• Journal of the Korea Society of Computer and Information
• /
• v.21 no.12
• /
• pp.115-124
• /
• 2016

In this paper, a method to generate the extended model automatically on the critical elements in enterprise system based real time distributed architecture as well as the platform specific model(PSM) for Microsoft(MS) .NET platform is proposed. The key ideas of this method are real time distributed architecture should performed with satisfying strict constraints on life cycle of object and response time such as synchronization, transaction and so on, and .NET platform is able to implement functionalities including before mentioned by only specifying Attribute Code and maximizing advantages of MDA. In order to realize the ideas, functionalities which should be considered enterprise system development are specified and these are to be defined in Meta Model and extended UML profile. In addition, after definition of UML profile for .NET specification, by developing and applying these into plug-in of open source MDA tool, and extended models are generated automatically through this tool. Accordingly, by using proposed specification technology, the profile and tools easily and quickly reusable extended model can be generated even though low level of detailed information for functionalities which is considered in .NET platform and real time distributed architecture. In addition, because proposed profile is MOF which is basis of standard extended and applied, UML and MDA tools which observed MOF is reusable.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.911-931
• /
• 2021

Recently, most cloud services use Docker container environment to provide their services. However, there are no researches to evaluate the performance of communication libraries for multi-GPU based distributed deep learning in a Docker container environment. In this paper, we propose an efficient communication architecture for multi-GPU based deep learning in a Docker container environment by evaluating the performances of various communication libraries. We compare the performances of the parameter server architecture and the All-reduce architecture, which are typical distributed deep learning architectures. Further, we analyze the performances of two separate multi-GPU resource allocation policies - allocating a single GPU to each Docker container and allocating multiple GPUs to each Docker container. We also experiment with the scalability of collective communication by increasing the number of GPUs from one to four. Through experiments, we compare OpenMPI and MPICH, which are representative open source MPI libraries, and NCCL, which is NVIDIA's collective communication library for the multi-GPU setting. In the parameter server architecture, we show that using CUDA-aware OpenMPI with multi-GPU per Docker container environment reduces communication latency by up to 75%. Also, we show that using NCCL in All-reduce architecture reduces communication latency by up to 93% compared to other libraries.

• Journal of Korean Society for Atmospheric Environment
• /
• v.21 no.1
• /
• pp.83-96
• /
• 2005

The purposes of this study were to characterize the local levels of VOCs (volatile organic compounds), to develop source profiles of VOCs, and to quantify the source contribution of VOCs using the CMB (chemical mass balance) model. The concentration of VOCs had been measured every 6-day duration in the SRO monitoring site in the Yeosu Petrochemical Industrial Complex from September 2000 to August 2002. The total of 35 target VOCs, which were included in the TO-14 designated from the U.S. EPA, was selected to be monitored in the study area. During a 24-h period, the ambient VOCs were sampled by using canisters placing about 10 ～ 15 m above the ground level. The collected canisters were then analyzed by a GC-MS in the laboratory. Aside from ambient sampling at the SRO site, the VOCs had been intensively and massively measured from 8 direct sources and 4 general sources in the study area. The results obtained in the study were as follows; first, the annual mean concentrations of the target VOCs were widely distributed regardless of monitoring sites in the Yeosu Petrochemical Industrial Complex. In particular, the concentrations of BTX (Benzene, Toluene, Xylene), vinyl chloride were higher than other target compounds. Second, based on these source sample data, source profiles for VOCs were developed to apply a receptor model, the CMB model. Third, the results of source apportionment study for the VOCs in the SRO Site were as follows; The source of petrochemical plant was apportioned by 31.3% in terms of VOCs mass. The site was also affected by 16.7% from wastewater treatment plant, 14.0% from iron mills, 8.4% from refineries, 4.4% from oil storage, 3.8% from automobiles, 2.3% from fertilizer, 2.3% from painting, 2.2% from waste incinerator, 0.6% from graphic art, and 0.4% from gasoline vapor sources.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.9
• /
• pp.16-23
• /
• 2009

In this paper, we propose a new distributed Alamouti space-time block coding scheme using cooperative relay system composed of one source node, three relay nodes and one destination node. The source node is assumed to be equipped with two antennas which respectively use a 2-beam array to communicate with two nodes selected from the three relay nodes. During the first time slot, the two signals which respectively were transmitted by one antenna at the source, are selected by one relay node, added, amplified, and forwarded to the destination. During the second time slot, the other two relay nodes implement the conjugate and minusconjugate operations to the two received signals, respectively, each in turn is amplified and forwarded to the destination node. This transmission scheme represents a new distributed Alamouti space-time block code that can be constructed at the relay-destination channel. Through an equivalent matrix expression of symbols, we analyze the performance of this proposed space-time block code in terms of the chernoff upper bound pairwise error probability (PEP). In addition, we evaluate the effect of the coefficient $\alpha$ ($0{\leq}{\alpha}{\leq}1$) determined by power allocation between the two antennas at the source on the received signal performance. Through computer simulation, we show that the received signals at the three relays have same variance only when the value of $\alpha$ is equal to $\frac{2}{3}$, as a consequence, a better performance is obtained at the destination. These analysis results show that the proposed scheme outperforms conventional proposed schemes in terms of diversity gain, PEP and the complexity of relay nodes.

• KNOM Review
• /
• v.23 no.1
• /
• pp.10-17
• /
• 2020

As the threat of Distributed Denial-of-Service attacks that exploit weakly secure IoT devices has spread, research on source-side Denial-of-Service attack detection is being activated to quickly detect the attack and the location of attacker. In addition, a collaborative source-side attack detection technique that shares detection results of source-side networks located at individual sites is also being activated to overcome regional limitations of source-side detection. In this paper, we evaluate the performance of a collaborative source-side DDoS attack detection using statistical weights. The statistical weight is calculated based on the detection rate and false positive rate corresponding to the time zone of the individual source-side network. By calculating weighted sum of the source-side DoS attack detection results from various sites, the proposed method determines whether a DDoS attack happens. As a result of the experiment based on actual DNS request to traffic, it was confirmed that the proposed technique reduces false positive rate 2% while maintaining a high attack detection rate.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.10-17
• /
• 2009

Wyner-Ziv video coding is a new video compression paradigm based on distributed source coding theory of Slepian-Wolf and Wyner-Ziv. Wyner-Ziv coding enables light-encoder/heavy-decoder structure by shifting complex modules including motion estimation/compensation task to the decoder. Instead of performing the complicated motion estimation process in the encoder, the Wyner-Ziv decoder performs the motion estimation for the generation of side information in order to make the predicted signal of the Wyner-Ziv frame. The efficiency of side information generation deeply affects the overall coding performance, since the bit-rates of the Wyner-Ziv coding is directly dependent on side information. In this paper, an improved side information generation method using field coding is proposed. In the proposed method, top fields are coded with the existing SI generation method and bottom fields are coded with new SI generation method using the information of the top fields. Simulation results show that the proposed method improves the quality of the side information and rate-distortion performance compared to the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.5
• /
• pp.1004-1009
• /
• 2004

Precise time synchronization is a main technology in high-speed communications, parallel and distributed processing systems, Internet information industry and electronic commerce. Synchronized clocks are useful for many leasers. Often a distributed system is designed to realize some synchronized behavior, especially in real-time processing in factories, aircraft, space vehicles, and military applications. Nowadays, time synchronization has been compulsory thing as distributed processing and network operations are generalized. A network time server obtains, keeps accurate and precise time by synchronizing its local clock to standard reference time source and distributes time information through standard time synchronization protocol. This paper describes design issues and implementation of a network time server for time synchronization especially based on a clock model. The system uses GPS (Global Positioning System) as a standard reference time source and offers UTC (universal Time coordinated) through NTP (Network Time protocol). Implementation result and performance analysis are also presented.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.2
• /
• pp.190-197
• /
• 2011

In industrial distributed control systems, sensors collect data from the physical environment periodically and transmit them to the actuators, which process the control operations based on the received data. For the effective operation of the control systems, the data transmitted by the sensors has to be delivered to the actuators reliably within the deadline, and if the message reception rate of the actuators becomes lower than a threshold, then the performance of the control systems drops greatly. This paper suggests a message routing protocol to transmit periodic messages reliably in a distributed control system based on wireless sensor networks. For reliable message transmission, the proposed protocol selects a routing path whose end-to-end message reception rate is the highest before transmitting data messages. The proposed protocol has the capability of maintaining a target message reception rate for each flow. To maintain the required target reception rate, each destination monitors the actual message reception rate periodically and transmits a feedback message to the source if it drops below the target reception rate. On receiving the feedback message, the source tries to find a new path which can satisfy the target rate. The performance of the proposed protocol has been evaluated using simulation and compared with other protocols in terms of the message reception rate, the message delay and delay jitter, and so on. The simulation results show that the proposed protocol has a higher message reception rate and comparable message delay and delay jitter to other protocols. The simulation results also show that the proposed protocol has an ability to adapt well to the dynamic network traffic change.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.7
• /
• pp.759-767
• /
• 2010

RT-eCos 3.0 is a micro-sized embedded real-time kernel that has been developed based on the open source eCos 3.0 to support the basic task model of the well-known distributed real-time object model, TMO(Time-Triggered Message-triggered Object). In this paper, the design and implementation techniques of the RMMC(Real-time Multicast & Memory replication Channel) that is a standard distributed IPC model of the TMO is described based on the RT-eCos 3.0. And the support technique of the global time for using the same time in a distributed environment using the RMMC is also described. The developed global time based RMMC supports highly abstracted distributed IPC environment in a wide area distributed computing environment with the RT-eCos 3.0.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.537-542
• /
• 2015

Database Shard is a technique that can be queried and stored by dividing one logical table into multiple databases horizontally. In order to analyze the shard data with aggregate or analysis functions, a process is required that integrates partial results on each shard database. In this paper, we introduce the design and implementation of a distributed processing system for aggregation and analysis on the CUBRID Shard distributed database, which is an open source database management system. The implemented system can accelerate the analysis onto multiple shards of partitioned tables; it shows efficient aggregation on shard distributed databases compared to stand-alone databases.