• 한국전자통신학회논문지
• /
• 제16권2호
• /
• pp.319-328
• /
• 2021

본 논문에서는 풍력 발전 수익 극대화 및 비용 최소화를 위해 설치하는 ESS에 대하여 정확한 용량 산정을 하기 위한 목적으로 풍력 단지용 전력량 예측을 다층 퍼셉트론을 이용하여 수행한다. 풍력 발전량을 예측하기 위해 풍속, 풍향, 공기밀도를 변수로 하고 그 변수를 병합하고 정규화한다. 모델을 훈련시키기 위해 병합된 변수를 70% 대 30% 비율로 훈련 및 테스트 데이터로 나눈다. 그런 다음 학습 데이터를 사용하여 모델을 학습시키고 테스트 데이터를 사용하여 모델의 예측 성능도 평가한다. 마지막으로 풍력량 예측 결과를 제시한다.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권1호
• /
• pp.171-177
• /
• 2021

In terms of distribution planning, accurate electric load prediction is one of the most important factors. The future load prediction has manually been performed by calculating the maximum electric load considering loads transfer/switching and multiplying it with the load increase rate. In here, the risk of human error is inherent and thus an automated maximum electric load forecasting system is required. Although there are many existing methods and techniques to predict future electric loads, such as regression analysis, many of them have limitations in reflecting the nonlinear characteristics of the electric load and the complexity due to Photovoltaics (PVs), Electric Vehicles (EVs), and etc. This study, therefore, proposes a method of predicting future electric loads on distribution lines by using Machine Learning (ML) method that can reflect the characteristics of these nonlinearities. In addition, predictive models were developed based on actual data collected at KEPCO's existing distribution lines and the adequacy of developed models was verified as well. Also, as the distribution planning has a direct bearing on the investment, and amount of investment has a direct bearing on the maximum electric load, various baseline such as maximum, lowest, median value that can assesses the adequacy and accuracy of proposed ML based electric load prediction methods were suggested.

• 조명전기설비학회논문지
• /
• 제29권1호
• /
• pp.86-93
• /
• 2015

Globally, wind power development is experiencing dramatic growth and wind power penetration levels are increasing. Wind generation is highly variable in time and space and it doesn't guarantee the system reliability and secure system operation. As wind power capacity becomes a significant portion of total generation capacity, the reliability assessment for wind power are therefore needed. At present, this operational reliability assessment is focusing on a generation adequacy perspective and does not consider transmission reliability issues. In this paper, we propose the critical transmission operating constraint prediction(CTOCP) system with high wind power penetration to enhance transmission reliability.

• 한국전자통신학회논문지
• /
• 제16권2호
• /
• pp.329-338
• /
• 2021

본 연구는 풍력발전의 합리적인 운영 계획과 에너지 저장창치의 용량산정을 위한 풍력 발전량을 예측한다. 예측을 위해 물리적 접근법과 통계적 접근법을 결합하여 풍력 발전량의 예측 방법을 제시하고 풍력 발전의 요인을 분석하여 변수를 선정한다. 선정된 변수들의 과거 데이터를 수집하여 딥러닝을 이용해 풍력 발전량을 예측한다. 사용된 모델은 Bidirectional LSTM(:Long short term memory)과 CNN(:Convolution neural network) 알고리즘을 결합한 하이브리드 모델을 구성하였으며, 예측 성능 비교를 위해 MLP 알고리즘으로 이루어진 모델과 오차를 비교하여, 예측 성능을 평가하고 그 결과를 제시한다.

• 산업공학
• /
• 제21권1호
• /
• pp.85-95
• /
• 2008

Reliability prediction serves many purposes during the life of a system, so several methods have been developed to predict the parts and systems reliability. MIL-HDBK-217F, among the those methods, has been widely used as a requisite tool for the reliability prediction which is applied to nuclear power plants and their safety regulations. This paper presents the reliability prediction for the DSP(Digital Signal Processor) module composed of three assemblies. One of the assemblies has a monitoring and self test function which is used to enhance the module reliability. The reliability of each assembly is predicted by MIL-HDBK-217F. Based on these predicted values, Markov modelling is finally used to predict the module reliability. Relax 7.7 software of Relax software corporation is used because it has many part libraries and easily handles Markov processes modelling.

• Journal of Electrical Engineering and Technology
• /
• 제8권5호
• /
• pp.1040-1048
• /
• 2013

In this paper, a sensorless pitch angle control method for a wind generation system is suggested. One-step-ahead prediction control law is adopted to control the pitch angle of a wind turbine in order for electric output power to track target values. And it is shown that this control scheme using the inverse dynamics of the controlled system enables us to predict current wind speed without an anemometer, to a considerable precision. The inverse input-output of the controlled system is realized by use of an artificial neural network. The proposed control and wind speed prediction method is applied to a Double-Feed Induction Generation system connected to a simple power system through computer simulation to show its effectiveness. The simulation results demonstrate that the suggested method shows better control performances with less control efforts than a conventional Proportional-Integral controller.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1997년도 춘계학술대회논문집; 경주코오롱호텔; 22-23 May 1997
• /
• pp.452-459
• /
• 1997

For computer aided design and construction of low noisy power plants, indoor and outdoor noise prediction program has been developed. The program utilizes the predefined data of noise sources and building materials and has the faculty to estimate the source level using the empirical formula in case of the measured data not being available. In the noise prediction, the mutual noise propagation between indoor and outdoor sites are considered. The outdoor noise source in the calculation of geometric divergence effects is modelled as the omni-directional finite line or planar source according to the source geometry and the receiving points. Outdoor noise prediction is carried out to consider the diffraction effect due to plant structures as well as the attenuation effect due to atmospheric absorption and soft ground. The results of indoor and outdoor noise prediction for a recently constructed diesel engine power plant show good agreement with the measured.

• 통합자연과학논문집
• /
• 제11권4호
• /
• pp.204-208
• /
• 2018

Comparison of different optimizer performance in photovoltaic power modeling using artificial neural deep learning techniques is described in this paper. Six different deep learning optimizers are tested for Long-Short-Term Memory networks in this study. The optimizers are namely Adam, Stochastic Gradient Descent, Root Mean Square Propagation, Adaptive Gradient, and some variants such as Adamax and Nadam. For comparing the optimization techniques, high and low fluctuated photovoltaic power output are examined and the power output is real data obtained from the site at Mokpo university. Using Python Keras version, we have developed the prediction program for the performance evaluation of the optimizations. The prediction error results of each optimizer in both high and low power cases shows that the Adam has better performance compared to the other optimizers.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권7호
• /
• pp.307-314
• /
• 2022

최근 전력수요를 예측하기 위해 통계기반 시계열 분석 기법을 대체하기 위해 딥러닝 기법을 활용한 연구가 활발히 진행되고 있다. 딥러닝 기반 전력수요 예측 연구 결과를 분석한 결과, LSTM 기반 예측 모델의 성능이 우수한 것으로 규명되었으나 장기간의 지역 범위 전력수요 예측에 대해 LSTM 기반 모델의 성능이 충분하지 않음을 확인할 수 있다. 본 연구에서는 기온 데이터를 반영하여 24시간 이전에 전력수요를 예측하는 WaveNet 기반 딥러닝 모델을 개발하여, 실제 사용하고 있는 통계적 시계열 예측 기법의 정확도(MAPE 값 2%)보다 우수한 예측 성능을 달성하는 모델을 개발하고자 한다. 먼저 WaveNet의 핵심 구조인 팽창인과 1차원 합성곱 신경망 구조를 소개하고, 전력수요와 기온 데이터를 입력값으로 모델에 주입하기 위한 데이터 전처리 과정을 제시한다. 다음으로, 개선된 WaveNet 모델을 학습하고 검증하는 방법을 제시한다. 성능 비교 결과, WaveNet 기반 모델에 기온 데이터를 반영한 방법은 전체 검증데이터에 대해 MAPE 값 1.33%를 달성하였고, 동일한 구조의 모델에서 기온 데이터를 반영하지 않는 것(MAPE 값 2.31%)보다 우수한 전력수요 예측 결과를 나타내고 있음을 확인할 수 있다.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제13권1호
• /
• pp.641-649
• /
• 2021

Fuel oil consumption (FOC) must be minimized to determine the economic route of a ship; hence, the ship power must be predicted prior to route planning. For this purpose, a numerical method using test results of a model has been widely used. However, predicting ship power using this method is challenging owing to the uncertainty of the model test. An onboard test should be conducted to solve this problem; however, it requires considerable resources and time. Therefore, in this study, a deep feed-forward neural network (DFN) is used to predict ship power using deep learning methods that involve data pattern recognition. To use data in the DFN, the input data and a label (output of prediction) should be configured. In this study, the input data are configured using ocean environmental data (wave height, wave period, wave direction, wind speed, wind direction, and sea surface temperature) and the ship's operational data (draft, speed, and heading). The ship power is selected as the label. In addition, various treatments have been used to improve the prediction accuracy. First, ocean environmental data related to wind and waves are preprocessed using values relative to the ship's velocity. Second, the structure of the DFN is changed based on the characteristics of the input data. Third, the prediction accuracy is analyzed using a combination comprising five hyperparameters (number of hidden layers, number of hidden nodes, learning rate, dropout, and gradient optimizer). Finally, k-means clustering is performed to analyze the effect of the sea state and ship operational status by categorizing it into several models. The performances of various prediction models are compared and analyzed using the DFN in this study.