• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.251-258
• /
• 2023

It is necessary to predict peak load accurately in order to supply electric power and operate the power system stably. Especially, it is more important to predict peak load accurately in winter and summer because peak load is higher than other seasons. If peak load is predicted to be higher than actual peak load, the start-up costs of power plants would increase. It causes economic loss to the company. On the other hand, if the peak load is predicted to be lower than the actual peak load, blackout may occur due to a lack of power plants capable of generating electricity. Economic losses and blackouts can be prevented by minimizing the prediction error of the peak load. In this paper, the latest deep learning model such as TCN is used to minimize the prediction error of peak load. Even if the same deep learning model is used, there is a difference in performance depending on the hyper-parameters. So, I propose methods for optimizing hyper-parameters of TCN for predicting the peak load. Data from 2006 to 2021 were input into the model and trained, and prediction error was tested using data in 2022. It was confirmed that the performance of the deep learning model optimized by the methods proposed in this study is superior to other deep learning models.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.859-866
• /
• 2001

Recently, fault injection techniques are used for evaluation of the fault coverage properties of safety-critical systems. This paper describes the TCN Fault Injector(TFI) implemented for TCN safety analysis. The implemented TFI injects network level faults to Intelligent MVB Controller that is designed for the Korean High Speed Train. With TFI, it can be verified whether the MVB controller meets TCN specification and its safety requirements.

• Proceedings of the KIEE Conference
• /
• 1999.07a
• /
• pp.483-485
• /
• 1999

Recently, distributed control network system has been widely applied to on-board control system than conventional relay logic with control wire. This paper presents two configuration of driver's desk system using TCN(Train Communication Network). One is configured with TCN, the other is partial adoption of TCN.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.573-574
• /
• 2009

열차 통신의 목적은 분산 제어 시스템에서 빠르고 정확한 데이터 교환에 있다. 이를 위하여 개발되고 1999년 IEC와 IEEE에 의해 국제 규격으로 승인된 TCN(Train Communication Network)은 차량간 통신 버스인 WTB(Wired Train Bus)와 차량내 통신 버스인 MVB(Multifunction Vehicle Bus)의 이중 계층 구조로 구성되며 TCN의 데이터 서비스는 프로세스 데이터, 메시지 데이터, 관리용 데이터의 세가지 데이터 서비스로 구분된다. MVB는 전송 가능한 데이터 서비스에 따라 디바이스의 클래스가 나눠지게 된다. 본 논문에서는 MVB에서 버스 마스터의 프레임에 따라 데이터를 보낼 수 있는 슬레이브 컨트롤러의 구성과 시뮬레이션을 통해 구현된 장치의 기능이 국제 표준의 제안사항들을 따르고 있는 지 증명한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.325-327
• /
• 2023

Diabetes is a common chronic disease that threatens human life and health, and its prevalence remains high because its mechanisms are complex, further its etiology remains unclear. According to the International Diabetes Federation (IDF), there are 463 million cases of diabetes in adults worldwide, and the number is growing. This study aims to explore the potential influencing factors of diabetes by learning data from the UCI diabetes dataset, which is a multivariate time series dataset. In this paper we propose the TCN-prophet model for diabetes. The experimental results show that the prediction of insulin concentration by the TCN-prophet model provides a high degree of consistency, compared to the existing LSTM model.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.129-139
• /
• 2023

Forecasting volatility is essential to avoiding the risk caused by the uncertainties of an financial asset. Complicated financial volatility features such as ambiguity between non-stationarity and stationarity, asymmetry, long-memory, sudden fairly large values like outliers bring great challenges to volatility forecasts. In order to address such complicated features implicity, we consider machine leaning models such as LSTM (1997) and GRU (2014), which are known to be suitable for existing time series forecasting. However, there are the problems of vanishing gradients, of enormous amount of computation, and of a huge memory. To solve these problems, a causal temporal convolutional network (TCN) model, an advanced form of 1D CNN, is also applied. It is confirmed that the overall forecasting power of TCN model is higher than that of the RNN models in forecasting VIX, VXD, and VXN, the daily volatility indices of S&P 500, DJIA, Nasdaq, respectively.

• Reproductive and Developmental Biology
• /
• v.29 no.1
• /
• pp.31-36
• /
• 2005

The purpose of this study was an improvement of efficiency and quality in the production of Korean Native Cow embryos. We investigated effects of concentration of ammonia in in vitro maturation (IVM) medium. In addition, we examined effects of addition or exchange of IVM medium on subsequent development and the cell numbers of blastocysts. The concentrations of ammonia in IVM medium was significantly increased by the increasement of IVM duration (p<0.05). The development rates to the 2 cell-, 8 cell- and blastocyst-stage embryos with the addition of IVM medium were similar among treatment groups. The number of inner cell mass (ICM) cells and the total cell number (TCN) of blastocysts were not differ among treatment groups, whereas the trophectoderm (TE) cell number was significantly lower in the group of 4.5 h addition. The ICM/TCN ratio was significantly higher in the group of 4.5 h addition than in the group of control and 9 h addition. The development rate to the 2-cell embryo with the exchange of IVM medium was significantly higher in the group of 4.5 h exchange and 9 h exchange than in control. The development rate to the blastocyst stage was the highest in the group of 9 h exchange. The number of ICM and ICM/TCN ratio were significantly higher in the group of 9 h exchange than the other groups. The numbers of TE and TCN was similar among treatment groups.

• Proceedings of the KSR Conference
• /
• 2006.05b
• /
• pp.742-755
• /
• 2006

• Proceedings of the KIEE Conference
• /
• 2003.07b
• /
• pp.1335-1337
• /
• 2003

한국형 고속 전철 과제는 6년의 과제 기간을 가시는 국가 연구 사업으로, 한국 실정에 적합한 차세대 고속 전철을 시험 제작하여 운용하는 것이 목적이다. 시속 350 km/h의 운행 속도를 목표로 하는 한국형 고속 전철은 현재 개발이 완료되어, 시험 주행 트랙에서 증속을 위한 시험 운행을 계속하고 있다. 한국형 고속 전철은 열차 내 각종 제어 장치들 간의 데이터 교환를 위해서 실시간 네트워크인 열차통신 네트워크(Train Communication Network; TCN)를 사용한다. 약 10년간의 표준 보완 기간을 거쳐서 1999년 국제 표준으로 확정된 TCN(IEC61373)은 열차 전용의 실시간 통신 네트워크로 열차 장치의 제어 및 진단에 적합한 다양한 기능과 특징을 가지고 있다. 한국형 고속전철은 열차의 주 제어 및 감시를 담당하는 주관 제어장치(SCU, Supervisory Control Unit)와 열차 안전에 중요한 역할을 하는 자동 열차 제어 장치(ATC, Automatic Train Control)을 포함하는 55개의 제어 장치들이 TCN으로 연결되어서 상호간의 데이터 교환을 수행하도록 구성되어 있다. 본 논문에서는 한국형 고속전철에 사용될 TCN의 구조와 실제 필드에 사용되어지기 위해서 필수적으로 필요한 네트워크의 고장 진단 기법에 대해서 설명한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.9
• /
• pp.38-45
• /
• 2016

For higher efficiency and reliability of railroad trains with many electronic sensors and actuators, a distributed control system with which electronic components communicate with each other in a distributed manner via a data network is considered. This paper considers Ethernet-based Train Communication Network (TCN) for this purpose and proposes a methodology to optimize the topology in terms of transmission latency and reliability, each of which is modeled as the number of traversing backbone nodes and the number of cables between vehicles, respectively. An objective function is derived accordingly and a closed-form optimum is obtained by relaxing the integer constraint of the number of vehicles for a unit network. Then, the final integer optimum is searched around it. Through numerical evaluation, the validity of the proposed methodology and the characteristics of the resulting solutions are shown.