• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.1
• /
• pp.13-17
• /
• 2018

According to the recent blackouts, large blackouts can be described by cascading outages. Cascading outage is defined by sequential outages from an initial disturbance. Sequential and probabilistic approach are necessary to minimize the blackout damage caused by cascading outages. In addition, conventional cascading outage analysis models are computationally complex and have time constraints, it is necessary to develop the new analytical techniques. In this paper, we propose the advance visualization model for probabilistic analysis of cascading failure risks. We introduce the visualization model for identifying size of cascading and potential outages and estimate the propagation rate of sequential outage simulation. The proposed model is applied to Korean power systems.

• Tribology and Lubricants
• /
• v.27 no.3
• /
• pp.167-173
• /
• 2011

In this paper, an actuator model of the thrust magnetic bearing for the flywheel energy storage is derived using magnetic circuit theory. And we compared this result with finite element magnetic field analysis result. Based on the actuator model, we made a simulation model of the thrust magnetic bearing system. We showed the closed loop transfer function and sensitivity function of the thrust magnetic bearing system using both the simulation model and the experiment. The experimental result at rotation velocity 18,000rpm of thrust magnetic bearing system is included.

• KEPCO Journal on Electric Power and Energy
• /
• v.5 no.3
• /
• pp.223-228
• /
• 2019

In order to integrate large amounts of variable generation resources such as wind and solar reliably into power grids, accurate renewable energy forecasting is necessary. Since renewable energy generation output is heavily influenced by environmental variables, accurate forecasting of power generation requires meteorological data at the point where the plant is located. Therefore, a spatial approach is required to predict the meteorological variables at the interesting points. In this paper, we propose the meteorological variable prediction model for enhancing renewable generation output forecasting model. The proposed model is implemented by three geostatistical techniques: Ordinary kriging, Universal kriging and Co-kriging.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.396-401
• /
• 2021

초거대 언어모델를 활용한 퓨샷(few shot) 학습법은 여러 자연어 처리 문제에서 좋은 성능을 보였다. 하지만 데이터를 활용한 추가 학습으로 문제를 추론하는 것이 아니라, 이산적인 공간에서 퓨샷 구성을 통해 문제를 정의하는 방식은 성능 향상에 한계가 존재한다. 이를 해결하기 위해 초거대 언어모델의 모수 전체가 아닌 일부를 추가 학습하거나 다른 신경망을 덧붙여 연속적인 공간에서 추론하는 P-tuning과 같은 데이터 기반 추가 학습 방법들이 등장하였다. 본 논문에서는 문맥에 따른 질의 정규화 문제를 대화형 음성 검색 서비스에 맞게 직접 정의하였고, 초거대 언어모델을 P-tuning으로 추가 학습한 경우 퓨샷 학습법 대비 정확도가 상승함을 보였다.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.3
• /
• pp.409-413
• /
• 2016

The 500 MW rated steam turbine model in coal fired power plant is developed to be used for validation and verification of controller rather than for the education of operator. The valve, steam turbine, reheater and generator are modeled and integrated into the simulator. And the data from the plant heat balance diagram are used for estimation of the model parameters together with actual operating data. It is found that the outputs of model such as pressure, temperature and speed are similar to the operating ones. So, it is expected that the developed model will play a very big role in controller development.

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.2
• /
• pp.163-171
• /
• 2020

A model test for assessment of towing stability and seakeeping of a multi-purpose mobile base (MMB) was performed in calm water and wave conditions. Scale ratio of the MMB was 1/48. Tension of the towing line was measured during tests to estimate effective power to tow the full scale MMB. The tests were repeated with towing speed. In addition, an inertial measurement unit was used to measure six DOF motion of the model. Seakeeping performance was assessed through the captive model test.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.4
• /
• pp.569-575
• /
• 2016

In this paper, we propose a method to develop a static equivalent model of an inverter-based distributed energy resource (DER), where the model is used for a steady-state fault analysis of a power grid. First, we introduce the characteristics of an inverter-based DER as well as its general configuration. Then, we derive the equivalent model of the DER on the basis of the characteristics. Last, the performance of the proposed method is proven by the results of computer simulations.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2018.11a
• /
• pp.418-419
• /
• 2018