• 전력전자학회논문지
• /
• 제20권3호
• /
• pp.290-295
• /
• 2015

Analysis and verification of reactive power compensator (RPC) for ITER pulsed power electric network (PPEN) are described in this paper. The RPC system is rated for a nominal power of 250 Mvar necessary to comply with the allowable reactive power limit value from the grid 200 Mvar. This system is currently under construction and is based on static var compensation technology with a thyristor-controlled reactor and a harmonic filter. The RPC minimizes reactive power from grid using prediction of reactive power consumption of AC-DC converters. The feasibility of the reactive power compensation was verified by assembling a real controller and implementing ITER PPEN in the real time digital simulator for the hardware-in-loop facility. When maximum reactive power is reached, grid voltage is stabilized and maximum reactive power decreased from 120 Mvar to 40 Mvar via the reactive power prediction method.

• 한국항해학회지
• /
• 제24권3호
• /
• pp.147-155
• /
• 2000

In this paper, we propose the Chaos Fuzzy controller to analyze the chaotic character of time series obtained from the specific plant and to predict the short-term for power consumption of the plant using the Fuzzy controller. We compared the predicted data with the active ones and checked the error generated by them after we time series of supplied power to the proposed controller. As a result of the simulation, we obtained a admirable consequence that the proposed controller can be advanced through various and accurate data acquisition, and continuous analysis of the resident and industrial environment.

• 한국빅데이터학회지
• /
• 제6권1호
• /
• pp.127-132
• /
• 2021

우리나라는 자원 빈국인 동시에 에너지 다소비 국가이다. 또한 전기 에너지에 대한 사용량 및 의존도가 매우 높고, 총 에너지 사용의 20% 이상은 건물에서 소비된다. 딥러닝과 머신러닝에 대한 연구가 활발해지면서 다양한 알고리즘을 에너지 효율 분야에 적용하려는 연구가 진행되고 있으며, 에너지의 효율적인 관리를 위한 건물에너지관리시스템(BEMS)의 도입이 늘어가는 추세이다. 본 논문에서는 스마트플러그를 이용하여 직접 수집한 가구당 기기별 에너지 사용량을 바탕으로 데이터베이스를 구축하였다. 또한 RNN과 LSTM 모델을 이용하여 수집한 데이터를 효과적으로 분석 및 예측하는 알고리즘을 구현하였다. 추후 이 데이터는 에너지 사용량 예측을 넘어 전력 소비 패턴 분석 등에 적용할 수 있다. 이는 에너지 효율 개선에 도움이 될 수 있으며, 미래 데이터의 예측을 통해 효과적인 전력 사용량 관리에 도움을 줄 것으로 기대된다.

• 오토저널
• /
• 제3권3호
• /
• pp.49-57
• /
• 1981

A cycle simulation of 4 cycle spark ignition engine using methanol-water blend as a fuel has been developed for study of prediction of power, specific fuel consumption, mean effective pressure and thermal efficiency. One-dimensional flow model for intake process and thermodynamic model for combustion process were selected. After, performance test was made with conventional engine which was modified in consideration of fuel properties. And computational results by simulation have been compared with experimental results. As the agreement between computational and experimental results was good, prediction of engine performance by was possible.

• 한국자동차공학회논문집
• /
• 제19권6호
• /
• pp.97-106
• /
• 2011

Both an optimal design of the engine operating strategy and fuel economy prediction technique for a HEV under the vehicle driving condition are very crucial for the development of vehicle fuel economy performance. Thus, in this study, engine operating characteristics of PRIUS III were analyzed with vehicle running conditions and the correlations between vehicle tractive power and fuel consumption were introduced. As a result, fuel economy performance of PRIUS III with various test modes were predicted and verified. Errors of predicted fuel economy were between -5% and -1%.

• 정보처리학회논문지D
• /
• 제16D권3호
• /
• pp.307-316
• /
• 2009

이 논문에서는 자동 원격 검침(AMR) 시스템에서 수집되는 전력 사용량 데이터의 분석 결과를 실세계에 적용하기 위하여 시간과 공간의 변화에 따른 전력 소비 패턴의 주기성 탐사를 위한 시공간 데이터마이닝 기법을 제안하였다. 첫째, 고객의 전력 사용 목적에 따른 군집 분석을 위하여 분할 군집화 기법을 적용하였다. 둘째, 3차원 큐브 마이닝 기법을 적용하여 고객의 전력 소비 데이터가 갖는 시간 속성과 공간 속성에 대한 패턴을 탐색하였다. 셋째, 다양한 시간 도메인에서의 주기 패턴 발견을 위한 캘린더 패턴 마이닝 기법을 이용하여 탐사된 패턴들이 갖고 있는 시간 속성의 의미와 관계를 분석 및 예측하였다. 제안된 시공간 데이터마이닝 기법을 평가하기 위해 한국 전력 연구원에서 구축된 GIS-AMR 시스템에 의해 제공되는 고압 전력 소비 고객 3,256명의 2007년 1월부터 4월까지 총 266,426건의 데이터로부터 시간의 주기성 및 공간적 특성을 포함한 전력 소비 패턴을 분석하였다. 제안한 분석 기법을 통하여 특정 그룹에 속한 각각의 대표 프로파일이 시간과 공간상에서 갖는 주기성을 발견하였다.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.134-142
• /
• 2019

에너지인터넷 기술의 발전과 다양한 전자기기의 보급으로 에너지소비량이 패턴이 다양해짐에 따라 수요예측에 대한 신뢰도가 감소하고 있어 발전량 최적화 및 전력공급 안정화에 문제를 야기하고 있다. 본 연구에서는 고신뢰성을 갖는 수요예측을 위해 딥러닝 기법인 Convolution neural network(CNN)과 Bidirectional Long Short-Term Memory(BLSTM)을 융합한 1Dimention-Convolution and Bidirectional LSTM(1D-ConvBLSTM)을 제안하고, 제안한 기법을 활용하여 시계열 에너지소비량대한 소비패턴을 효과적으로 추출한다. 실험 결과에서는 다양한 반복학습 횟수와 feature map에 대해서 수요를 예측하고 적은 반복학습 횟수로도 테스트 데이터의 그래프 개형을 예측하는 것을 검증한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2008년도 춘계학술발표대회
• /
• pp.231-234
• /
• 2008

Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in load demand data. The main aim of our work is to forecast customers' contract information from capacity of daily power consumption patterns. According to the result, we try to evaluate the contract information's suitability. The proposed our approach consists of three stages: (i) data preprocessing: noise or outlier is detected and removed (ii) cluster analysis: SOMs clustering is used to create load patterns and the representative load profiles and (iii) classification: we applied the K-NNs classifier in order to predict the customers' contract information base on power consumption patterns. According to the our proposed methodology, power load measured from AMR(automatic meter reading) system, as well as customer indexes, were used as inputs. The output was the classification of representative load profiles (or classes). Lastly, in order to evaluate KNN classification technique, the proposed methodology was applied on a set of high voltage customers of the Korea power system and the results of our experiments was presented.

• 한국해양공학회지
• /
• 제28권2호
• /
• pp.111-118
• /
• 2014

In drilling process of oil wells, the drilling fluid such as mud keeps the drill bit cool and clean during drilling, with suspending drill cuttings and lubricating a drill bit. In this paper, a commercial CFD package(ANSYS Fluent 15.0) was used to solve the hydrodynamic force and evaluate mud mixing time in the mud mixing tank on offshore drilling platforms. Prediction of power consumption in co-rotating and counter-rotating models has been compared with results of Nagata's correlation equation. This research shows the hydrodynamic effect inside the two phase mud mixing tank according to rotating directions(co-rotating and counter-rotating). These results, we can conclude that the co-rotating direction of the two shafts with mixing blade in the mud mixing tank can be a preferable in power consumption and mixing time reduction.

• 대한기계학회논문집B
• /
• 제25권12호
• /
• pp.1730-1738
• /
• 2001

This paper presents an overview of testing and analyzing field performance of a centrifugal chiller which has a rated capacity of 200 RT(703 kW). Field data of a chiller installed in the cleanroom research building of KIST has been collected far performance analysis. The operating data included start-up, shut-down, and quasi-static state where cooling capacity and compressor power consumption varied cyclically. It was found that the steady-state thermodynamic model could be applied to relate the cooling capacity and COP under quasi-static conditions. The results led to finding the required cooling load pattern and a possible energy saving method. This study provides a method of evaluating performance of a large capacity centrifugal chiller in which field test is necessary.