• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.92-92
• /
• 2023

본 연구에서는 대한민국 도시 유역에 대하여 딥러닝 네트워크 기반의 분산형 수문 모형을 개발하였다. 개발된 모형은 완전연결계층(Fully Connected Layer)으로 연결된 여러 개의 장단기 메모리(LSTM-Long Short-Term Memory) 은닉 유닛(Hidden Unit)으로 구성되었다. 개발된 모형을 사용하여 연구 지역인 중랑천 유역을 분석하기 위해 1km² 해상도의 239개 모델 격자 셀에서 10분 단위 레이더-지상 합성 강수량과 10분 단위 기온의 시계열을 입력으로 사용하여 10분 단위 하도 유량을 모의하였다. 모형은 보정과(2013~2016년)과 검증 기간(2017~2019년)에 대한 NSE 계수는각각 0.99와 0.67로 높은 정확도를 보였다. 본 연구는 모형을 추가적으로 심층 분석하여 다음과 같은 결론을 도출하였다: (1) 모형을 기반으로 생성된 유출-강수 비율 지도는 토지 피복 데이터에서 얻은 연구 지역의 불투수율 지도와 유사하며, 이는 모형이 수문학에 대한 선험적 정보에 의존하지 않고 입력 및 출력 데이터만으로 강우-유출 분할과정을 성공적으로 학습하였음을 의미한다. (2) 모형은 연속 수문 모형의 필수 전제 조건인 토양 수분 의존 유출 프로세스를 성공적으로 재현하였다; (3) 각 LSTM 은닉 유닛은 강수 자극에 대한 시간적 민감도가 다르며, 응답이 빠른 LSTM 은닉 유닛은 유역 출구 근처에서 더 큰 출력 가중치 계수를 가졌는데, 이는 모형이 강수 입력에 대한 직접 유출과 지하수가 주도하는 기저 흐름과 같이 응답 시간의 차이가 뚜렷한 수문순환의 구성 요소를 별도로 고려하는 메커니즘을 가지고 있음을 의미한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8A
• /
• pp.1169-1176
• /
• 2000

In this paper, label assignment schemes considering the IP flow model for the efficient MPLS traffic engineering are proposed and evaluated. Based on the IP flow model, the IP flows are classified into transient flows and base flows. Base flows, which last for a long time, transmit data in high bit rate, and be composed of many packets, have good implications for the MPLS traffic engineering, because they usually cause network congestion. To make use of base flows for the MPLS traffic engineering, we propose two base flow classifiers and label assignment schemes where transient flows are allocated to the default LSPs and base flows to explicit LSPs. Proposed schemes are based on the traffic-driven label triggering method combined with a routing tabel. The first base flow classifier uses both flow size in packet counts and routing entries, and the other one, extending the dynamic X/Y flow classifier, is based on a cut-through ratio. Proposed schemes are shown to minimize the number of labels, not degrading the total cut-through ratio.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.965-974
• /
• 2003

Today's network consists of a large number of routers and servers running a variety of applications. In this paper, we have designed and constructed the general simulation environment of network security model composed of multiple IDSs agent and a firewall agent which coordinate by CNP (Contract Net Protocol). The CNP, the methodology for efficient integration of computer systems on heterogeneous environment such as distributed systems, is essentially a collection of agents, which cooperate to resolve a problem. Command console in the CNP is a manager who controls the execution of agents or a contractee, who performs intrusion detection. In the knowledge-based network security model, each model of simulation environment is hierarchically designed by DEVS (Discrete Event system Specification) formalism. The purpose of this simulation is the application of rete pattern-matching algorithm speeding up the inference cycle phases of the intrusion detection expert system. we evaluate the characteristics and performance of CNP architecture with rete pattern-matching algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.12B
• /
• pp.758-766
• /
• 2007

IStreaming services with a client-server architecture have scalability problem because a server cannot accomodate clients more than its processing capability. This paper introduces a case study for implementing H.264 streaming system based on P2P architecture in order to provide scalable and stable broadcast streaming services over the internet. The prototype system called OmniCast264 consists of the H.264 encoding server, the streaming server, the proxy server, and peer nodes. The proxy server dynamically manages placement of the peer nodes on the P2P network. Omnicast264 has the concepts of distributed streaming loads, real-time playback, error-robustness and modularity. Thus, it can provide large-scale broadcast streaming services. Finally, we have built P2P streaming systems with 12 PCs connected serially or in parallel. The experiment shows that OmniCast264 can provide real-time playback.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.5
• /
• pp.351-359
• /
• 2009

Recently with increase of data in the Internet, platform technologies that can process huge data effectively such as Google platform and Hadoop are regarded as worthy of notice. In this kind of platform, there exist network I/O overheads to send task outputs due to the MapReduce operation which is a programming model to support parallel computation in the large cluster system. In this paper, we suggest applying of TIPC (Transparent Inter-Process Communication) protocol for reducing network I/O overheads and increasing network performance in the distributed computing environments. TIPC has a lightweight protocol stack and it spends relatively less CPU time than TCP because of its simple connection establishment and logical addressing. In this paper, we analyze main features of the Hadoop-based distributed computing system, and we build an experimental model which can be used for experiments to compare the performance of various protocols. In the experimental result, TIPC has a higher bandwidth and lower CPU overheads than other protocols.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.9 s.339
• /
• pp.29-40
• /
• 2005

In this paper, we propose a Cluster-based Multicast Routing (CMR) suitable for mobile ad-hoc networks. The main features that our proposed method introduces are the following: a) mobility-based clustering and group based hierarchical structure in order to effectively support stability and scalability, b) group based mesh structure and forwarding tree concepts in order to support the robustness of the mesh topologies which provides limited redundancy and the efficiency of tree forwarding simultaneously, and c) combination of proactive and reactive concepts which provide low route acquisition delay and low overhead. The performance evaluation of the proposed protocol is achieved via modeling and simulation. The corresponding results demonstrate the Proposed multicast protocol's efficiency in terms of packet delivery ratio, scalability, control overhead, end-to-end delay, as a function of mobility, multicast group size, and number of senders.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.351-359
• /
• 2010

In this paper, we propose a transmission algorithm of the TLI protocol of the IEC 61162-4 standard to perform the e-Navigation on ship, and we design and implement the TLI protocol according to the proposed algorithm. The implemented protocol is a TCP/IP based protocol, and is a network protocol with the MAU and LNA components proposed in the IEC 61162-4 standard. In addition, it makes a data transmission over the network architecture based on client/server network model. In the implemented protocol, there are a communication between the MAU and the LNA in one host, and also a communication between the LNA and the LNA in each other hosts. In order to provide a variety of service in a host, every client host has a LNA and multiple MAUs. According to the standard specification and the proposed transmission algorithm, we designed and implemented the TLI protocol using object-oriented mechanism. We carried out the experiment under a simple network model similar to real ship environment, and confirmed that it successfully transmits and receives data between the hosts.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.3
• /
• pp.127-143
• /
• 2022

Recently, many attempts to run numerical ocean models in cloud computing environments have been tried actively. A cloud computing environment can be an effective means to implement numerical ocean models requiring a large-scale resource or quickly preparing modeling environment for global or large-scale grids. Many commercial and private cloud computing systems provide technologies such as virtualization, high-performance CPUs and instances, ether-net based high-performance-networking, and remote direct memory access for High Performance Computing (HPC). These new features facilitate ocean modeling experimentation on commercial cloud computing systems. Many scientists and engineers expect cloud computing to become mainstream in the near future. Analysis of the performance and features of commercial cloud services for numerical modeling is essential in order to select appropriate systems as this can help to minimize execution time and the amount of resources utilized. The effect of cache memory is large in the processing structure of the ocean numerical model, which processes input/output of data in a multidimensional array structure, and the speed of the network is important due to the communication characteristics through which a large amount of data moves. In this study, the performance of the Regional Ocean Modeling System (ROMS), the High Performance Linpack (HPL) benchmarking software package, and STREAM, the memory benchmark were evaluated and compared on commercial cloud systems to provide information for the transition of other ocean models into cloud computing. Through analysis of actual performance data and configuration settings obtained from virtualization-based commercial clouds, we evaluated the efficiency of the computer resources for the various model grid sizes in the virtualization-based cloud systems. We found that cache hierarchy and capacity are crucial in the performance of ROMS using huge memory. The memory latency time is also important in the performance. Increasing the number of cores to reduce the running time for numerical modeling is more effective with large grid sizes than with small grid sizes. Our analysis results will be helpful as a reference for constructing the best computing system in the cloud to minimize time and cost for numerical ocean modeling.

• Journal of KIISE:Information Networking
• /
• v.29 no.3
• /
• pp.253-264
• /
• 2002

Recently, hierarchical architectures of databases for location management have been proposed in order to accommodate the increase in user population in future personal communication systems. In particular, a 3-level hierarchical database architecture is compatible with current cellular mobile systems. In the architecture, a newly developed additional databases, regional location database(RLR), are positioned between HLR and VLRs. We propose an efficient cache scheme, called the Double T-thresholds Location Cache Scheme. The cache scheme extends the existing T-threshold location cache scheme which is competent only under 2-level architecture of location databases currently adopted by IS-41 and GSM. The idea behind our scheme is to use two pieces of cache information, VLR and RLR serving called portables. The two pieces are required in order to exploit root only locality of registration area(RA) but also locality of regional registration area(RRA) which is the wide area covered by RLR. We also use two threshold values in order to determine whether the two pieces are obsolete. In order to model the RRA residence time, the branching Eralng-$\infty$ distribution is introduced. Our minute cost analysis shows that the double T-threshold location cache scheme yields significant reduction of network and database costs for molt patterns of portables.

• Information Systems Review
• /
• v.21 no.4
• /
• pp.125-141
• /
• 2019

With the advent of deep learning technology, which is represented by AlphaGo, artificial intelligence (A.I.) has quickly emerged as a key theme of digital transformation to secure competitive advantage for businesses. In order to understand the trends of A.I. based digital transformation, a clear comprehension of the A.I. business ecosystem should precede. Therefore, this study analyzed the A.I. business ecosystem from the multi-actor network perspective and identified the A.I. platform strategy type. Within internal three layers of A.I. business ecosystem (infrastructure & hardware, software & application, service & data layers), this study identified four types of A.I. platform strategy (Tech. vertical × Biz. horizontal, Tech. vertical × Biz. vertical, Tech. horizontal × Biz. horizontal, Tech. horizontal × Biz. vertical). Then, outside of A.I. platform, this study presented five actors (users, investors, policy makers, consortiums & innovators, CSOs/NGOs) and their roles to support sustainable A.I. business ecosystem in symbiosis with human. This study identified A.I. business ecosystem framework and platform strategy type. The roles of government and academia to create a sustainable A.I. business ecosystem were also suggested. These results will help to find proper strategy direction of A.I. business ecosystem and digital transformation.