or are entered by user as object units, and implementation of simulation is automatically proceeded by user interface. Ouput results obtained by COMNAS are the status of node, link and entire network such as mean message transmission delay, throughput, utilization, and so on, and they can be selectively obtained upon the request of the user.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.5
• /
• pp.1200-1207
• /
• 1996

The paper presents and analyzes two efficient burst-level bandwidth reservation protocols for multi-hop ATM Local Area Networks. With the tell-and-wait (TNW) protocol and the tell-and-go (TNG) protocol[6], a negative acknowledgmen(NACK) message representing the bandwidth starvation on a switch on the source-destnation path can be always sent by a destination. We note that the protocols waste more bandwidth as the round-trip delay increases, since the switches on the path must reserve the bandwidth until the NACK will arrive. Based on this pitfall, the proposed protocols allow and ATM node, rather than a destination node to send a NACK. This allowance can save the needless bandwidth wastage. Using the thinned load approximation method, we show the proposed protocols have good performance and practical simplicity. Thus, the proposed protocols may be candidates for the ABR service in multi-hop ATM LANs and ATM WANs.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1656-1660
• /
• 2006

Distributed coordination function(DCF) is the primary random access mechanism of IEEE 802.11, which is the basic protocol of wireless LAN based on the CSMA/CA protocol. It enables fast installation with minimal management and maintenance costs and is a very robust protocol for the best effort service in wireless medium. The current DCF, however, is known to be unsuitable for real-time applications such as voice message transmission. In this paper, we focus on the performance issues of IEEE 802.11 which accommodate the prioritized messages. Existing results use the initial window size and backoff window-increasing factor as tools to handle the priority of the messages. Instead, we introduce a novel scheme which chooses the backoff timer with arbitrary probabilities. By this, one can greatly reduce the backoff delay of the lower priority messages without degrading the performance of higher priority.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.1
• /
• pp.16-24
• /
• 2000

In the distributed multimedia document system, media objects distributed over a computer network are retrieved from their sources and presented to users according to specifed temporal relations. For effective presentation, synchronization have to he supported. Furthermore, presentation in distributed environments is influenced by network band with and delay, so they have to be considered for synchronization. This paper propose a distributed multimedia presentation model that supports synchronization effectively. In this model, when media objects are transfered from servers to a client, network situation and resources are monitored and thus a feedback message for change of them is sent to sever. Then, the sever adjusts the data sending rate to control synchronization.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.110-113
• /
• 1999

In this paper. we propose an adaptive handover scheme in wireless network The proposed handover scheme is a hybrid type of virtual path extension and rerouting. The proposed handover scheme chooses the virtual path management scheme according to the service QoS instead of the network topology which is used in the previous hybrid handover schemes. The proposed scheme supports the seamless service and small buffering during virtual path rerouting handover through the multicasting service. To evaluate the performance of the proposed scheme. we compute the number of signaling message used for handover and perform computer simulation. The simulation results show that the proposed scheme provides more efficiency in the handover delay and seamless service than the previous methods.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.45-48
• /
• 2003

We can easily buy network system for high performance micro-processor, progress computer architecture is caused of high bandwidth and low delay time. Coupling PC-based commodity technology with distributed computing methodologies provides an important advance in the development of single-user dedicated systems. Lately Network is joined PC or workstation by computers of high performance and low cost. Than it make intensive that Cluster system is resembled supercomputer. Unix, Linux, BSD, NT(Windows series) can use Cluster system OS(operating system). I'm chosen linux gain low cost, high performance and open technical documentation. This paper is benchmark performance of Beowulf clustering by UltraSPARC-1K(64bit-RISC processor). Benchmark tools use MPI(Message Passing Interface) and NetPIPE. Beowulf is a class of experimental parallel workstations developed to evaluate and characterize the design space of this new operating point in price-performance.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.6
• /
• pp.19-25
• /
• 2002

A regular virtual topology requires little processing time for routing purposes which may be a desirable property for high-speed networks. Asymmetric bilayered ShuffleNet, proposed by us as a virtual topology, can be more efficient to be used to design a wide-area optical network compared to ShuffleNet. In this paper, asymmetric bilayered ShuffleNet is imbedded on a given physical topology with the objective of minimizing the total message delay.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.1
• /
• pp.41-52
• /
• 2012

Recently, FlexRay was developed to replace controller area network (CAN) protocol in chassis networking systems, to remedy the shortage of transmission capacity and unsatisfactory real-time transmission delay of conventional CAN. FlexRay network systems require correct synchronization and complex scheduling parameters. However, because platform configuration register (PCR) setting and message scheduling is complex and bothersome task, FlexRay is more difficult to implement in applications than CAN protocol. To assist a network designer for implementing FlexRay cluster, this paper presents an analysis of FlexRay platform configuration register and automatic generation program of PCR. To demonstrate the feasibility of the automatic generation program, we evaluated its performance using experimental testbed.