• Journal of Wind Energy
• /
• v.15 no.2
• /
• 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.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.189.1-189.1
• /
• 2010

The wind farm where the wind velocity condition is excellent and economical can be established to produce power with the multiple wind power turbine. The wind velocity which is suitable to Wind Power Development must be evaluated for searching the economical wind farm on planning the wind farm. In this paper, based on wind speed data at 24 locations in Korea from 1971 through 2009, the basic wind velocity which can be applied to designing wind power development is estimated using the statiscal process. The wind velocity which is measured from observation stations is revised according to wind gauge's height and Circumferential environment. The wind speeds for 200 year's return period in 24 locations are determined using the Gumbel's distribution.

• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.249-250
• /
• 2011

국제 전기 위원회(IEC)의 기술 위원회(TC-88)에서는 풍력 시스템과 계통 안정성 분석 그리고 단락회로(LVRT), 발전기와 부하의 손실 해석, 시스템 분리와 같은 전력 시스템의 동적 시뮬레이션에 활용하기 위한 풍력 발전기와 발전 단지의 동적 시뮬레이션 모델 표준화 작업을 수행하고 있다. 본 논문의 목적은 특정한 풍력 터빈 제조사를 알 수 없는 상태에서 계통 연구가 적용될 수 있는 일반적인 모델을 소개하는 것이다. 그와 함께 제조사의 모델이 표준화 된 모델로의 쉬운 교환을 가능하게 하는 블록도가 적용되어야 한다. 본 작업의 1단계 작업은 2011년 마무리 될 계획이다.

• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.240-241
• /
• 2011

국제 전기 위원회(IEC)의 기술 위원회(TC-88)에서는 풍력시스템과 계통 안정성 분석 그리고 단락회로(LVRT), 발전기와 부하의 손실 해석, 시스템 분리와 같은 전력 시스템의 동적 시뮬레이션에 활용하기 위한 풍력 발전기와 발전 단지의 동적 시뮬레이션 모델 표준화 작업을 수행하고 있다. 본 논문의 목적은 특정한 풍력 터빈 제조사를 알 수 없는 상태에서 계통 연구가 적용될 수 있는 일반적인 모델을 소개하는 것이다. 그와 함께 제조사의 모델이 표준화 된 모델로의 쉬운 교환을 가능하게 하는 블록도가 적용되어야 한다. 본 작업의 1단계 작업은 2011년 마무리 될 계획이다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.1
• /
• pp.81-89
• /
• 2012

Commonly used horizontal-axis wind turbines (HAWT) have the following structure: two or three blades, a nacelle which contains power converting equipments, generators, and a tower which supports the nacelle. The generated power is transmitted from the nacelle to the ground. Due to this structure, the power transmission lines are twisted when the nacelle is yawing. Thus, slip ring or additional yaw control mechanism is required. We propose a new structure of HAWT which is free of this transmission line problem. Moreover, the size of inverter can be reduced since two generators are connected in parallel in our mechanism so that power is distributed. A controller for yawing is developed so that it works in harmony with the controller for power generation. A MPPT (Maximum Power Point tracking) algorithm is implemented for the proposed system and efficiency of the system is validated by simulation.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.27 no.4
• /
• pp.266-273
• /
• 2015

In this paper, annual wind data in 2014 at six locations(Seosudo, Gadaeam, Sibidongpa, Galmaeyeo, Haesuseo, Jigwido) are collected and analyzed in order to review optimal candidate site for offshore wind farm in the Western Seas of Korea. Observed wind data is fitted to Rayleigh and Weibull distribution and annual energy production is estimated according to wind frequency. GWE-3kH(3 kW-class) and GWE-10KU (10 kW-class) turbine are selected as wind turbine. Also, power curve are used to calculate wind energy potential. As a result, annual mean wind speed at six locations(Seosudo, Gadaeam, Sibidongpa, Galmaeyeo, Haesuseo, Jigwido) were calculated about 4.60, 4.5, 5.00, 5.13, 5.51, 5.90 m/s, respectively. In addition, annual energy production were estimated at 10,622.752, 11,313.05, 13,509.41, 14,899.55, 17,106.13, 19,660.85 kWh. Generally, annual mean energy density were between poor and marginal class and capacity factor at Jigwido was calculated at 22.44%. Its value is higher than the others.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.143-144
• /
• 2015

최근 대체에너지에 대한 관심이 많아진 가운데 풍력발전에 대한 관심이 증대하고 있다. 풍력발전기는 사람의 접근이 용이하지 않은 산간벽지에 주로 설치됨에 따라 상시 운전상태를 모니터링하기 위한 원격 모니터링 장치가 필요하다. 본 논문에서는 풍력발전기의 원격 모니터링 시스템을 개발에서 필요한 요소기술 분야의 설계 방법을 제시한다. 다수의 풍력발전기가 설치되는 풍력단지에서 효과적으로 모니터링을 위해 Zigbee 무선통신을 사용하여 모니터링하고, 모니터링 시스템 구현이 용이한 LabVIEW를 활용하여 실시간 상태 모니터링의 설계 요소를 제안한다.

• Journal of Digital Convergence
• /
• v.12 no.3
• /
• pp.211-218
• /
• 2014

Recently, wind energy is expanding to combination of computing to forecast of wind power generation as well as intelligent of wind powerturbine. Wind power is rise and fall depending on weather conditions and difficult to predict the output for efficient power production. Wind power is need to reliably linked technology in order to efficient power generation. In this paper, distributed power generation forecasts to enhance the predicted and actual power generation in order to minimize the difference between the power of distributed power short-term prediction model is designed. The proposed model for prediction of short-term combining the physical models and statistical models were produced in a physical model of the predicted value predicted by the lattice points within the branch prediction to extract the value of a physical model by applying the estimated value of a statistical model for estimating power generation final gas phase produces a predicted value. Also, the proposed model in real-time National Weather Service forecast for medium-term and real-time observations used as input data to perform the short-term prediction models.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.05a
• /
• pp.165.1-165.1
• /
• 2011

In the present study, two numerical methods were developed and compared for the performance prediction of the horizontal axis energy conversion turbine. The Blade Element Momentum Theory was adopted, and the rotating reference frame method for Computational Fluid Dynamics solver was also used. Hybrid meshing was used for the complex geometry of turbines. The analysis results using each method were compared to figure out a better method for the performance prediction.

• Proceedings of the KIPE Conference
• /
• 2013.11a
• /
• pp.65-66
• /
• 2013

본 논문에서는 계통 전압 사고 상황에서 계통 연계형 풍력 발전 시스템이 만족시켜야 할 LVRT(Low Voltage Ride Through) 동작 모의 및 동특성을 분석하였다. 제작한 시뮬레이터는 유도전동기를 이용한 풍력터빈 모델과 영구자석 동기 발전기 그리고 컨버터와 인버터로 구성된 Back to Back Converter를 통해 계통과 연계되는 구조를 가지고 있다. 계통과 연계되는 부분에 슬라이닥스와 변압기 그리고 IGBT를 이용해 계통의 사고를 모의할 수 있는 계통 전압사고 모의 장치를 제작하여 연결하였으며, 이 계통 전압사고 모의 장치는 A, B, C 각 상을 독립적으로 제작해 다양한 계통사고를 모의할 수 있도록 구성하였다. 하드웨어 시뮬레이터와 제안된 계통 전압 사고 모의 장치 분석을 위해 PSCAD/EMTDC 소프트웨어를 이용한 시뮬레이션을 실시하였고 하드웨어 실험을 통해 그 타당성을 검증하였다.