• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.115-126
• /
• 2023

Due to the fluctuating random and periodical nature of renewable energy generation power quality disturbances occurred more frequently in power generation transformation transmission and distribution. Various power quality disturbances may lead to equipment damage or even power outages. Therefore it is essential to detect and classify different power quality disturbances in real time automatically. The traditional PQD identification method consists of three steps: feature extraction feature selection and classification. However, the handcrafted features are imprecise in the feature selection stage, resulting in low classification accuracy. This paper proposes a deep neural architecture based on Convolution Neural Network and Long Short Term Memory combining the time and frequency domain features to recognize 16 types of Power Quality signals. The frequency-domain data were obtained from the Fast Fourier Transform which could efficiently extract the frequency-domain features. The performance in synthetic data and real 6kV power system data indicate that our proposed method generalizes well compared with other deep learning methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.2
• /
• pp.139-147
• /
• 2008

The positioning accuracies tend to deteriorate as the distance between the rover and the reference station increases in the Real-Time Kinematic (RTK) surveys using Global Positioning System (GPS). To solve this problem, the National Geographic Information Institute (NGII) of Korea has installed Virtual Reference System (VRS), which is one of the network-based RTK systems. In this study, we conducted the accuracy tests of the VRS-RTK surveys. We surveyed 50 control points inside the NGII's GPS Continuously Operating Reference Stations (CORS) network using the VRS-RTK system, and compared the results with the published coordinates to verify the positioning accuracies. We also conducted the general RTK surveys at the same control points. The results showed that the positioning accuracy of the VRS-RTK was comparable to that of the general RTK, because the horizontal positioning accuracy was 3.1 cm while that of general RTK was 2.0 cm. Also the vertical positioning accuracy of VRS-RTK was 6.8 cm.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.402-411
• /
• 2020

Power line noise in electrocardiogram signals makes it difficult to diagnose cardiovascular disease. ECG signals without power line noise are needed to increase the accuracy of diagnosis. In this paper, it is proposed DNN(Deep Neural Network) model to remove the power line noise in ECG. The proposed model is learned with noisy ECG, and clean ECG. Performance of the proposed model were performed in various environments(varying amplitude, frequency change, real-time amplitude change). The evaluation used signal-to-noise ratio and root mean square error (RMSE). The difference in evaluation metrics between the noisy ECG signals and the de-noising ECG signals can demonstrate effectiveness as the de-noising model. The proposed DNN model learning result was a decrease in RMSE 0.0224dB and a increase in signal-to-noise ratio 1.048dB. The results performed in various environments showed a decrease in RMSE 1.7672dB and a increase in signal-to-noise ratio 15.1879dB in amplitude changes, a decrease in RMSE 0.0823dB and a increase in signal-to-noise ratio 4.9287dB in frequency changes. Finally, in real-time amplitude changes, RMSE was decreased 0.3886dB and signal-to-noise ratio was increased 11.4536dB. Thus, it was shown that the proposed DNN model can de-noise power line noise in ECG.

• The KIPS Transactions:PartC
• /
• v.8C no.5
• /
• pp.597-606
• /
• 2001

In this paper, we propose the delay sensitive traffic and a high bandwidth QoS service in order to supply real-time traffic such as VoIP, multimedia service. We use IntServ over DiffServ network to supply end-to-end QoS service in the IETF. We define the proposed QoS services which are Best, Good, Default service. We analyze the performance using NS simulator with end to end QoS service in IntServ over DiffServ network. The proposed billing system uses the Accounting, Authentication, Authorization (AAA) functions of RADIUS protocol and proposes the dynamic pricing method according to network usage state using end-to-end QoS of IntServ over DiffServ network. In order to secure billing system, we design and implement audit trail system by the IEEE POSIX.1E standard.

• Journal of Advanced Navigation Technology
• /
• v.19 no.5
• /
• pp.417-422
• /
• 2015

A service size of the IoT environment is determined by the number of sensors. The number of sensors increase means increases the amount of data generated by the IoT environment. There are studies to reliably operate a network for research and operational dynamic buffer for data when network congestion control congestion in the network environment. There are also studies of the stream data that has been processed in the connectionless network environment. In this study, we propose a sensor gateway for processing big data of the IoT environment. For this, review the RESTful for designing a sensor middleware, and apply the double-buffer algorithm to process the stream data efficiently. Finally, it generates a big data traffic using the MJpeg stream that is based on the HTTP protocol over TCP to evaluate the proposed system, with open source media player VLC using the image received and compare the throughput performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.1B
• /
• pp.53-60
• /
• 2007

We investigate the end-to-end delay bounds in large scale networks with Differentiated services (DiffServ) architecture. It is generally understood that networks with DiffServ architectures, where packets are treated according to the class they belong, can guarantee the end-to-end delay for packets of the highest priority class, only in lightly utilized cases. We focus on tree networks, which are defined to be acyclic connected graphs. We obtain a closed formula for delay bounds for such networks. We show that, in tree networks, the delay bounds exist regardless of the level of network utilization. These bounds are quadratically proportional to the maximum hop counts in heavily utilized networks; and are linearly proportional to the maximum hop counts in lightly utilized networks. Considering that tree networks, especially the Ethernet networks are being accepted more and more for access networks as well as provider networks, we argue that based on these delay bounds DiffServ architecture is able to support real time applications even for a large network. Throughout the paper we use Latency-Rate (LR) server model, with which it has proven that FIFO and Strict Priority are LR servers to each flows in certain conditions.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2663-2675
• /
• 1998

The billing manabement techniques for multiple services in the B-ISDN network have been rarely developed. In fact, the management techniques including billing manabement only focus on a single service environment. In this paper, we propose a billing management system architecture for the multiple services in a Broadband access network. The architecture is based in OSI system management infrastruture and TMN Q3 interface to exchange and process the billing information from access node that is an ATM Cross connecter. The system is designed to actively adopt the rapidly changing service environments and B-ISDN network management techniques. Futhermore, this system supports multiple services providers by real-time collector and charging functions for their requirements compared to the previous methodologies tat only use the statistical data.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.2
• /
• pp.254-264
• /
• 2000

The billing techniques to support multiple services in an ATM based broadband access network have been rarely developed. In fact, the management techniques including accounting management have only focused on a single service environment such as PSTN thus far. In this paper, we present an accounting management system, called rtFAMS, designed and implemented to provide multiple Value Added Service Providers (VASPS) the charging records for the multiple services in a broadband access network. The architecture is based on OSI system management infrastructure and TMN Q3 interface to acquire accounting information from agents in the ATM cross-connecters as well as to process the billing mechanisms in the manager. This system Is designed to actively adopt the rapidly changing service environments and B-ISDN network management techniques. It also provides real-time accounting information to users using Web in addition to supplying the billing records to VASPs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.4
• /
• pp.1344-1367
• /
• 2014

Mobile traffic is increasing a masse because of the propagation of the Internet and the development of wireless mobile technology. Accordingly, the Network Local Mobility Management (NETLMM) working group [1] of the Internet Engineering Task Force (IETF) has standardized Proxy Mobile IPv6 (PMIPv6) [2] as a protocol for accomplishing the transmissibility of mobile terminals. PMIPv6 is a network-led IP-based mobility management protocol, which can control terminal mobility without depending on the type of access system or the capability of the terminal. By combining PMIPv6 and the mobility of Session Initiation Protocol (SIP), we can establish terminal mobility and session mobility through a more effective route. The mobility function can be improved and the overlap of function reduced as compared to that in the case of independent operation. PMIPv6 is appropriate for a non-real-time service using TCP, and SIP is appropriate for a real-time service using RTP/UDP. Thus, in the case of a terminal using both services, an effective mobility management is possible only by using PMIPv6 together with SIP. In order to manage mobility in this manner, researches on PMIPv6-SIP are in progress. In line with this trend, this paper suggests a new PMIPv6-SIP architecture where when a mobile terminal conducts a handover, a network-led handover while maintaining the session without the addition of a special function or middleware is possible along with effective performance evaluation through mathematical modeling by comparing the delay and the packet loss that occur during the handover to the Pure-SIP.