• Journal of the Korean Data and Information Science Society
• /
• 제24권3호
• /
• pp.585-592
• /
• 2013

최근 신재생에너지와 대체에너지의 필요성이 증가함에 따라 환경오염과 온실효과를 초래하지 않는 풍력에너지 개발에 많은 연구와 투자가 이루어지고 있다. 풍력에너지는 무공해 에너지이며 자원양이 무한대이고 바람이 부는 곳이라면 어디에서든지 전력생산이 가능하다. 그러나 풍력에너지는 바람에 크게 의존하며 불규칙적인 특성이 있어 효율적인 풍력발전이 어렵다는 단점이 있다. 이러한 이유로 풍력발전에 있어서 정확한 풍력발전량 예측은 매우 중요한 요소이다. 본 연구에서는 이러한 풍력발전량의 효율적인 예측을 위해 군산 풍력단지의 자료를 이용해 시계열모형인 ARMA모형과 데이터 마이닝 기법 중 신경망모형을 사용하여 풍력발전량을 예측하고 비교분석 하였다. 그 결과 신경망모형 적합결과가 ARMA모형 적합결과 보다 더 좋은 예측력을 나타내었다.

• 조명전기설비학회논문지
• /
• 제29권7호
• /
• pp.80-86
• /
• 2015

As wind farm outputs depend on natural wind resources that vary over space and time, spatial correlation analysis is needed to estimate power outputs of wind generation resources. As a result, geographic information such as latitude and longitude plays a key role to estimate power outputs of spatially distributed wind farms. In this paper, we introduce spatial correlation analysis to estimate the power outputs produced by wind farms that are geographically distributed. We present spatial correlation analysis of empirical power output data for the JEJU Island and ERCOT ISO (Texas) wind farms and propose the Correlation Decay Distance (CoDecDist) model based on geographic correlation analysis to enhance the estimation of wind power outputs.

• 한국태양에너지학회 논문집
• /
• 제34권1호
• /
• pp.1-7
• /
• 2014

A study on the available power of a wind turbine to be used for wind farm control was performed in this study, To accurately estimate the available power it is important to obtain a suitable wind which represents the three dimensional wind that the wind turbine rotor faces and also used to calculate the power. For this, two different models, the equivalent wind and the wind speed estimator were constructed and used for dynamic simulation using matlab simulink. From the comparison of the simulation result with that from a commercial code based on multi-body dynamics, it was found that using the hub height wind to estimate available power from a turbine results in high frequency components in the power prediction which is, in reality, filtered out by the rotor inertia. It was also found that the wind speed estimator yielded less error than the equivalent wind when compared with the result from the commercial code.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.247-253
• /
• 2011

A sustainability of electricity supply has emerged as a critical issue for low carbon green growth in South Korea. Wind power is the fastest growing source of renewable energy. However, due to its own intermittency and volatility, the power supply generated from wind energy has variability in nature. Hence, accurate forecasting of wind speed and power plays a key role in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. This paper presents a short-term wind speed prediction method based on support vector regression. Moreover, particle swarm optimization is adopted to find an optimum setting of hyper-parameters in support vector regression. An illustration is given by real-world data and the effect of model regularization by particle swarm optimization is discussed as well.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2008년도 춘계학술대회논문집
• /
• pp.652-655
• /
• 2008

Despite of the laminar-turbulent transition region co-exist with fully turbulence region around the leading edge of an airfoil, still lots of researchers apply to fully turbulence models to predict aerodynamic characteristics. It is well known that fully turbulent model such as standard k-${\varepsilon}$ model couldn't predict the complex stall and the separation behavior on an airfoil accurately, it usually leads to over prediction of the aerodynamic characteristics such as lift and drag forces. So, we apply correlation based transition model to predict aerodynamic performance of the NREL (National Renewable Energy Laboratory) Phase IV wind turbine. And also, compare the computed results from transition model with experimental measurement and fully turbulence results. Results are presented for a range of wind speed, for a NREL Phase IV wind turbine rotor. Low speed shaft torque, power, root bending moment, aerodynamic coefficients of 2D airfoil and several flow field figures results included in this study. As a result, the low speed shaft torque predicted by transitional turbulence model is very good agree with the experimental measurement in whole operating conditions but fully turbulent model(k-${\varepsilon}$) over predict the shaft torque after 7m/s. Root bending moment is also good agreement between the prediction and experiments for most of the operating conditions, especially with the transition model.

• 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.

• 한국컴퓨터정보학회논문지
• /
• 제16권11호
• /
• pp.245-253
• /
• 2011

화석 연료의 무분별한 사용으로 환경이 심각하게 오염되고, 화석 연료의 고갈에 대한 문제가 대두됨에 따라서 화석 연료에 대한 문제를 해결 할 수 있는 대체 에너지원에 대해 관심이 집중되기 시작하였다. 현재 신재생 에너지 중에서 가장 각광을 받고 있는 에너지는 중에 하나가 풍력에너지이다. 풍력에너지 발전단지와 기존의 전력 발전소는 소비되는 전력에 대한 생산의 균형을 맞춰야하며, 풍력에너지단지에서 균형적인 생산을 하기 위해서는 풍력에너지에 대한 분석 및 예측이 필요하다. 이를 위해서 데이터마이닝 분야의 예측 기법이 활용 될 수 있다. 본 논문에서는 풍력 데이터를 이용하여 발전 패턴을 예측하기 위해 SOM(Self-Organizing Feature Map) Clustering 기법과 의사결정나무(decision tree)를 이용한 연구를 진행하였다. 즉, 1) 풍력 데이터의 누락된 데이터와 이상치 데이터를 처리하기 위하여, 전처리 과정을 수행하였고, 이 과정에서 특징 벡터를 추출하였다. 2) 전처리 단계를 거쳐 정제되고 정규화된 데이터 집합을 MIA(Mean Index Adequacy) 척도와 SOM Clustering 기법에 적용하여 대표 발전 패턴을 찾아내고 각각의 데이터에 해당하는 대표 패턴을 클래스 레이블로 할당하도록 하였다. 3) 의사결정나무 기반의 분류 기법에 데이터 집합을 적용시켜 새로운 풍력에너지에 대한 분석 및 예측 모델을 생성하였다. 실험 결과, 의사결정나무를 통한 풍력에너지 발전 패턴을 예측하기 위한 모델을 구축하였다.

• Journal of Power Electronics
• /
• 제9권1호
• /
• pp.85-92
• /
• 2009

This paper studies the method to predict voltage variation that can be presented in the case of operating a small-sized wind turbine in grid connection to the isolated small-sized power system. In order to do this, it makes up the simplified simulation model of the existing power plant connected to the isolated system, load, transformer, and wind turbine on the basis of PSCAD/EMTDC and compares them with the operating characteristics of the actual established wind turbine. In particular, it suggests a simplified model formed with equivalent impedance of the power system network including the load to analytically predict voltage variation at the connected point. It also confirms that the voltage variation amount calculated by the suggested method accords well with both simulation and actually measured data. The results can be utilized as a tool to ensure security and reliability in the stage of system design and preliminary investigation of a small-sized grid connected wind turbine.

• 조명전기설비학회논문지
• /
• 제28권5호
• /
• pp.60-67
• /
• 2014

Wind power is one of the fastest growing renewable energy sources. The blades length and tower height of wind turbine have been growing steadily in the last 10 years in order to increase the output amount of wind power energy. The amount of wind turbine energy is increased by increasing the capacity of wind turbine, but the costs of preventive, corrective and replacement maintenance are also increased accordingly. Recently, Condition Monitoring System that can repair the fault diagnose and repair of wind turbine in the real-time. However, these system have a problem that cannot predict and diagnose of the fault. In this paper, wind turbine predict methodology is proposed by using the SVM method. In the case study, correlation analysis between wind turbine fault and external environmental factors is performed by using the SVM method.

• 신재생에너지
• /
• 제5권4호
• /
• pp.11-18
• /
• 2009

Wind energy resources are recently considered as an important power generation alternative in the future. The fact that the investment of wind turbine installation continues to increase has motivated a need to develop more widely applicable methodologies for evaluating the actual benefits of adding wind turbines to conventional generating systems. This study is aiming to estimate the future wind resources with various estimation methods. The wind power is calculated at the hub height 75m of 800KW and 1,500KW wind turbines in Wolryong site, Jeju island, South Korea. Three equations - logarithmic, profile, and power law methods are applied for the accurate prediction of wind profile. In addition, yearly wind power can be calculated by using Weibull & Rayleigh distribution. It is found that predicted wind speed is highly affected by friction velocity, atmospheric stability, and averaged roughness length. It is concluded that Rayleigh distribution provides greater power generation than the Weibull distribution, especially for low wind-speed condition.