Prediction Of Wind Power Generation Research Articles

Research on short-term power prediction of wind power generation based on WT-CABC-KELM

Under the framework of the gradual scarcity of fossil energy, how to make better use of wind power to provide a safe and effective guarantee for the power grid has become a hot topic today. Aiming at the problems of existing short-term wind power prediction models that are easy to fall into local optimum, slow training speed, and poor accuracy, this paper proposes an improved artificial bee colony algorithm based on wavelet transform (WT) combined with a nuclear extreme learning machine. Power prediction method (WT-CABC-KELM). First, aiming at the volatility of historical wind power data, it is proposed to use wavelet transform to extract the hidden main features at each frequency to improve the prediction accuracy. Then, because the two parameters C and λ of the KELM model have a greater impact on the prediction accuracy, The improved artificial bee colony algorithm (CABC) is used to optimize the parameters of its model to achieve the purpose of improving the prediction accuracy, and the WT-CABC-KELM short-term wind power prediction model is established. In order to prove the effectiveness of the method proposed in this paper, 4 Each season is forecasted separately, and compared with traditional SVM and BP neural network. Finally, the results are compared and analyzed by 4 kinds of error indicators. The experimental results show that the short-term wind power prediction method (WT-CABC-KELM) mentioned in this article can effectively improve the short-term power prediction accuracy of wind power.

CNN-BiLSTM Short-Term Wind Power Forecasting Method Based on Feature Selection

Wind power has great uncertainty and short-term wind power forecasting technology can provide great help to power system scheduling after wind power integration. In this paper, a Convolutional neural network -bidirectional long and short-term memory network combination modeliCNN-BiLITMjbased on feature selection is proposed. Firstly, high correlation feature parameters were optimized based on effective feature screening of multidimensional feature datasets. Secondly, the input data are weighted according to the feature correlation to form a multi-dimensional feature data set. Finally, CNN-BiLSTM developed the wind energy forecast model. For verification, the KDD Cup 2022 wind power generation prediction data set was employed. The outcomes demonstrate that CNN-BiLSTM has a greater time series data utilization rate and prediction accuracy.

Predicting Wind Power Generation Using Hybrid Deep Learning With Optimization

Accurate prediction of wind power generation is complex due to stochastic component, but can play a significant role in minimizing operating costs, and improving reliability and security of a power system. This paper proposes a hybrid deep learning model to accurately forecast the very-short-term (5-min and 10-min) wind power generation of the Boco Rock Wind Farm in Australia. The model consists of a convolutional neural network, gated recurrent units (GRU) and a fully connected neural network. To improve performance, the hyper-parameters of the model are tuned using the Harris Hawks Optimization algorithm. The effectiveness of the proposed model is evaluated against other advanced models, including multilayer feedforward neural network (NN), recurrent neural network (RNN), long short-term memory (LSTM) and GRU. The forecasting model demonstrates around 38% and 24% higher accuracy as compared to the 5- and 10-min forecasting of the NN model, respectively.

Research on short-term wind power Prediction of GRU based on similar days

As the proportion of wind power generation continues to increase, accurate forecasting of wind power output is of great significance to the smooth operation of the entire power grid. However, due to the greater impact of environmental factors, wind power generation has strong randomness, and it becomes difficult to accurately predict the power generation. Thus, a new hybrid model for wind power generation prediction combining GRU neural networks and similar days’ characters analysis is proposed to address solve this problem. The prediction method employs grey relation analysis to screen similar days, which not only reduces the amount of data required to train the model, reduces the computational complexity, and improves the training speed, but also improves the prediction accuracy based on the selected datasets. In addition, this method also filters and processes the data through box-plot analysis and linear smoothing, which further improves the prediction accuracy of the model. The results show that compared with a single GRU network, the MAE of this method has dropped by 1.89, RMSE has dropped by 1.9, and MAPE has dropped by 11.07%. Obviously, the prediction model based on similar days extraction has obvious advantages.

Prediction of Wind Power Generation with Modern Artificial Intelli-gence Technology

<div><p class="4">In view of the continuous growth of energy demand and interest in environmental protection, the use of clean energy to replace fossil fuels is a global trend. Wind energy is the fastest growing renewable energy in the world in recent years. However, in the case of Mexico, there are still some difficulties in promoting its use in some areas of the national territory. One difficulty is knowing in advance how much energy can be injected into the grid. This paper introduces the development of artificial intelligence technology for wind power generation prediction based on multi-year meteorological information. In particular, the potential application of Bayesian network in these prediction applications is studied in detail. A weather forecasting method based on Dynamic Bayesian network (RBD) is proposed. The forecasting system was tested using meteorological data from the regional wind energy technology center (CERT) of the National Institute of Electricity and Clean Energy (INEEL) in Oaxaca, Mexico. The results are compared with the time series prediction results. The results show that dynamic Bayesian network is a promising wind power generation prediction tool.</p></div>

A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation

Predictions of renewable energy (RE) generation and electricity load are critical to smart grid operation. However, the prediction task remains challenging due to the intermittent and chaotic character of RE sources, and the diverse user behavior and power consumers. This article presents a novel method for the prediction of RE generation and electricity load using improved stacked gated recurrent unit-recurrent neural network (GRU-RNN) for both univariate and multivariate scenarios. First, multiple sensitive monitoring parameters or historical electricity consumption data are selected according to the correlation analysis to form the input data. Second, a stacked GRU-RNN using a simplified GRU is constructed with improved training algorithm based on AdaGrad and adjustable momentum. The modified GRU-RNN structure and improved training method enhance training efficiency and robustness. Third, the stacked GRU-RNN is used to establish an accurate mapping between the selected variables and RE generation or electricity load due to its self-feedback connections and improved training mechanism. The proposed method is verified by using two experiments: prediction of wind power generation using multiple weather parameters and prediction of electricity load with historical energy consumption data. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods of machine learning or deep learning in achieving an accurate energy prediction for effective smart grid operation.

Regional wind power probabilistic forecasting based on an improved kernel density estimation, regular vine copulas, and ensemble learning

Reliable wind energy forecasting is crucial for the stable operation of power grids. This paper proposes a regional wind power probabilistic forecasting model comprising an improved kernel density estimation (IKDE), regular vine copulas, and ensemble learning. The IKDE is firstly used to generate the margin probability density function (PDF) of each wind farm and the KDE bandwidth is optimized via the golden-section search algorithm to obtain the best possible prediction. Then, several dependence structures are formulated by building different regular vine copulas based on multiple criteria, and all the dependence structures work together with marginal PDF to generate respective joint distribution functions. Finally, ensemble learning is applied to combine all the joint distribution functions and establish an ultimate distribution function. Furthermore, a novel multi-distribution mega-trend-diffusion (MD-MTD) with parametric optimization is proposed to improve the prediction when the data are insufficient. The results of comparative evaluations conducted on datasets from eight wind farms indicate that the proposed model outperforms existing models in wind power generation prediction. Specifically, the proposed model can reliably forecast power generation for an entire region for the next 24 h with only three months of historical data. In contrast, most benchmark models require a year of data.

Forecasting the wind power generation in China by seasonal grey forecasting model based on collaborative optimization

Renewable energy represented by wind energy plays an increasingly important role in China’s national energy system. The accurate prediction of wind power generation is of great significance to China’s energy planning and power grid dispatch. However, due to the late development of the wind power industry in China and the lag of power enterprise information, there are little historical data available at present. Therefore, the traditional large sample prediction method is difficult to be applied to the forecasting of wind power generation in China. For this kind of small sample and poor information problem, the grey prediction method can give a good solution. Thus, given the seasonal and long memory characteristics of the seasonal wind power generation, this paper constructs a seasonal discrete grey prediction model based on collaborative optimization. On the one hand, the model is based on moving average filtering algorithm to realize the recognition of seasonal and trend features. On the other hand, based on the optimization of fractional order and initial value, the collaborative optimization of trend and season is realized. To verify the practicability and accuracy of the proposed model, this paper uses the model to predict the quarterly wind power generation of China from 2012Q1 to 2020Q1, and compares the prediction results with the prediction results of the traditional GM(1,1) model, SGM(1,1) model and Holt-Winters model. The results are shown that the proposed model has a strong ability to capture the trend and seasonal fluctuation characteristics of wind power generation. And the long-term forecasts are valid if the existing wind power expansion capacity policy is maintained in the next four years. Based on the forecast of China’s wind power generation from 2021Q2 to 2024Q2 in the future, it is predicted that China’s wind power generation will reach 239.09 TWh in the future, which will be beneficial to the realization of China’s energy-saving and emission reduction targets.

Wind power generation prediction in a complex site by comparing different numerical tools

This paper focuses on the estimation of annual energy production (AEP) by simulating the flowfield on a complex terrain located in the northeast region of Brazil using different numerical approaches: CFD RANS with k-ε and k-ω turbulence models (WindSim), simple mass-conserving (WindMap), and refined mesoscale (SiteWind). The last two are run through OpenWind software. Wind observations from five meteorological masts are used to adjust the models. Optimal layouts for a hypothetical wind farm with 50 wind turbines are obtained over each of the four wind fields to predict the power generation. As non-negligible differences are found on the spatial distribution of the winds simulated by the different models, the layouts are also substantially different. The AEP is calculated to compare scenarios varying the layouts over the wind fields. The distinct micrositing generate differences of up to 13 % on AEP prediction, which could mean the impact of an improper siting on the wind farm profitability. It is not plausible to categorically claim the superiority of accuracy of one model over the others. Nonetheless, the observed data provide an indicative that the refined mesoscale model was able to better capture the wind acceleration in the western region of the studied site.

기상 테이터를 이용한 딥러닝 기반 풍력 발전량 예측에 관한 연구

Although the proportion of wind energy sources in the system is increasing, the variability and stochastic characteristics of wind power have a negative effect on system stability and on the rescheduling of the system’s power generation. Therefore, an accurate prediction of wind power generation is necessary for stable power distribution in the power system. High-precision wind power forecasting provides a reliable basis for dispatching of power system. Since wind power data is time series data with uncertainty, a suitable model, the LSTM algorithm of Keras, was proposed to predict a short-term wind power generation. The LSTM has memory to store past states, so it is suitable for the problem of predicting time series data. This paper proposes a forecasting procedure using an LSTM neural network to forecast wind power. First, Pearson correlation coefficient method is utilized to determine the parameters of LSTM forecasting model. Then a case study was performed using real data collected from a wind farm in Yeongheung to confirm that the LSTM model was suitable for wind power prediction.

Selection of Input Variables and Comparison of Artificial Neural Networks and One-Dimensional Convolutional Neural Networks for Prediction of Wind Power Generation in Yeongheung Wind Power Plant

Objectives : In this study, deep learning models of artificial neural network (ANN) and one-dimension convolutional neural networks (1D-CNN) were compared to predict nonlinear wind power generation at Yeongheung wind power plant.Methods : The study site was Yeongheung-do, which has a 46 MW wind power plant. Hourly wind power and meteorological data from January to December 2018 were collected. After pre-processing with standardscaler, the training data were 64%, the validation data were 16%, and the test data were 20%. The optimum input variables of the model were selected using literature, and trial and error method. Rectified linear unit was used as the activation function. Hyperparameters were adjusted by trial and error method to optimized models. To compare the optimized models, the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) were used as the performance efficiency. Both ANN, and 1D-CNN were imported from the Keras library, and all of the performance efficiency was imported from the Scikit-learn library.Results and Discussion : The optimized input variables in this study were wind speed, wind direction, temperature, and humidity. The optimized ANN performance was R2=0.848, MAE=1.054, and RMSE=1.616, and the hyperparameters were 8 hidden layers with 100 nodes in each layer. The optimized 1D-CNN (R2=0.875, MAE=0.982, and RMSE=1.583) had 4 convolutional layers and the number of filters were 64, 128, 64, and 32 in order from the first layer, and one hidden fully connected layer had 100 nodes. The 1D-CNN had higher R2, and lower MAE and RMSE than the ANN. Therefore, the 1D-CNN was selected as the optimized model to predict wind generation of the Yeongheung wind power plant.Conclusions : The optimized 1D-CNN model in this study was more effective in predicting the Yeongheung wind power plant than the ANN. The optimal input variables were wind speed, wind direction, temperature, and humidity.

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Renewable energy becomes progressively popular in the world because renewable resources such as solar, geothermal, wind energy are clean, inexhaustible and come from natural sources. Wind energy is one of the most significant resources of renewable energy and it plays a key role in the generation of electricity. Thus, accurate wind power estimation is crucial to deal with the challenges to balance energy trading, planning, scheduling decisions and strategies of wind power generation. This study proposes a prediction model to solve a real-life problem in the renewable energy sector by accurately estimating the amount of wind energy production per hour in the next 24 hours by applying machine learning (ML) techniques using historical wind power generation data and weather forecasting reports. In the proposed approach, first, an unsupervised ML method (i.e., the K-Means clustering algorithm) is applied to group data into meaningful clusters; then, these clusters are accepted as new feature values and added to the dataset to enlarge it; finally, a supervised ML method (i.e., regression) is performed for prediction. This study compares nine supervised learning algorithms: K-Nearest Neighbors, Support Vector Regression, Random Forest, Extra Trees, Gradient Boosting, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Decision Tree, and Convolutional Neural Network. The aim of this study is to investigate the success of different ML algorithms on real-world data of wind turbines and propose a methodology to benchmark various machine learning algorithms to choose the most accurate final model for wind power generation prediction.

Regional Wind Power Probabilistic Forecasting Based on an Improved Kernel Density Estimation, Regular Vine Copulas, and Ensemble Learning

Reliable wind energy forecasting is crucial for the stable operation of power grids. This paper proposes a regional wind power probabilistic forecasting model comprising an improved kernel density estimation (IKDE), regular vine copulas, and ensemble learning. The IKDE is firstly used to generate the margin probability density function (PDF) of each wind farm and the KDE bandwidth is optimized via the golden-section search algorithm to obtain the best possible prediction. Then, several dependence structures are formulated by building different regular vine copulas based on multiple criteria, and all the dependence structures work together with marginal PDF to generate respective joint distribution functions. Finally, ensemble learning is applied to combine all the joint distribution functions and establish an ultimate distribution function. Furthermore, a novel multi-distribution mega-trend-diffusion (MD-MTD) with parametric optimization is proposed to improve the prediction when the data are insufficient. The results of comparative evaluations conducted on datasets from eight wind farms indicate that the proposed model outperforms existing models in wind power generation prediction. Specifically, the proposed model can reliably forecast power generation for an entire region for the next 24 h with only three months of historical data. In contrast, most benchmark models require a year of data.

A Novel Deep Learning Approach for Wind Power Forecasting Based on WD-LSTM Model

Wind power generation is one of the renewable energy generation methods which maintains good momentum of development at present. However, its extremely intense intermittences and uncertainties bring great challenges to wind power integration and the stable operation of wind power grids. To achieve accurate prediction of wind power generation in China, a hybrid prediction model based on the combination of Wavelet Decomposition (WD) and Long Short-Term Memory neural network (LSTM) is constructed. Firstly, the nonstationary time series is decomposed into multidimensional components by WD, which can effectively reduce the volatility of the original time series and make them more stable and predictable. Then, the components of the original time series after WD are used as input variables of LSTM to predict the national wind power generation. Forty points were used, 80% as training samples and 20% as testing samples. The experimental results show that the MAPE of WD-LSTM is 5.831, performing better than other models in predicting wind power generation in China. In addition, the WD-LSTM model was used to predict the wind power generation in China under different development trends in the next two years.

Enhanced Wind Generation Forecast Using Robust Ensemble Learning

This letter proposes a robust ensemble learning scheme to enhance short-term prediction of wind power generation. The ensemble problem associated with pruning and combination is formulated as a worst-case robust approximation problem, taking forecast uncertainty in individual predictors into consideration. This problem is then transformed into the scaled form of the augmented Lagrangian and is solved via the alternating direction method of multipliers (ADMM). The proposed scheme can be applied to both deterministic and probabilistic forecasting. A comprehensive study is carried out to illustrate the advantage of the proposed scheme in both point and interval forecasting.

An improved seasonal GM(1,1) model based on the HP filter for forecasting wind power generation in China

With rapid development of wind power in China, it has become an integral part of the energy structure, so it is of practical significance to forecast wind power generation accurately. As wind power generation in China experiences both an exponential increase trend and a seasonal fluctuation pattern, it cannot be accurately forecasted by traditional models. As the grey model GM(1,1) can capture an exponential growth trend and the Hodrick-Prescott filter is known for its capability of characterizing seasonality factors, this paper proposes a novel seasonal forecasting method that integrates the HP filter into the grey model GM(1,1). The proposed model is then applied to carry out an empirical analysis based on the seasonal wind power generation data between 2013 and 2019 in China. The forecasting results from the new model are then compared with three existing approaches. The comparison results indicate that the proposed model generally outperforms existing methods as it can well capture seasonal fluctuations in the data series. A further prediction of wind power generation in China is conducted into a future horizon of 2020 and 2021 by using our model, followed by a set of policy recommendations for further development of the wind power industry in China.

A novel method based on lower–upper bound approximation to predict the wind energy

Recently, the prediction of wind power generation has served as a prerequisite problem for determining the objective of the reliability and low–cost power system performance. The difference between conventional deterministic prediction and probabilistic prediction is that the first types ignore the uncertainty of the wind speeds. In this paper, a novel probabilistic prediction method as improved lower–upper bound approximation is applied for building the reliable prediction intervals, which is based on the system that uses the mathematical models of the environment to prognosticate the weather based on existing meteorology (Numeral Weather Prediction System). To verify the worth of the proposed method, forecasting modes in this study are divided as hourly and daily predictions, which are applied to seven wind farms of Taiwan. In addition, adapting parameters in improved lower–upper bound approximation method is performed by resorting to the charged search system algorithm. Also, to increase the prediction speed, the probability density function of wind speed is used, and to decrease the estimation model volume, the kernel density estimation model is applied into the proposed method. The simulation results in comparison with other methods indicate that the prediction intervals produced by the proposed method outperformed and its indices are better. The average error between prediction and real data in the proposed method obtained as about 11%, while other methods error is more than 15%. In addition, three prediction interval indices are used in order to evaluate the different studied manners as: prediction interval overlay probability, normalized average of prediction interval length, and overlay width scale. As the results shown, the best performance is related to the proposed method.

Robust short-term prediction of wind power generation under uncertainty via statistical interpretation of multiple forecasting models

The predictions of the autoregressive moving average model, the artificial neural network model, and the grey prediction model are comparatively studied for the wind power generation. Each predictive model is the most suitable for a certain variance of wind at a given period. In this study, the weighting method is proposed to systematically combine the predicted values of those three predictive models over time, based on their forecasting performance by the root mean square errors (RMSEs) between the actual values and the predicted values. The multiple forecasting models are applied to predict the wind power generation of a wind farm with 1 h, 3 h and 6 h ahead. The RMSEs of the multiple forecasting models are significantly the lowest values among those three predictive models and the benchmark of the persistence model. Also, the prediction interval around the predicted value is statistically determined to indicate the feasible range of the wind power generation with a prescribed percentage of confidence under uncertainty causing the historic prediction errors.

Forecasting of Wind Power Generation with the Use of Artificial Neural Networks and Support Vector Regression Models

The stochastic character of wind power generation suggests limitations on the increased shares of wind energy in electricity systems and challenges market integration of wind power, mainly due to the fact that nowadays, new wind parks are set to cope with more dynamic pricing mechanisms. In this new environment, where advanced bidding strategies need to be adopted from wind power actors, the introduction of novel elements to support wind power generation and address the inherent impact of variability is thought to be a prerequisite. To this end, the current study expands the work of previous studies by examining different methods of prediction with regards to wind power forecasting. More specifically, both Artificial Neural Networks (ANNs) and Support Vector Regression (SVR) models are trained and tested on the basis of different prediction horizons, using as case study real wind speed and wind power generation measurements from a wind park operating in the Greek territory. Models are trained using an in-house forecasting tool, with results obtained reflecting the better fit of the SVR method overall, especially for time horizons longer than 6 hours ahead. At the same time, an effort is made in order to optimize prediction of wind power generation through the combination of both prediction approaches via clustering of prediction areas. This novel approach results in an improvement of the predictions obtained, despite the fact that the SVR method already performs sufficiently even for 24 hours ahead.

A novel clustering algorithm based on mathematical morphology for wind power generation prediction

Wind power has the characteristic of daily similarity. Furthermore, days with wind power variation trends reflect similar meteorological phenomena. Therefore, wind power prediction accuracy can be improved and computational complexity during model simulation reduced by choosing the historical days whose numerical weather prediction information is similar to that of the predicted day as training samples. This paper proposes a new prediction model based on a novel dilation and erosion (DE) clustering algorithm for wind power generation. In the proposed model, the days with similar numerical weather prediction (NWP) information to the predicted day are selected via the proposed DE clustering algorithm, which is based on the basic operations in mathematical morphology. And the proposed DE clustering algorithm can cluster automatically without supervision. Case study conducted using data from Yilan wind farm in northeast China indicate that the performance of the new generalized regression neural network (GRNN) prediction model based on the proposed DE clustering algorithm (DE clustering-GRNN) is better than that of the DPK-medoids clustering-GRNN, the K-means clustering-GRNN, and the AM-GRNN in terms of day-ahead wind power prediction. Further, the proposed DE clustering-GRNN model is adaptive.