• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.989-995
• /
• 2017

As is known to all that the output of wind power generation has a character of randomness and volatility because of the influence of natural environment conditions. At present, the research of wind power prediction mainly focuses on point forecasting, which can hardly describe its uncertainty, leading to the fact that its application in practice is low. In this paper, a wind power range prediction model based on the multiple output property of BP neural network is built, and the optimization criterion considering the information of predicted intervals is proposed. Then, improved Particle Swarm Optimization (PSO) algorithm is used to optimize the model. The simulation results of a practical example show that the proposed wind power range prediction model can effectively forecast the output power interval, and provide power grid dispatcher with decision.

• 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.

• 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.

• 전기학회논문지P
• /
• 제58권4호
• /
• pp.483-489
• /
• 2009

Electrolytic capacitors are used in variety of equipments as smoothening element of the power converters because it has high capacitance for its size and low price. Electrolytic capacitors, which is most of the time affected by aging effect, plays a very important role for the power electronics system quality and reliability. Therefore it is important to estimate the parameter of an electrolytic capacitor to predict the failure. This objective of this paper is to propose a new method to detect the rise of equivalent series resistor(ESR) in order to realize the online failure prediction of electrolytic capacitor for DC output filter of power converter. The ESR of electrolytic capacitor estimated from RMS result of filtered waveform(BPF) of the ripple capacitor voltage/current. Therefore, the preposed online failure prediction method has the merits of easy ESR computation and circuit simplicity. Simulation and experimental results are shown to verify the performance of the proposed on-line method.

• 풍력에너지저널
• /
• 제15권2호
• /
• pp.10-22
• /
• 2024

This research is a comprehensive analysis of wind power prediction sensitivity using a Long Short-Term Memory (LSTM) deep learning neural network model, accounting for the inherent uncertainties in wind speed estimation. Utilizing a year's worth of operational data from an operational wind farm, the study forecasts the power output of both individual wind turbines and the farm collectively. Predictions were made daily at intervals of 10 minutes and 1 hour over a span of three months. The model's forecast accuracy was evaluated by comparing the root mean square error (RMSE), normalized RMSE (NRMSE), and correlation coefficients with actual power output data. Moreover, the research investigated how inaccuracies in wind speed inputs affect the power prediction sensitivity of the model. By simulating wind speed errors within a normal distribution range of 1% to 15%, the study analyzed their influence on the accuracy of power predictions. This investigation provided insights into the required wind speed prediction error rate to achieve an 8% power prediction error threshold, meeting the incentive standards for forecasting systems in renewable energy generation.

• KEPCO Journal on Electric Power and Energy
• /
• 제5권3호
• /
• 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.

• 전기전자학회논문지
• /
• 제23권2호
• /
• pp.529-533
• /
• 2019

오늘날 복합 화력 발전소는 전력 생산을 위해 많이 사용되고 있고, 최근에는 운전 매개 변수를 기반으로 발전 출력을 예측하는 것이 주요 관심사이다. 본 논문에서는 복합 화력 발전소의 출력을 예측하기 위해 컴퓨터 지능 기법을 이용하는 방법을 제시한다. 컴퓨터 지능 기술은 지속적으로 발전되어 많은 실제 문제에 적용되어 왔다. 본 논문에서는 트리 구조의 퍼지 뉴럴 네트워크를 이용하여 발전 출력을 예측하고자 한다. 트리 구조의 퍼지 뉴럴 네트워크는 퍼지 뉴런을 노드로 선택하고 관련 입력을 최적으로 선택하여 규칙 수를 줄이는 장점이 있다. 네트워크의 최적화를 위해 2 단계 최적화 방법이 사용된다. 유전 알고리즘은 최적의 노드와 리프를 선택하여 네트워크의 이진 구조를 최적화 한 다음 랜덤 신호 기반 학습을 수행하여 최적화 된 이진 연결을 단위 구간에서 미세 학습한다. 제안 된 방법의 유용성을 검증하기 위해 UCI Machine Learning Repository Database에서 얻은 복합 화력 발전소 데이터를 사용한다.

• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.1874-1885
• /
• 2018

The customer side operation is getting more complex in a smart grid environment because of the adoption of renewable resources. In performing energy management planning or scheduling, it is essential to forecast non-controllable resources accurately and robustly. The PV system is one of the common renewable energy resources in customer side. Its output depends on weather and physical characteristics of the PV system. Thus, weather information is essential to predict the amount of PV system output. However, weather forecast usually does not include enough solar irradiation information. In this study, a PV system power output prediction model (PPM) under limited weather information is proposed. In the proposed model, meteorological radiation model (MRM) is used to improve cloud cover radiation model (CRM) to consider the seasonal effect of the target region. The results of the proposed model are compared to the result of the conventional CRM prediction method on the PV generation obtained from a field test site. With the PPM, root mean square error (RMSE), and mean absolute error (MAE) are improved by 23.43% and 33.76%, respectively, compared to CRM for all days; while in clear days, they are improved by 53.36% and 62.90%, respectively.

• 시스템엔지니어링학술지
• /
• 제16권1호
• /
• pp.58-67
• /
• 2020

A big data processing method to predict solar power generation using systems engineering approach is developed in this work. For developing analytical method, linear model (LM), support vector machine (SVN), and artificial neural network (ANN) technique are chosen. As evaluation indices, the cross-correlation and the mean square root of prediction error (RMSEP) are used. From multi-variable comparison test, it was found that ANN methodology provides the highest correlation and the lowest RMSEP.

• 한국정보통신학회논문지
• /
• 제18권10호
• /
• pp.2562-2570
• /
• 2014

단백질의 기능을 유추할 수 있는 중요한 정보중의 하나는 단백질이 존재하는 세포내 위치이다. 최근에는 하나의 단백질이 동시에 존재하는 여러 세포내 위치를 예측하는 연구가 활발하다. 본 논문에서는 단백질이 존재하는 세포내의 다중위치를 예측하기 위해서 레이블 멱집합 방법을 개선한다. 레이블 멱집합 방법으로 분류한 다중위치들을 예측 확률에 따라 결합하여 최종적인 다중레이블로 분류한다. 각 다중위치에 대한 정확한 확률적 기여를 구하기 위하여 쌍별 비교와 오류정정 출력코드를 사용한 다중클래스 확률추정 방법을 적용하였다. 단백질 세포내 위치 예측 실험에 제안한 방법을 적용하여 성능이 향상됨을 보였다.