• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.5
• /
• pp.55-64
• /
• 1996

This paper presents performance evaluation of a new high speed inter-processor communication(HIPC) network for large capacity and high performance digitral switching system. The HIPC structure implements the fast reservation and concurrent arbitration technique (modified round-robin arbitration). The performance evaluation of HIPC was performed by not only computer simulation but also numerical approximation method which was derived for a single server multi-queue system with nonexhaustive cyclic service. The approximation results are almost same with that of computer simulation. The TDX-10 basic callscenario was applied to the HIPC netowrk and analyzed. these results were compared with TDX-10 IPC and shows that the difference of th emean waiting time in the TX buffer of NTP node increases sharply according to the increase of the message arrival rate.

• Korean Management Science Review
• /
• v.25 no.3
• /
• pp.87-99
• /
• 2008

Besieged by needs for upgrading the current Internet, social pressures, and regulatory concerns, a network operator may be left with few options to Improve his services. Yet he can still consider a transition prioritizing network services. In this paper, we describe a transition from a non-priority system to a prioritized one, using non-preemptive M/G/1 model. After reviewing the constraints and theoretical results from past research, we describe steps making the transition Pareto-improving, which boils down to a multi-goal search for a Pareto-improving state. We use a genetic algorithm that captures actual transition costs along with incentive-compatible and Pareto-Improving constraints. Simulation results demonstrate that the initial post-transition solutions are typically Pareto-improving. for non Pareto-improving solutions, the heuristic quickly generates Pareto-improving and incentive-compatible solutions.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.87-93
• /
• 2007

In the component based software development, it is very important to interface between modules of component. Almost of existing method, Connectors are deal with all communication channels between two or more components/interfaces by RPC(Remote procedure call) and event call. But these process has limits when component send a lot of request call to other component through connector. That is, we need more efficient interface method that connector can process multi request call. In this paper, I propose interaction scheduling algorithm using message queue in the connector. For this purpose, I use message buffer which operate to save and load message temporarily.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.6
• /
• pp.584-590
• /
• 2000

Urban traffic situations are extremely complex and highly interactive. The multi-agent systems approach can provide a new desirable solution. Currently, a traffic simulator is needed to understand and explore the difficulties in an agent-oriented traffic control. This paper presents an agent-oriented fuzzy logic controller for multiple crossroads simulation. A fuzzy logic control simulation with variables of arrival, queue, and traffic volume could alleviate traffic congestion. We developed an agent-oriented simulator suitable for traffic junctions with η$\times$η intersections in Visual C++. The proposed method adaptively controls the cycle of traffic signals even though the traffic volume varies. The effectiveness of this method was shown through simulation of multiple intersections.

• Journal of the Korea Society for Simulation
• /
• v.13 no.4
• /
• pp.43-53
• /
• 2004

The distributed OCSP (Online Certificate Status Protocol), composed of multiple responders, is a model that enhances the utilization of each responder and reduces the response time. In a multi-user distributed environment, load balancing mechanism must be developed for the improvement of the performance of the whole system. Conservative load balancing algorithms often ignore the communication cost of gathering the information of responders. As the number of request is increased, however, fail to consider the communication cost may cause serious problems since the communication time is too large to disregard. We propose an adaptive load balancing algorithm and evaluate the effectiveness by performing modeling and simulation. The principal advantage of new algorithm is in their simplicity: there is no need to maintain and process system state information. We evaluated the quality of load balancing achieved by the new algorithm by comparing the queue size of responders and analyzing the utilization of these responders. The simulation results show how efficiently load balancing is done with the new algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.556-558
• /
• 2005

대용량의 고속 멀티미디어 데이터 전송 서비스, 주문형비디오 (VoD)와 같이 네트워크 어플리케이션 서비스를 포함하는 서비스들은 높은 대역폭을 요구한다. 이로 인하여, 네트워크에서 혼잡이 일어날 가능성이 증가된다. 네트워크의 혼잡을 피하기 위해서는 물리적인 방법과 논리적인 방법으로 나눌 수 있다. 물리적인 방법은 시간과 고성능의 장비를 필요로 하기 때문에 논리적인 방법으로 제한적인 네트워크의 자원을 효율적으로 사용할 필요성이 있다. 본 논문에서는 멀티미디어 데이터 QoS를 보장하기 위해 트래픽의 특성을 고려하는 차별적인 큐 관리 적용 방안을 제시하고, OPNET을 사용하여 이를 검증한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2226-2231
• /
• 2008

As the mobile devices and the wireless networks have high-performance capabilities, it is possible to synchronize the spatio-temporal data of a server with the spatio-temporal data of a mobile device which are collected at a field. However, since the server process the synchronization which the model device requests, the whole synchronizations of mass mobile devices take long time. In this paper, we propose the scheme to process concurrently the synchronizations of mobile devices to use multi-queue which does not conflict.

• Journal of the Korea Society for Simulation
• /
• v.11 no.1
• /
• pp.71-82
• /
• 2002

One of the most important things in the research for MIN-based switch operation the management scheme of network cycle. In the traditional MIN, when the receving buffer module is empty, the sell has to move forward the front-most buffer position by the characteristic of the conventional FIFO queue. However, most of buffer modules are almost always full for practical amount of input loads. The long network cycle of the traditional scheme is thus a substantial waste of bandwidth. In this paper, we propose the modeling method for the input and multi-buffered MIN with unit step buffering scheme, In spite of simplicity, simulation results show that the proposed model is very accurate comparing to previous modeling approaches in terms of throughput and the trend of delay.

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.784-795
• /
• 2016

In this paper, we investigate the resource allocation problem in time-varying heterogeneous wireless networks (HetNet) with multi-homing user equipments (UE). The stochastic optimization model is employed to maximize the network utility, which is defined as the difference between the HetNet's throughput and the total energy consumption cost. In harmony with the hierarchical architecture of HetNet, the problem of stochastic optimization of resource allocation is decomposed into two subproblems by the Lyapunov optimization theory, associated with the flow control in transport layer and the power allocation in physical (PHY) layer, respectively. For avoiding the signaling overhead, outdated dynamic information, and scalability issues, the distributed resource allocation method is developed for solving the two subproblems based on the primal-dual decomposition theory. After that, the adaptive resource allocation algorithm is developed to accommodate the timevarying wireless network only according to the current network state information, i.e. the queue state information (QSI) at radio access networks (RAN) and the channel state information (CSI) of RANs-UE links. The tradeoff between network utility and delay is derived, where the increase of delay is approximately linear in V and the increase of network utility is at the speed of 1/V with a control parameter V. Extensive simulations are presented to show the effectiveness of our proposed scheme.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.347-352
• /
• 2014

In this paper, we propose a Markovian queueing model(M/M/1)-based call admission control to reduce forced terminating rate of non-real secondary user's call for Multi-services Cognitive Radio Networks. A existing control has a problem that the forced terminating rate increases because of adopting a policy of spectrum priority allocation to real calls. In our scheme the rate can be reduced as the call that has no useful spectrum waits in a queue until getting an available spectrum. Our scheme use a neural-net based prediction of primary user's reappearance. Through the simulation, we analysis the call forced terminating rate, access delay and spectrum utilization efficiency, and then show that our scheme can more reduce the forced terminating rate of the call, compared to that of the existing algorithm.