• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.12
• /
• pp.75-82
• /
• 1991

We proposed an optimal parallel implementation of an optimization neural network with linear increase of speedup by using multicomputer system and presented performance analysis model of the system. We extracted the temporal-and the spatial-parallelism from the optimization neural network and constructed a parallel pipeline processing model using the parallelism in order to achieve the maximum speedup and efficiency on the CSP architecture. The results of the experiments for the TSP using the Transputer system, show that the proposed system gives linear increase of speedup proportional to the size of the optimization neural network for more than 140 neurons, and we can have more than 98% of effeciency upto 16-node system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.9
• /
• pp.1162-1170
• /
• 1995

In this paper, we present a message transfer scheme for efficient message passing in the hierarchically structured multiprocessor computer SPAX(Scalable Parallel Architecture computer based on X-bar network). The message transfer scheme provides interface not only with operating system but also with end users. In order to transfer two types of control message and data message efficiently, it supports both of memory-mapped transfer and DMA-based transfer. Dual-port RAMs are used as message buffers, and control and status registers provide efficient programming interface. Interlaced parity scheme is adopted for error control. If any error is detected at receiving node, errored packet is resent by sender according to retry mechanism. In conjunction with retry mechanism, watchdog timers are used to protect infinite waiting and repeated retry. The proposed message transfer scheme can be applied to input/output nodes and communication connection nodes as well as processing nodes in the SPAX.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.12
• /
• pp.9-19
• /
• 1997

This paper describes the design and FPGA implementation of a system control unit within a multiprocessor chip which can be used as a node processor ina massively parallel processing (MPP) caches, memory management units, a bus unit and a system control unit. Major functions of the system control unit are locking/unlocking of the shared variables of protected access, synchronization of instruction execution among four integer untis, control of interrupts, generation control of processor's status, etc. The system control unit was modeled in very high level using verilog HDL. Then, it was simulated and verified in an environment where trap handler and external interrupt controller were added. Functional blocks of the system control unit were changed into RTL(register transfer level) model and synthesized using xilinx FPGA cell library in synopsys tool. The synthesized system control unit was implemented by Xilinx FPGA chip (XC4025EPG299) after timing verification.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.349-351
• /
• 2003

무선 센서 네트웍은 동작 환경과 구조가 매우 특이하du 개발자들은 센서 네트웍의 노드를 디자인할 때 많은 제약 조건들과 요구 조건들을 고려해야 한다. 먼저 우선 센서 네트웍 상의 각 센서 노드에는 극도로 제한된 하드웨어 자원 조건 하에서도 무선 통신 기능뿐만 아니라 동시에 여러 이벤트를 재빠르게 처리할 수 있는 기능이 포함되어야 한다. 또한 환경과 응용 프로그램의 변화에 잘 대처하기 위해 런타임(run-time)에 각 센서 노드들을 동적으로 재구성할 수 있는 기능이 제공되어야 한다. 이러한 디자인 요구 조건들과 제약 조건들은 얼핏 서로 상반된 것처럼 보이는데, 무선 센서 노드들을 위한 실행 환경을 디자인할 때는 이러한 조건들을 모두 만족시킬 수 있는 운영 체제가 반드시 필요하다. 본 논문에서 우리는 무선 센서 노드들을 위한 매우 효율적이고 효과적인 유한 상태 머신(finite state machine) 기반의 운영체제, SenOS를 제안한다. 또한 새로운 운영 체제인 SenOS가 극도의 제한적인 자원에서도 동시성과 반응성, 재구성성의 요구 조건을 모두 만족시키면서 동작할 수 있다는 것을 보일 것이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.223-225
• /
• 2005

기존의 패킷 교환 네트워크는 해킹과 같은 보안 공격에 많은 취약점을 가지고 있다. 침입차단시스템 (Firewall system)과 침입탐지 시스템 (Intrusion Detection system)같은 보안 시스템이 개발되고 있지만 DOS나 Probe등을 비롯한 다양한 공격에 대해 적극적으로 대처 할 수 없다. 결과 DARPA를 비롯한 여러 기관에서 전송중인 액티브 패킷이 라우터에서 관리자의 정책을 담고 있는 코드를 실행할 수 있고 그 코드의 실행결과에 따라 라우터의 상태를 변경할 수 있는 액티브 네트워크 전반적인 구조를 제안하였다. 하지만 액티브 네트워크에서 중요한 것은 기존 네트워크와 달리 액티브 패킷이 액티브 노드의 자원에 접근함으로써 발생하게 되는 네트워크 보안이다. 따라서 액티브 노드의 NodeOs단에 Crypto engine, Integrity Engine, Authentication Engine, Authorization Engine등을 비롯한 액티브 노드 인증 및 액티브 패킷/코드 인증 보안 모듈을 둠으로써 액티브 노드 간 서로 안전한 협업적 관리를 통해 보안을 강화한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.7
• /
• pp.1335-1343
• /
• 2009

This paper focuses on the implementation of hand held typeARM11 Platform for gas sensor based on Embedded Linux OS. The S3C6400, which is ARM11 architecture based, is the key component of the ARM11 Platform, Bluetooth is adapted to consist the network for the wireless transmission of environmental data between a sensor node and hand held type ARM11 Platform. Linux is ported to the Platform, QT/embedded is used for the application development.

• Journal of information and communication convergence engineering
• /
• v.17 no.2
• /
• pp.97-104
• /
• 2019

Distributed mobility management (DMM) does not use a centralized device. Its mobility functions are distributed among routers; therefore, the mobility services are not limited to the performance and reliability of specific mobility management equipment. The DMM scheme has been studied as a partially distributed architecture, which distributes only a packet delivery domain in combination with the software defined network (SDN) technology that separates the packet delivery and control areas. Particularly, a separated control area is advantageous in introducing a new service, thereby optimizing the network by recognizing the entire network situation and taking an optimal decision. The SDN-based mobility management scheme is studied as a method to optimize the packet delivery path whenever a mobile node moves; however, it results in excessive signaling processing cost. To reduce the high signaling cost, we propose a hybrid distributed mobility management method and analyze its performance mathematically.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5252-5268
• /
• 2018

To support a large-scale Hadoop cluster, Hadoop heartbeat messages are designed to deliver the significant messages, including task scheduling and completion messages, via piggybacking to reduce the number of messages received by the NameNode. Although Hadoop is designed and optimized for high-throughput computing via batch processing, the real-time processing of large amounts of data in Hadoop is increasingly important. This paper evaluates Hadoop's performance and costs when the heartbeat period is controlled to support latency sensitive applications. Through an empirical study based on Hadoop 2.0 (YARN) architecture, we improve Hadoop's I/O performance as well as application performance by up to 13 percent compared to the default configuration. We offer a guideline that predicts the performance, costs and limitations of the total system by controlling the heartbeat period using simple equations. We show that Hive performance can be improved by tuning Hadoop's heartbeat periods through extensive experiments.

• Structural Engineering and Mechanics
• /
• v.70 no.3
• /
• pp.279-287
• /
• 2019

This paper intends to introduce a near-tip grid refinement and to explore its usefulness in the crack analysis by the natural element method (NEM). As a sort of local h-refinement in FEM, a NEM grid is locally refined around the crack tip showing the high stress singularity. This local grid refinement is completed in two steps in which grid points are added and Delaunay triangles sharing the crack tip node are divided. A plane-state plate with symmetric edge cracks is simulated to validate the proposed local grid refinement and to examine its usefulness in the crack analysis. The crack analysis is also simulated using a uniform NEM grid for the sake of comparison. The near-tip stress distributions and SIFs that are obtained using a near-tip refined NEM grid are compared with the exact values and those obtained using uniform NEM grid. The convergence rates of global relative error to the total number of grid points between the refined and non-refined NEM grids are also compared.

• Electronics and Telecommunications Trends
• /
• v.36 no.4
• /
• pp.13-22
• /
• 2021

Among the activities of 3GPP for operating 5G-based unmanned aerial vehicles, we introduce several use cases of UAVs in 5G mobile communication such as radio access node onboard UAV, simultaneous support data transmission for UAVs and eMBB users, autonomous UAVs controlled by AI, isolated deployment of radio access through UAV, and separation of UAV service area. From this, we further summarize 5G mobile communication requirements for UAVs, including definition and operational criteria of UAS, UAS remote identification requirements, UAS usage requirements, and performance requirements. Finally, regarding 5G mobile communication-based UAS connectivity, identification and tracking support, we discuss the 3GPP UAV architecture, seven major problems, the proposed solutions to each problem, and propose the results for future specification work.