Search

As the penetration of renewable energy sources into a power system increases, the significance of precise short-term forecasts for wind power generation becomes paramount. However, the erratic and non-periodic nature of wind poses challenges in accurately predicting the output. This paper presents a comprehensive investigation into forecasting wind power generation for the following day, using three machine learning models: long short-term memory (LSTM), convolutional neural network-bidirectional LSTM (CNN-biLSTM), and light gradient boosting machine (LGBM). In addition, this paper proposes a method to improve the prediction performance of LGBM by separating data according to the distribution of features, and training and testing each separated dataset with a distinct model. This study includes a comparative analysis of the performance of the proposed models in predicting wind turbine output, offering valuable insights into their respective efficiencies. The results of this investigation were analyzed for two geographically distinct wind farms (Korea and the UK). The findings of this study are expected to facilitate the selection of efficient prediction models within the forecast accuracy auxiliary service market and assist grid operators in ensuring reliable power supply for the grid. [ABSTRACT FROM AUTHOR]

Recently, the proportion of renewable energy (RE) sources in a power system has been increasing worldwide to reduce carbon emissions. To effectively accommodate renewable energy, there is a growing need to develop integrated planning strategies for both renewable energy sources and transmission lines in a power system, taking into account the location-specific characteristics of renewable energy. Economically viable and rapid system expansion plans are required to resolve the problem of delayed integration of renewable energy into existing power system, which arises due to inadequate transmission facilities. To address these problems, this paper presents an integrated economic evaluation method that considers the inherently uncertain output characteristics of renewable energy, contingent on location, the costs associated with installing transmission lines, and environmental benefits. The case study is conducted using a modified power system in Korea. In the case study, it is assumed that by integrating solar power generators in a low-demand area and wind power generators in a high-demand area, wind power plants have higher construction costs than solar power generators. However, the transmission costs for wind power plants are lower than those for solar power generators due to the regional characteristics of the power grid in the installation areas because renewable energy in high-demand areas typically requires less additional power infrastructure than in low-demand areas. The results of this study show that the net benefit for the wind power plant is estimated at USD 225.4 M, while the solar power plant yields a net benefit of USD 22.9 M in the example system. These results demonstrate the effectiveness of the proposed method, underscoring its potential to mitigate the challenges faced in the practical implementation of renewable energy projects. [ABSTRACT FROM AUTHOR]

This paper proposes a wind power probabilistic model (WPPM) using the reflection method and multi-kernel function kernel density estimation (KDE). With the increasing penetration of renewable energy sources (RESs) into power systems, several probabilistic approaches have been introduced to assess the impact of RESs on the power system. A probabilistic approach requires a wind power scenario (WPS), and the WPS is generated from the WPPM. Previously, WPPM was generated using a parametric density estimation, and it had limitations in reflecting the characteristics of wind power data (WPD) due to a boundary bias problem. The paper proposes a WPPM generated using the KDE, which is a non-parametric method. Additionally, the paper proposes a reflection method correcting for the boundary bias problem caused by the double-bounded characteristic of the WPD and the multi-kernel function KDE minimizing the effect of tied values. Six bandwidth selectors are used to calculate the bandwidth for the KDE, and one is selected by analyzing the correlation between the normalized WPD and the calculated bandwidth. The results were validated by generating WPPMs with WPDs in six regions of the Republic of Korea, and it was confirmed that the accuracy and goodness-of-fit are improved when the proposed method is used. [ABSTRACT FROM AUTHOR]

Not only the driving for offshore wind energy capacity of 12 GW by Korea's Renewable Energy 2030 plan but also the need for the rejuvenation of existing world-class shipbuilders' infrastructures is drawing much attention to offshore wind energy in Korea, especially to the diverse substructures. Considering the deep-sea environment in the East Sea, this paper presents detailed modeling and analysis of spar-type substructure for a 5 MW floating offshore wind turbine (FOWT). This process uses a fully coupled integrated load analysis, which was carried out using FAST, a widely used integrated load analysis software developed by NREL, coupled with an in-house hydrodynamic code (UOU code). The environmental design loads were calculated from data recorded over three years at the Ulsan Marine buoy point according to the ABS and DNVGL standards. The total 12 maximum cases from DLC 6.1 were selected to evaluate the structural integrity of the spar-type substructure under the three co-directional conditions (45°, 135°, and 315°) of wind and wave. A three-dimensional (3D) structural finite element (FE) model incorporating the wind turbine tower and floating structure bolted joint connection was constructed in FEGate (pre/post-structural analysis module based on MSC NASTRAN for ship and offshore structures). The FEM analysis applied the external loads such as the structural loads due to the inertial acceleration, buoyancy, and gravity, and the environmental loads due to the wind, wave, and current. The three-dimensional FE analysis results from the MSC Nastran software showed that the designed spar-type substructure had enough strength to endure the extreme limitation in the East Sea based on the von Mises criteria. The current process of this study would be applicable to the other substructures such as the submersible type. [ABSTRACT FROM AUTHOR]