• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.10a
• /
• pp.368-371
• /
• 2000

The distributed object computing is possible to distributed computing on same or heterogeneous machine environment with growth of distributed computing and object-oriented technology. The typical of model, CORBA is int solved the interoperability in heterogeneous machine environment over the network But, the CORBA has a problem that the server is can't rely on request of client occurs network overhead by extinction of network A plan was on the rise to solve the problem that is combination of mobile agent and distributed computing technology.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11B
• /
• pp.972-984
• /
• 2003

In this paper, new on-line routing algorithms with a bandwidth constraint are proposed. The proposed algorithms may be used for a dynamic LSP setup in MPLS network. We extend the WSP algorithm, the SWP algorithm and a utilization-based routing algorithm into the proposed algorithms by slightly modified K-shortest loopless path algorithms. The performances such as accepted bandwidth, accepted request number and average path length of the proposed and the previous algorithms are evaluated through extensive simulations. All simulations are conducted under the condition that any node can be an ingress or egress node for a LSP setup. The simulation results show that the proposed algorithms have the good performances in most cases in comparison to the previous algorithms. Under the heavy load condition, the algorithms based on the minimum hop path perform better than any other algorithms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.643-645
• /
• 2015

Real life has been actively utilizing storage from anywhere automobiles and Aviation field etc to the development of storage. Recent Big Data is stored as a number of data storage and data distribution processing emerged in research has been actively conducted to process the data. But many bottlenecks or processing speed slows down when you request the data at the same time a problem arises. In this paper consider should be used in the field of big data storing and processing large amounts of data, the process data more efficiently when the number of data request and data suggest that the weight-effective, manageable data processing system algorithm.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.487-492
• /
• 2003

To satisfy the requirements for QoS of Users using multimedia content stream service, it is required to control mechanism for QoS based on class priority, URFA classifies the user by two classes (super class, base class) and controls the admission ratio of user's requests by user's class information. URFA increases the admission ratio class and utilization ratio of stream server resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4640-4661
• /
• 2018

To cope with the explosive growth of Internet services, Service Function Chaining (SFC) based on Software-defined Networking (SDN) is an emerging and promising technology that has been suggested to meet this challenge. Determining the placement of Virtual Network Functions (VNFs) and routing paths that optimize the network utilization and resource consumption is a challenging problem, particularly without violating service level agreements (SLAs). This problem is called the optimal SFC placement problem and an Integer Linear Programming (ILP) formulation is provided. A greedy heuristic solution is also provided based on an improved two-step mapping algorithm. The obtained experimental results show that the proposed algorithm can automatically place VNFs at the optimal locations and find the optimal routing paths for each online request. This algorithm can increase the average request acceptance rate by about 17.6% and provide more than 20-fold reduction of the computational complexity compared to the Greedy algorithm. The feasibility of this approach is demonstrated via NetFPGA-10G prototype implementation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.894-897
• /
• 2008

This paper analyzes the throughput performance of a selective repeat (SR)/automatic repeat request (ARQ) scheme to transmit packet data in burst home network channel. To combat the high degree of error caused by transmission of home network data a robust error control scheme is a necessity. Basically, error control schemes can be divided in two categories: ARQ schemes and forward error correction (FEC) schemes. ARQ schemes are often used for reliable data transmission. The performance of packet transmission using SR-ARQ schemes for bursty channels is analyzed and simple analytical expressions of its throughput are presented. Theoretic analysis and numerical results indicate that a small number of packet sizes can get good performance in bursty home network channel.

• Journal of KIISE:Information Networking
• /
• v.31 no.3
• /
• pp.259-268
• /
• 2004

According to the increasing demand of application software that must be applied to the distributed computing environment, the various tools are proposed to write distributed softwares. But, if using these tools, programmers have to know the usage of each tool requisite for writing distributed softwares. If programmers can write distributed software without additional knowledge, they can get better concentration of the functions of software itself to develop, because it reduces burden for distributed programming. In this paper. we introduce new distributed programming tool, named TORB(Transparent Object Request Broker). With TORB, thanks to programming transparency that is supported by TORB, we can write the distributed software with java more easily. After postprocessing, this software can run in the distributed processing environment that is supported by TORB.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1236-1245
• /
• 2000

This paper propose a novel scheme, called Mobiel Terminal Initiated Scheme(MTIS), in which mobile terminal initiates the backward handover by sending handover request message with the list of target radio ports. In this scheme, the old ATM switch suporting end-user mobility, denoted by EMAS\ulcorner, checks whether each EMAS\ulcorner, managing the target radio port, has its available resources. If it has, the EMAS\ulcorner performs the path rerouting between CrossOver Switch (COS) and itself after deciding the most suitable target radio port. Therefore, the MT initiates the handover after deciding the most suitable target radio port through the beacon signal of Wireless Access Point (WAP). The EMAS\ulcorner have only to check the resource availability of the target radio port. It is no need to waste time to decide the suitable target radio port. Also, once receiving the request of the resource availability, the EMAS\ulcorner can reduce the rerouting delay time due to perform the path rerouting to the COS. In comparison with that of the ATM-Forum procedure, our proposed MTIS handover delay time reduced 14~21%, and end-to-end transfer delay time reduced 2~9%, as a result of the simulation.

• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.26-31
• /
• 2016

Migrim(Migration enhanced Grid Middleware) is a communication middleware between embedded devices and multiple servers. In traditional client-server communication, users' requests are sent to and processed by a designated server even though the server may suffer from a heavy load. In addition, the designated server may not have proper information to process the user's request correctly. Proposed connection migration mechanism and transaction migration mechanism are designed to improve the performance and accuracy of request processing. The connection migration is a procedure for delegating a connection to another server, which results in a well-distributed balancing of load among the servers. The transaction migration is a procedure for delegating a transaction to another server, and improves the accuracy of response.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.1 s.39
• /
• pp.1-10
• /
• 2006

Load redistribution algorithm is a critical factor in computer system. In a receiver-initiated load redistribution algorithm, receiver(underloaded processor) continues to send unnecessary request messages for load transfer until a sender(overloaded processor) is found while the system load is light. Therefore, it yields many problems such as low CPU utilization and system throughput because of inefficient inter-processor communications until the receiver receives an accept message from the sender in this environment. This paper presents an approach based on genetic. algorithm(GA) for dynamic load redistribution in heterogeneous distributed systems. In this scheme the processors to which the requests are sent off are determined by the proposed GA to decrease unnecessary request messages.