Numerical Weather Prediction Wind Research Articles

Two-stage correction prediction of wind power based on numerical weather prediction wind speed superposition correction and improved clustering

The unavoidable wind power prediction error poses a challenge for wind power to participate in day-ahead scheduling plan. This paper proposes a two-stage correction method considering NWP wind speed and power correction. Firstly, this paper fully considers the historical similarity of NWP wind speed, and adopts the improved clustering distance for segment matching and wind speed correction based on the extracted most relevant trend component, which enhances the utilization of NWP information and avoids the randomness and uncertainty of the intelligent correction method, and gram angular field (GAF) and stacked autoencoder (SAE) are used for feature extraction and conditional variational autoencoder (CVA) is used to generate specific samples to ensure the adequacy of the clustering process. Secondly, considering the historical similarity of error of predicted power, the power is further corrected based on the proposed weighted double-constraint to realize the secondary calibration. The Proposed method is applied to several wind farms in China to verify its effectiveness. The results show that the proposed method reduces the NRMSE by 3.82 % and NMAE by 3.40 % compared with direct prediction in the wind farms in western Inner Mongolia, which is important for promoting wind power consumption and maintaining the safe and stable operation of the power system.

Dual NWP wind speed correction based on trend fusion and fluctuation clustering and its application in short-term wind power prediction

With the continuous growth of grid-connected installed capacity of wind power, the inevitable gap, volatility and randomness of wind power pose challenges to the stability of real-time operation of power system. Accurate wind power prediction (WPP) can effectively ensure the safe and stable operation of power system. At present, the main input of short-term power prediction based on data-driven model is numerical weather prediction (NWP), and its prediction accuracy leads to the failure to effectively improve the accuracy of short-term power prediction. To solve this problem, this paper proposes a dual NWP wind speed (WS) correction method based on trend fusion and fluctuation clustering. First, the WS trend is used to construct a new input feature, and the NWP WS error distribution is determined to establish a more correct and stable mapping relationship with the NWP WS error. Secondly, the error is decomposed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and the trend and fluctuation components are defined by Pearson coefficient. The trend curve features in the short 24h period were extracted from the two dimensions of time and value, and the trend and fluctuation curve databases under different scenarios were formed by K-Medoids clustering. Finally, the trend component is modified by the Attention-GRU model, and the corresponding trend component is searched and matched from the database to correct the fluctuation component. The NWP WS is modified by the superposition of the two components and the short-term WPP is made. Two wind farms in Mengxi, China were used for example analysis, and the prediction accuracy was improved by 10 % and 13.1 % respectively, which demonstrated the effectiveness of the proposed method.

Short-Term Forecasting of Wind Power Based on Error Traceability and Numerical Weather Prediction Wind Speed Correction

Short-Term Forecasting of Wind Power Based on Error Traceability and Numerical Weather Prediction Wind Speed Correction

A Hybrid Model for Long-Term Wind Power Forecasting Utilizing NWP Subsequence Correction and Multi-Scale Deep Learning Regression Methods

The accuracy of long-term wind power forecasting (WPF) is crucial for the efficient operation of grid systems. However, wind power generation is highly stochastic and intermittent due to the influence of weather, which makes long-term WPF less effective. Numerical weather prediction (NWP) data contains valuable weather forecast information, which can mitigate the negative effects of stochastic weather fluctuations on WPF. However, the accuracy of NWP data decreases over time, and multiple NWP data can have redundancy and errors that make it challenging to extract valid information. Reducing the variety and errors in NWP data and using more effective information extraction methods are essential for improving long-term WPF performance. In this article, we propose a novel long-term WPF hybrid model that corrects NWP wind speed and uses multi-scale deep learning regression prediction to exclude excessive NWP data. We use only the corrected NWP wind speed data to establish a nonlinear mapping relationship with actual power data. The validation case study shows that our proposed model reduces the mean squared error (MSE) and mean absolute error (MAE) by 65.0% and 43.8%, respectively, compared to the current state-of-the-art time series forecasting model in a seven-day forecasting scenario.

Research on Numerical Weather Prediction Wind Speed Correction Based on Stacking Ensemble Learning Algorithm

The transportation of wind fields plays a crucial role in the dispersion and distribution of air pollutants, and accurate wind speed prediction is essential for assessing pollutant concentrations. In this study, we constructed a Stacking ensemble learning model using three models, namely Random Forest, LightGBM, and XGBoost, as base learners, and the LASSO regression model as the meta-learner to optimize wind speed data forecasting for Zhengzhou City’s urban area using WRF. Firstly, based on Pearson correlation coefficients, we selected meteorological variables that have a significant impact on near-surface wind speed and derived historical lagged features. Bayesian TPE was utilized for hyperparameter tuning and model building. Finally, the performance of the trained model was evaluated by comparing it with ground observation data. The results showed that compared to the WRF model, Random Forest, LightGBM, and XGBoost effectively reduced forecast errors and significantly improved wind speed predictions. Both LightGBM and XGBoost demonstrated similar performance in the correction models across the 11 stations and outperformed Random Forest. The Stacking method integrated the advantages of the base learners and exhibited improvement capabilities over individual models, highlighting the potential of machine learning in enhancing localized and accurate weather forecasting.

Considering dynamic perception of fluctuation trend for long-foresight-term wind power prediction

With the increasing proportion of renewable energy being integrated into the power system, the stable operation of the power system is facing great challenges. Breaking through the limitation and prolonging the time period of power prediction will help to improve the consumption ability of wind power (WP), adjust the power generation plan, and ensure the safe operation of the power system. Based on the availability of long-foresight-term numerical weather prediction (NWP) and fluctuation trend mining, a wind farm cluster power forecasting method based on dynamic perception of fluctuation trend is proposed for the long-foresight-term wind power prediction (WPP). The method first matches historical power based on the fluctuation trend of NWP wind speed (WS), and then obtains statistical characteristics of similar processes in order to construct new input features. Secondly, after the prediction results are obtained, the predicted power is corrected according to the fluctuation trend to improve the prediction reliability. This method is applied to a wind farm cluster in Gansu Province, China, and the overall prediction accuracy is 2.23 % higher than that of the direct prediction method. It is verified that this method can achieve long-foresight-term prediction and increase the reliability of prediction.

A robust error correction method for numerical weather prediction wind speed based on Bayesian optimization, variational mode decomposition, principal component analysis, and random forest: VMD-PCA-RF (version 1.0.0)

Abstract. Accurate wind speed prediction is crucial for the safe and efficient utilization of wind resources. However, current single-value deterministic numerical weather prediction methods employed by wind farms do not adequately meet the actual needs of power grid dispatching. In this study, we propose a new hybrid forecasting method for correcting 10 m wind speed predictions made by the Weather Research and Forecasting (WRF) model. Our approach incorporates variational mode decomposition (VMD), principal component analysis (PCA), and five artificial intelligence algorithms: deep belief network (DBN), multilayer perceptron (MLP), random forest (RF), eXtreme gradient boosting (XGBoost), light gradient boosting machine (lightGBM), and the Bayesian optimization algorithm (BOA). We first predict wind speeds using the WRF model, with initial and lateral boundary conditions from the Global Forecast System (GFS). We then perform two sets of experiments with different input factors and apply BOA optimization to tune the four artificial intelligence models, ultimately building the final models. Furthermore, we compare the aforementioned five optimal artificial intelligence models suitable for five provinces in southern China in the wintertime: VMD-PCA-RF in December 2021 and VMD-PCA-lightGBM in January 2022. We find that the VMD-PCA-RF evaluation indices exhibit relative stability over nearly a year: the correlation coefficient (R) is above 0.6, forecasting accuracy (FA) is above 85 %, mean absolute error (MAE) is below 0.6 m s−1, root mean square error (RMSE) is below 0.8 m s−1, relative mean absolute error (rMAE) is below 60 %, and relative root mean square error (rRMSE) is below 75 %. Thus, for its promising performance and excellent year-round robustness, we recommend adopting the proposed VMD-PCA-RF method for improved wind speed prediction in models.

Wind power ultra-short-term prediction method based on NWP wind speed correction and double clustering division of transitional weather process

Wind power prediction technology is important for building novel power systems with a high proportion of renewable energy. The quality of Numerical weather prediction (NWP) has a significant impact on the accuracy of ultra-short-term wind power prediction (USTWPP). However, existing NWP do not reflect the adaptability of different weather processes, because of it’ s forecasting errors. In view of this, this paper proposes an USTWPP method based on NWP wind speed correction and division of transitional weather process. The combined prediction method was first used to correct the NWP wind speed, and then we use the double clustering method to divide the transitional weather processes to establish a model for USTWPP based on different scenarios, the overall method was finally applied to a wind farm in west inner Mongolia, China. Compared to the pre-correction, the wind speed forecasted RMSE was reduced by 1.702 and the MAE by 1.366. Based on the wind power ultra-short-term prediction method proposed in this paper, the average reduction in RMSE is 5.93% and in MAE is 4.82% compared to the various comparison methods in the four seasons. The USTWPP method combining wind speed correction and double clustering division of transitional weather scenarios can significantly improve accuracy of USTWPP.

A hybrid method for numerical weather prediction wind speed based on Bayesian optimization (version 1.2.0) and error correction: First release of my code

A hybrid method for numerical weather prediction wind speed based on Bayesian optimization (version 1.2.0) and error correction: First release of my code

Deterministic and Probabilistic Wind Power Forecasts by Considering Various Atmospheric Models and Feature Engineering Approaches

This study proposed a model for deterministic and probabilistic wind power generation forecasting and its corresponding procedures. The main contents include numerical weather prediction (NWP) systems, data preprocessing techniques, and forecasting models that use artificial intelligence methods. NWP wind speeds generated by the Central Weather Bureau (CWB) of Taiwan based on three atmospheric models, namely deterministic weather research and forecasting (WRFD), radar weather research and forecasting (RWRF), and WRF-based ensemble prediction system (WEPS), were used as model inputs. In terms of data preprocessing, the NWP wind speeds were corrected based on the height of the wind turbines, and principal components analysis (PCA) and empirical mode decomposition (EMD) were also evaluated for their feature extraction performance. Artificial neural network (ANN), long short-term memory (LSTM), gated recurrent unit (GRU), and eXtreme gradient boosting (XGBoost) were the forecast models used to predict wind power generation. The forecast results demonstrated that the use of the XGBoost model in conjunction with both PCA and EMD data preprocessing achieved the most accurate forecasting. The average forecasting errors (i.e., normalized root mean square error (NRMSE) and mean absolute percentage error (MAPE)) were 5.43% and 3.30% for one-hour-ahead and 9.78% and 6.83% for one-day-ahead, respectively. The empirical data collected at a wind farm in Taiwan verified the accuracy of the proposed method. Thus, the importance of model selection, NWP, and data preprocessing is ultimately self-evident.

Emulating the Adaptation of Wind Fields to Complex Terrain with Deep Learning

Abstract Estimating the impact of wind-driven snow transport requires modeling wind fields with a lower grid spacing than the spacing on the order of 1 or a few kilometers used in the current numerical weather prediction (NWP) systems. In this context, we introduce a new strategy to downscale wind fields from NWP systems to decametric scales, using high-resolution (30 m) topographic information. Our method (named “DEVINE”) is leveraged on a convolutional neural network (CNN), trained to replicate the behavior of the complex atmospheric model ARPS, and was previously run on a large number (7279) of synthetic Gaussian topographies under controlled weather conditions. A 10-fold cross validation reveals that our CNN is able to accurately emulate the behavior of ARPS (mean absolute error for wind speed = 0.16 m s−1). We then apply DEVINE to real cases in the Alps, that is, downscaling wind fields forecast by the AROME NWP system using information from real alpine topographies. DEVINE proved able to reproduce main features of wind fields in complex terrain (acceleration on ridges, leeward deceleration, and deviations around obstacles). Furthermore, an evaluation on quality-checked observations acquired at 61 sites in the French Alps reveals improved behavior of the downscaled winds (AROME wind speed mean bias is reduced by 27% with DEVINE), especially at the most elevated and exposed stations. Wind direction is, however, only slightly modified. Hence, despite some current limitations inherited from the ARPS simulations setup, DEVINE appears to be an efficient downscaling tool whose minimalist architecture, low input data requirements (NWP wind fields and high-resolution topography), and competitive computing times may be attractive for operational applications. Significance Statement Wind largely influences the spatial distribution of snow in mountains, with direct consequences on hydrology and avalanche hazard. Most operational models predicting wind in complex terrain use a grid spacing on the order of several kilometers, too coarse to represent the real patterns of mountain winds. We introduce a novel method based on deep learning to increase this spatial resolution while maintaining acceptable computational costs. Our method mimics the behavior of a complex model that is able to represent part of the complexity of mountain winds by using topographic information only. We compared our results with observations collected in complex terrain and showed that our model improves the representation of winds, notably at the most elevated and exposed observation stations.

Improving the Accuracy of the Cross-Calibrated Multi-Platform (CCMP) Ocean Vector Winds

The Cross-Calibrated Multi-Platform (CCMP) Ocean vector wind analysis is a level-4 product that uses a variational method to combine satellite retrievals of ocean winds with a background wind field from a numerical weather prediction (NWP) model. The result is a spatially complete estimate of global ocean vector winds on six-hour intervals that are closely tied to satellite measurements. The current versions of CCMP are fairly accurate at low to moderate wind speeds (<15 m/s) but are systematically too low at high winds at locations/times where a collocated satellite measurement is not available. This is mainly because the NWP winds tend to be lower than satellite winds, especially at high wind speed. The current long-term CCMP version, version 2.0, also shows spurious variations on interannual to decadal time scales caused by the interaction of satellite/model bias with the varying amount of satellite measurements available as satellite missions begin and end. To alleviate these issues, here we explore methods to adjust the source datasets to more closely match each other before they are combined. The resultant new CCMP wind analysis agrees better with long-term trend estimates from satellite observations and reanalysis than previous versions.

Machine learning forecasts of Scandinavian numerical weather prediction wind model residuals with control theory for wind energy

The quality of wind data from the numerical weather prediction significantly influences the accuracy of wind power forecasting systems for wind parks. Therefore, an in-depth investigation of these wind data themselves is essential to improve wind power generation efficiency and maintain grid reliability. This paper proposes a novel framework based on machine learning for concurrently analyzing and forecasting predictive errors, called residuals, of wind speed and direction from a numerical weather prediction model versus measurements over a while. The performance of the framework is testified by a wind farm inside the Arctic. It is demonstrated that the residuals still contain significant meteorological information and can be effectively predicted with machine learning and the linear autoregression works well for multi-timesteps predictions of overall, East–West,​ and North–South wind speeds residuals by comparing the four forecast learning algorithms’ performance. The predictions may be applied to correct the NWP wind model, making quality feedback improvements for inputs for wind power forecasting systems.

The Effect of Decision Analysis on Power System Resilience and Economic Value During a Severe Weather Event

Because of climate changes, natural disasters are becoming more serious. For instance, the intensity of typhoons has been increasing in recent years. Typhoons and other natural disasters have high-impact low-probability characteristics. Thus, procedures for preparing for natural disasters and increasing power system resilience are important issues. This article proposes an all-inclusive process for system operators to make decisions for enhancing power system resilience and economic value during a severe weather event. This process first considers the typhoon track, the fragility curve and the recovery time of transmission lines. After collecting these data, system simulations and a calculated resilience index are implemented according to cases with and without disaster prevention. Next, the probability threshold and calculated economic value index are obtained based on numerical weather prediction wind speeds and the cost-loss ratio. Finally, the two indexes are considered in combination to obtain the highest resilience with the greatest benefit. The proposed process helps system operators make decisions for appropriate preventive actions at the least cost. An actual Taiwan power system and a severe weather event are used as an example to demonstrate the proposed decision analysis. The simulation results indicate the feasibility of the proposed method, which can reduce potential risks caused by extreme weather events with the maximum economic benefits.

Numerical Weather Prediction Correction Strategy for Short-Term Wind Power Forecasting Based on Bidirectional Gated Recurrent Unit and XGBoost

Accurate short-term wind power forecasting (WPF) plays a crucial role in grid scheduling and wind power accommodation. Numerical weather prediction (NWP) wind speed is the fundamental data for short-term WPF. At present, reducing NWP wind speed forecast errors contributes to improving the accuracy of WPF from the perspective of data quality. In this article, a variational mode decomposition combined with bidirectional gated recurrent unit (VMD-BGRU) method for NWP wind speed correction and XGBoost forecasting model are proposed. First, several NWP wind speed sub-series are divided by VMD to obtain more abundant multidimensional timing features. BGRU is applied to establish the potential relation between decomposed NWP wind speed sub-series and measured wind speed and get the proposed wind speed correction model. Then, a more clear regression forecasting model is trained based on XGBoost using historical measured wind speed and power. The corrected NWP wind speed is used to forecast wind power by XGBoost. Finally, the superiority of the proposed method is validated on a wind farm located in China. The results show that the proposed correction model and forecasting model outperform other compared models.

A novel pure data-selection framework for day-ahead wind power forecasting

Numerical weather prediction (NWP) data possess internal inaccuracies, such as low NWP wind speed corresponding to high actual wind power generation. This study is intended to reduce the negative effects of such inaccuracies by proposing a pure data-selection framework (PDF) to choose useful data prior to modeling, thus improving the accuracy of day-ahead wind power forecasting. Briefly, we convert an entire NWP training dataset into many small subsets and then select the best subset combination via a validation set to build a forecasting model. Although a small subset can increase selection flexibility, it can also produce billions of subset combinations, resulting in computational issues. To address this problem, we incorporated metamodeling and optimization steps into PDF. We then proposed a design and analysis of the computer experiments-based metamodeling algorithm and heuristic-exhaustive search optimization algorithm, respectively.Experimental results demonstrate that (1) it is necessary to select data before constructing a forecasting model; (2) using a smaller subset will likely increase selection flexibility, leading to a more accurate forecasting model; (3) PDF can generate a better training dataset than similarity-based data selection methods (e.g., K-means and support vector classification); and (4) choosing data before building a forecasting model produces a more accurate forecasting model compared with using a machine learning method to construct a model directly.

Feature extraction of meteorological factors for wind power prediction based on variable weight combined method

To achieve a high penetration of renewable energy integration, an effective solution is to explore the interdependence between numerical weather prediction (NWP) data and historical wind power to improve prediction accuracy. This paper proposes a novel combined approach for wind power prediction. The characteristics of NWP and historical wind power data are extracted by using the feature extraction technique, the predictor is designed based on extreme learning machine (ELM) and least squares support vector machine (LSSVM) model, and then key parameters of the prediction models are optimized by improving cuckoo search (ICS) to obtain a reliable value, which is defined as the pre-combined prediction value (PPA). To obtain a reliable result, a variance strategy is developed to allocate the weights of the pre-combined prediction model to obtain the final predicted values. Four seasons dataset collected from regional wind farms in China is utilized as a benchmark experiment to evaluate the effectiveness of the proposed approach. The results of comprehensive numerical cases with different seasons show that the proposed approach, which considers multiple-error metrics, including error metrics, accuracy rate, qualification rate, and improvement percentages, achieves higher accuracy than other benchmark prediction models.

Coupling High-Resolution Numerical Weather Prediction and Computational Fluid Dynamics: Auckland Harbour Case Study

In this study, the resilience of large cities and their built infrastructure in New Zealand to extreme winds, is investigated by coupling the outputs of a very high-resolution, 333-m resolution, numerical weather prediction (NWP) model with computational fluid dynamics (CFD) simulations. Following an extreme wind event on 18 September 2020 in Auckland, in which two trucks travelling over the Auckland Harbour bridge tipped over and damaged the bridge structure, a CFD simulation of airflow over the bridge using the Reynolds-averaged Navier–Stokes (RANS) method and NWP wind speed forecasts as the inlet profile is conducted. The 333 m NWP forecasts were validated against four nearby observation sites, showing generally high correlations of greater than 0.8 and low mean bias (±3 m s−1) and RMSE (<3 m s−1) values. The CFD-based estimates of the mean wind speed-up over the bridge showed that the mean wind speed could increase by a factor of 1.15–1.20 in the vicinity of the road where the toppled vehicles were travelling. Additionally, NWP forecasts and CFD estimates of wind gusts at the maximum bridge height, within the area not affected by the bridge structure, agreed well with a value of about 25 m s−1. An anemometer mounted at the top of the bridge arch measured a higher gust wind speed of about 35 m s−1 that could have been influenced by the gust speed-up resulting from the flow separation from the bridge arch, which is demonstrated in the CFD results. The results demonstrate the importance of understanding localised wind speed-up effects and distinguishing them from the approaching undisturbed airflow.

Assessing probabilistic modelling for wind speed from numerical weather prediction model and observation in the Arctic

Mapping Arctic renewable energy resources, particularly wind, is important to ensure the transition into renewable energy in this environmentally vulnerable region. The statistical characterisation of wind is critical for effectively assessing energy potential and planning wind park sites and is, therefore, an important input for wind power policymaking. In this article, different probability density functions are used to model wind speed for five wind parks in the Norwegian Arctic region. A comparison between wind speed data from numerical weather prediction models and measurements is made, and a probability analysis for the wind speed interval corresponding to the rated power, which is largely absent in the existing literature, is presented. The results of the present study suggest that no single probability function outperforms across all scenarios. However, some differences emerged from the models when applied to different wind parks. The Nakagami and Generalised extreme value distributions were chosen for the numerical weather predicted prediction and the observed wind speed modelling, respectively, due to their superiority and stability compared with other methods. This paper, therefore, provides a novel direction for understanding the numerical weather prediction wind model and shows that its speed statistical features are better captured than those of real wind.

Day‐ahead wind power combination forecasting based on corrected numerical weather prediction and entropy method

To satisfy the grid operation scheduling requirements for wind power forecasting model accuracy, the measured wind speed near the height of the wind turbine hub is added to the wind power combined forecasting model. First, the relationship between the numerical weather prediction wind speed and the measured wind speed at different heights are analysed, and the correlation between each wind speed and the wind power is compared. Second, the random forest algorithm combined with the cumulative contribution rate is used to select several meteorological types of numerical weather prediction data as the input of the long short-term memory network to predict wind speed. Third, while inputting the meteorological data provided by numerical weather prediction, which is highly related to wind power, the wind power prediction network also uses the predicted wind speed of the upper network as input to predict wind power. Finally, the entropy method is used to dynamically determine the combined weights of each forecasting model and improve the adaptability of the model. Research and analysis using measured data from two wind farms located in northeast China have verified the effectiveness of the method.