Ultra-short Term Wind Power Research Articles

KAN-Transformer Model for UltraShort-Term Wind Power Prediction Based on EWMA Data Processing

When using the Transformer model for wind power prediction, the presence of noise in wind power data and the model’s final layer relying solely on a simple linear output reduces the model’s ability to capture nonlinear relationships, leading to a decrease in prediction accuracy. To address these issues, this paper proposes an ultrashort-term wind power prediction model based on exponential weighted moving average (EWMA) data processing and Kolmogorov–Arnold Network (KAN)-Transformer. First, multiple variable features are smoothed using EWMA, which suppresses noise while preserving the original data trends. Then, the EWMA-processed data is input into the Encoder and Decoder modules of the Transformer model to extract features. The output from the Decoder layer is then passed through the KAN layer, built using a cubic B-spline function, to enhance the model’s ability to capture nonlinear relationships, thereby improving the prediction accuracy of the Transformer model for wind power. Finally, experimental analysis is conducted, and it shows that the proposed model achieves the highest prediction accuracy, with a mean absolute error of 4.38 MW, a root mean squared error of 7.37 MW, and a coefficient of determination of 98.73%.

Ultra-short term wind power prediction method based on LightGBM and transformer

Abstract Accurate ultra-short-term wind power prediction is very important for the safe and stable operation of the power system. At present, most wind power forecasting systems use numerical weather forecast data and the data collected by the Supervisory Control And Data Acquisition (SCADA) system. However, these data have the characteristics of high data dimension, feature redundancy, and feature correlation. Therefore, in the process of ultra-short power prediction, it is necessary to select features with high power correlation and low cross-correlation between features. In this paper, a feature selection method for wind power prediction based on LightGBM is proposed to calculate the importance of all features and determine the preliminary selected features. Then, the maximum information coefficient is used to construct the correlation discriminant matrix, according to which the features with similar importance in a single screening are evaluated, and the input features with high similarity are discarded. In addition, in order to improve the accuracy of the system’s wind power prediction, this paper uses the effective features extracted by LightGBM to design an ultra-short-term power prediction method based on Transformer. The results show that the RMSE of ultra-short-term wind power prediction is 7.3%.

Ultra-short term wind power prediction based on quadratic variational mode decomposition and multi-model fusion of deep learning

To address the challenges associated with the intricate selection of decomposition technical parameters and the adverse impact of high-frequency non-stationary components on prediction accuracy, a differential evolution (DE) and sparrow search algorithm (SSA) parameter optimization model is formulated. Through the optimization of variational mode decomposition (VMD) and bidirectional short and long-term memory (BiLSTM) neural networks, enhancements are made to the overall performance of the prediction method. Subsequently, DESSA–VMD is employed to quadratically decompose the high-frequency unstable component, mitigating the detrimental effects of randomness and volatility on the prediction accuracy of the primary component. Following this, the DESSA–BiLSTM neural network is applied to predict the high-frequency strong non-stationary component, whereas the autoregressive integrated moving average is utilized for predicting the low-frequency periodic component. Finally, a case analysis is conducted using actual data comprising 2000 sets of wind power in a province. When the test set consisted of 600 groups, the root mean square error index value of the proposed prediction model exhibited reductions of 1.95 MW, 2.86 MW, and 1.16 MW, respectively, compared with the BP, SVM, and LSTM methods. Additionally, the mean absolute percentage error index showed decreases of 2.26 %, 2.96 %, and 1.73 %, respectively.

A novel model for ultra-short term wind power prediction based on Vision Transformer

Wind power has quickly developed in the world owing to the advantages of pure, inexpensive, and inexhaustible. However, strong volatility, unmanageable, and randomness make it difficult to achieve secure wind power generation. An excellent wind power prediction is effective for power system scheduling and safely stable operation. Vision Transformer (ViT) model is introduced for building a connection of the extracted characteristics and desired output. Long-short term memory (LSTM) is combined with ViT, and a new wind power forecasting model is proposed in this paper. For the proposed LSTM-ViT model, the temporal aspects of the weather data and correspondence properties are extracted based on LSTM. The link of the output and characteristic is established in view of the ViT, and the multi-headed self-attentiveness mechanisms in ViT fully exploit the relationship between the inputs. The validity and sophistication of the LSTM-ViT method are validated by the climate statistics and statistics of wind power. The results indicate that the wind power forecasting model is provided with higher prediction accuracy. The forecast results for the fourth quarter are used as analysis cases. The root mean square error of the method is reduced by 41.77%, 16.60%, 28.72%, 26.81%, and 16.25% compared to gate recurrent unit (GRU), LSTM, ViT, convolutional neural network (CNN)-ViT, and GRU-ViT respectively. The mean absolute error of the LSTM-ViT method in the first quarter is 0.327, with model comparison values reduction of 33.71%, 38.30%, 32.99%, 17.63% and 10.65% respectively.

Ultra-short term wind power forecasting method based on improved VMD

A CNN-GRU ultra-short term wind power prediction method based on improved VMD is proposed. Firstly, in the data processing part, according to the irregularity and non-stationary peculiarities of wind power, the variational mode decomposition algorithm is adopted to decompose the original sequence of wind power to reduce the non-stationarity. At the same time, considering that the parameter setting and selection in the variational modal decomposition algorithm are of great significance to the decomposition effect, the improved whale improvement method is adopted to find the best parameters in VMD to avoid the problem of poor decomposition effect caused by artificial setting. Finally, the CNN-GRU and GRU models are simulated and compared on the Matlab platform through the field wind farm data.

Ultra-short-term wind power forecasting techniques: comparative analysis and future trends

In recent years, the integration of wind power into the grid has steadily increased, but the volatility and uncertainty of wind power pose significant challenges to grid planning, scheduling and operation. Ultra-short term wind power forecasting technology as the basis of daily scheduling decision can accurately predict the future hourly wind power output, and has important research significance for ensuring the safe and stable operation of power grid. Although research on ultra-short-term wind power forecasting technology has reached maturity, practical engineering applications still face several challenges. These challenges include the limited potential for improving the accuracy of numerical weather forecasts, the issue of missing historical data from new wind farms, and the need to achieve accurate power prediction under extreme weather scenarios. Therefore, this paper aims to critically review the current proposed ultra-short-term wind power forecasting methods. On this basis, analyze the combined power forecasting method under extreme weather scenarios, and illustrate its effectiveness through wind farm case studies. Finally, according to the development trend and demand of future power systems, future research directions are proposed.

Ultra short-term wind power prediction based on lightweight learning machine with error compensation

Ultra short-term wind power prediction based on lightweight learning machine with error compensation

A novel ultra short-term wind power prediction model based on double model coordination switching mechanism

Ultra-short-term wind power provides technical support for unit control and scheduling to optimize the power system. Wind fluctuation is the main factor that makes it difficult to accurately predict wind power output. To improve the power prediction accuracy of the wind power fluctuation period, a combined prediction model that can automatically switch between two models is proposed. For small fluctuations in wind speed, we construct a sequence-to-sequence model that integrates temporal and spatial attention mechanisms for power prediction. The prediction model switches to the wind power curve model when the wind speed fluctuates significantly, which reflects the static characteristics of the unit. We determine the appropriate wind speed fluctuation threshold on the verification set, so that the two prediction models can coordinate the switchSimulation experiments were carried out on the data set provided by a wind farm in Inner Mongolia, China. The normalized RMSE of the forecast in the future 4h is 0.1405.

A novel ultra-short-term wind power prediction model jointly driven by multiple algorithm optimization and adaptive selection

Ultrashort-term wind power forecasting with great precision and robustness is essential for improving power quality and reliability management and reducing the cost of rotating backup supply, thus guaranteeing the security and stability of power systems in large-scale grid-connected wind power. This study proposed a novel ultra-short-term wind power prediction model jointly driven by multiple algorithm optimization and adaptive selection. The original wind power sequence is decomposed into smooth subsequences by the optimized variational mode decomposition algorithm. Each sequence is predicted in advance by two outstanding prediction methods. The method with high accuracy is automatically selected for the prediction output of that sequence. The two excellent models are least square support vector machine optimized by improved whale optimization algorithm and hybrid kernel extreme learning machine optimized by sine cosine search-sparrow search algorithm, improving the prediction accuracy and efficiency. Based on three publicly available datasets, the proposed model has more than 41 % percent improvement in root mean square error compared to the current studies and about 20 % percent improvement in root mean square error compared to the proposed models without selection strategy. Combined with the adaptive selection concept, the proposed prediction model can obtain more accurate wind power prediction results with higher prediction accuracy, more substantial prediction generalization, and robustness.

A novel EMD and causal convolutional network integrated with Transformer for ultra short-term wind power forecasting

Accurate wind power forecasting can enhance the safety, stability, economy and controllability of the power system. Traditional physical methods and statistical methods are easily affected by data quality and extraction methods in wind power forecasting. The commonly used recursive neural network method may have memory decline phenomenon in wind power forecasting and does not support parallel calculation, thus limiting the forecasting accuracy. To solve the above problems, in this paper, a wind power forecasting method based on EMD-CCTransformer is proposed. The network model is based on an encoder–decoder structure, where the encoder is used to parse historical wind power sequences, the decoder generates future wind power, and the encoder and decoder are connected using an attention mechanism. In this method, the EMD algorithm is used to decompose the wind power series and obtain the changes of power signals in different time scales, which improves the ability of Transformer to maintain long-term information. Meanwhile, in view of the partial unknowability of the Transformer model, the convolutional attention mechanism is introduced to replace the dot product attention mechanism to form the CCTransformer model, which further improves the forecasting accuracy. We use large-scale wind power data (annual data of the year of 2020 ) to train and test the proposed model. Experimental results show that compared with commonly used wind power forecasting methods, the forecasting error of the proposed EMD-CCTransformer forecasting method in this paper is lower and its model training time is further shortened.

Predictive maintenance of wind turbines based on digital twin technology

Predictive maintenance of wind turbines plays a crucial part in directing power grid dispatching and maintaining power grid security. In this paper, a way of ultra-short term wind power prediction relied on digital twin technology is proposed, which realizes actual time and accurate wind power prediction by building a digital model. Firstly, BP neural network (back propagation neutral network) was used to predict the wind power, and the initial predicted value of wind power was obtained. Then the meteorological data was substituted into the historical meteorological database to find similar meteorological conditions data, and the BP neural network predicted value was weighted to get the final digital twin predicted value. The simulation results indicate that this method can effectively enhance prediction accuracy of wind power.

An Ultrashort-Term Wind Power Prediction Method Based on a Switching Output Mechanism

The ultrashort-term wind power prediction (USTWPP) technology assists the grid to arrange spare capacity, which is important to optimize power investment reasonably. To improve the accuracy of USTWPP and optimize power investment requirements, a USTWPP method with dynamic switching of multiple models is proposed. For high wind speed fluctuation samples, the wind speed-power curve (WSPC) is fitted in a large sample of historical data, and the corrected wind speed is the input of WSPC. The spatiotemporal attentive network model (STAN) is built for the prediction of low wind speed fluctuation samples. According to the real-time fluctuation characteristics of the correction wind speed, a switching mechanism between multiple models is established to reconstruct the prediction results along the time axis direction, and the predicted power is set to zero for the samples whose correction wind speed is lower than the cut-in wind speed. We conducted simulation experiments with data provided by a wind farm with an installed capacity of 130.5 MW in China. The normalized root mean square error (NRMSE) for the 4 h ahead predicted power reaches 0.0907, which verified the validity and applicability of the proposed model.

A Selective Review on Recent Advancements in Long, Short and Ultra-Short-Term Wind Power Prediction

With large penetration of wind power into power grids, the accurate prediction of wind power generation is becoming extremely important. Planning, scheduling, maintenance, trading and smooth operations all depend on the accuracy of the prediction. However due to the highly non-stationary and chaotic behaviour of wind, accurate forecasting of wind power for different intervals of time becomes more challenging. Forecasting of wind power generation over different time spans is essential for different applications of wind energy. Recent development in this research field displays a wide spectrum of wind power prediction methods covering different prediction horizons. A detailed review of recent research achievements, performance, and information about possible future scope is presented in this article. This paper systematically reviews long term, short term and ultra short term wind power prediction methods. Each category of forecasting methods is further classified into four subclasses and a comparative analysis is presented. This study also provides discussions of recent development trends, performance analysis and future recommendations.

A Novel Framework for Ultra-Short Term Wind Power Prediction Based on Rf-Woa-Vmd and Bigru Optimized by Attention Mechanism

A Novel Framework for Ultra-Short Term Wind Power Prediction Based on Rf-Woa-Vmd and Bigru Optimized by Attention Mechanism

Ultra-short term wind power prediction applying a novel model named SATCN-LSTM

Accurate and reliable wind power forecasting has become very important to power system scheduling and safely stable operating. In this paper, a novel self-attention temporal convolutional network (SATCN) is combined with long-short term memory (LSTM) to forecast wind power for guaranteeing the continuous electricity supply. In the proposed SATCN-LSTM model, the structure of SATCN with a self-attention mechanism is conducted to pay more attention to features that contribute more to the output. The strength of SATCN is performed through extracting temporal feature of meteorological data and correlation characteristics between variables. LSTM is used after SATCN to further build the connection between features and outputs for predicting future ultra-short time wind power. The effectiveness and advancement of the proposed method is tested by using meteorological data and wind power data from two different wind farms in the U.S. The experimental results reveal that the SATCN-LSTM model is more accurate comparing to other methods. Taking California's fourth quarter wind power forecast results as an example, the proposed method has carried out a reduction of 17.56%, 10.99%,11.34% and 3.68% on the root mean square error compared with LSTM, TCN, CNN-LSTM, TCN-LSTM.

Ultra-short-term Wind Power Output Prediction Based On LS-WMC Combined Model

In this paper, an ultra short term wind power output prediction method based on least square and weighted Markov chain model is proposed. Firstly, the wind farm output is fitted based on the least square method, and then the prediction accuracy is improved by using the weighted Markov chain model. At the same time, the partial exponential weighting method is used to improve the prediction accuracy of ultra short-term wind power output on the basis of reducing the generation frequency of transition probability matrix, so as to optimize and improve the prediction results. The results show that the method can improve the prediction accuracy.

Ultra Short Term Wind Power Prediction Model Based on WRF Wind Speed Prediction and CatBoost

Due to the urgent requirements of clean energy development, the installed capacity of wind turbine is gradually increasing. In order to achieve effective wind turbine grid control, accurate wind power prediction is very important. In this paper, based on the US Atmospheric Research Center (NCAR) Weather Research and Forecast (WRF) model, the predicted wind field is obtained. Then, a super short-term fast wind power prediction model is proposed, which is composed of Spearman correlation coefficient method for feature extraction and catboost algorithm. With historical power, historical wind speed and predicted wind speed as inputs, the predicted power in the next 4 hours (15 minutes interval) is output. In order to evaluate the prediction ability of the proposed model, four algorithms, LSTM, CatBoost, XGBoost and LightBGM, are adopted. Taking root mean square error (RMSE), mean absolute error (MAE) and training time as evaluation indexes, the results show that CatBoost has the best comprehensive performance.

Wind Power Deterministic Prediction and Uncertainty Quantification Based on Interval Estimation

Abstract With the increasing penetration of wind power into modern power systems, accurate forecast models play a crucial role in large-scale wind power consumption and power system stability. To improve the accuracy and reliability of ultrashort-term wind power prediction, a novel deterministic prediction model and uncertainty quantification with interval estimation were proposed in this study. In consideration of the dynamic characteristics of a generator and conditional dependence, the generator rotor speed and pitch angle were regarded as the indicators of the dynamic characteristics of the generator, and light gradient boosting machine (LGBM) with a Bayesian optimization method was explored to build the deterministic prediction model. Considering the conditional dependence between output power and forecast error, a fuzzy C-means clustering method was used to cluster forecast errors into different clusters, and the best error probability distribution was obtained by fitting the error histogram with nonparametric kernel density estimation. Prediction intervals at different confidence levels were calculated, and the error uncertainty was quantified. A case study was conducted to compare prediction accuracy and reliability by using the present and proposed methods. Results demonstrate that the LGBM deterministic prediction model combined with Bayesian optimization has better prediction accuracy and lower computational cost than the comparative models, specifically when the input features are high-dimensional big data. The nonparametric estimation method with conditional dependence is reliable for interval prediction. The proposed method has a certain reference value for wind turbines participating in frequency regulation and power control of power grid.

A novel ultra-short term wind power forecasting intelligence system based on hybrid neural network

In the current state of globalization, intraday forecasting plays a vital role in different fields such as wind energy, trade, stock, aircraft operations and healthcare operations. The ultra-short term forecasting which is used forecast 30 sec to 6 h time horizon task is critical due to prediction from the less data. Ultra short term forecasting is essential one for traders, investors, wind firms and policy makers. This research investigated ultra-short term forecasting intelligence system with hybrid neural network model to forecast the wind power. Recorded data for wind power, wind direction and wind speed were used which is comprised 3 days at Yalova, Turkey were used for model training and testing. The hybrid neural network model predicted result was compared with neural network model.

A Hybrid Method for Ultrashort-Term Wind Power Prediction considering Meteorological Features and Seasonal Information

High-precision wind power prediction is important for the planning, economics, and security maintenance of a power grid. Meteorological features and seasonal information are strongly related to wind power prediction. This paper proposes a hybrid method for ultrashort-term wind power prediction considering meteorological features (wind direction, wind speed, temperature, atmospheric pressure, and humidity) and seasonal information. The wind power data are decomposed into stationary subsequences using the ensemble empirical mode decomposition (EEMD). The principal component analysis (PCA) is used to reduce the redundant meteorological features and the algorithm complexity. With the stationary subsequences and extracted meteorological features data as inputs, the long short-term memory (LSTM) network is used to complete the wind power prediction. Finally, the seasonal autoregressive integrated moving average (SARIMA) is innovatively used to fit seasonal features (quarterly and monthly) of wind power and reconstruct the prediction results of LSTM. The proposed method is used to predict 15-minute wind power. In this study, three datasets were collected from a windfarm in Laizhou to validate the prediction performance of the proposed method. The experimental results showed that the prediction accuracy was significantly improved when meteorological features were considered and further improved with seasonal correction.