Short-term Wind Power Prediction Method Research Articles

A short-term wind power prediction method via self-adaptive adjacency matrix and spatiotemporal graph neural networks

Graph neural networks (GNN) recently have been successfully applied in wind power prediction by employing geo-information to construct the graphs that serve as the GNN-based prediction model. However, these graphs cannot maintain the latent correlation and attribute of the wind turbines, leading to inferior performance. This research proposes an optimizing wind power prediction model through attention mechanism and spatiotemporal graph neural networks. Initially, the spectral clustering and a self-adjacency matrix to construct the graph nodes and edges. Subsequently, the proposed ASTGNN combined from graph convolutional networks and a gated recurrent unit with an attention mechanism is designed to act as the prediction model. A comprehensive set of experiments has been carried out and the proposed method not only improved prediction accuracy but also enhanced computational efficiency. According to the results obtained, the developed model demonstrated an improvement that is up to 13 % in terms of RMSE and 6.7 % in terms of computation time compared to the latest models.

A centralized power prediction method for large-scale wind power clusters based on dynamic graph neural network

The uncertainty of the wind process leads to the randomness of its regional propagation, and the spatial correlation between nearby wind farms also shows a dynamic change tendency under the influence of wind direction. To consider the influence of dynamic spatial correlation on wind power prediction modeling, a short-term wind power prediction method based on a dynamic graph neural network is proposed. First, the topology graph of the wind farm cluster was established to represent the correlation of wind farms based on graph theory. Then, a dynamic spatiotemporal graph neural network was constructed to adapt graph topology by node embedding, which can explore the changing characteristics of spatial correlation among wind farms. Finally, we proposed a decoupling error model that can quantify the proportion of errors caused by the modeling process, which can assist in evaluating the performance of predictive models. We conducted experiments using data provided by the wind farm cluster in Inner Mongolia, and the average normalized Root Mean Square Error for the 12 wind farms was 0.1424, which verified the effectiveness of the proposed model.

Short-term wind power prediction method based on multivariate signal decomposition and RIME optimization algorithm

Accurate characterization of the dynamics of wind power systems under highly unstable conditions is essential for short-term wind power forecasting. Multivariate factors, such as wind speed, wind direction and climatic factors at different heights, as well as the relationships between them, need to be fully considered. To this end, after the Pearson correlation coefficient is used to identify the main influencing variables, the empirical modal decomposition (MEMD) method is utilized to decompose the data in order to capture the deep coupling relationship and the spatio-temporal pattern of change among the variables. Combined with a bidirectional long and short-term memory network (BiLSTM) optimized through the RIME algorithm, a short-term wind power prediction model was constructed. Data analysis of two wind farms in Xinjiang and Gansu, China, shows that the model has higher prediction accuracy compared to the baseline model. The effectiveness of RIME and MEMD is verified through component ablation experiments and comparison experiments with other optimization algorithms and signal decomposition algorithms. To cope with large-scale data, dimensionality reduction of IMF features using Elastic Net (EN) is explored to reduce computational requirements and maintain good prediction performance. The method provides strong support for power system scheduling and efficient utilization of renewable energy.

A new short-term wind power prediction methodology based on linear and nonlinear hybrid models

Fast and accurate wind power prediction is of great significance for grid planning. However, wind power dataset tends to be highly stochastic and volatile, while showing more stable seasonal and cyclical changes, which is a linear and nonlinear superposition features, and it is difficult to use a single linear or nonlinear model to make accurate predictions. Considering these essential features of wind power data, a short-term wind power prediction method based on linear and nonlinear hybrid models is proposed in this paper. First, the complete ensemble empirical mode decomposition (CEEMD) is used to decompose and reconstruct the wind speed and direction in the original dataset to reduce the volatility. Then, to capture the linear features in the dataset, the autoregressive integrated moving average model with exogenous input variables (AIRMAX) is used for linear modeling, and the sparrow search algorithm optimized gated recurrent unit (SSA-GRU) is used to model the nonlinear features. At the same time, to improve the efficiency of model training, federated learning (FL) is utilized for distributed model training. Finally, the ARIMAX and SSA-GRU models are weighted and summed the prediction results to gain the final prediction results using equal weighted averaging (EWA), minimum sum of squares error (MSSE), and maximum grey relational analysis (MGRA), which are commonly used to compute the weights of the combined models, respectively. The wind power dataset from a wind farm in northwest China from January 1, 2022 to October 31, 2022 are used for experiments and analysis, and the results show that the root mean square error (RMSE), R-square (R2), and accuracy (ACC) of the proposed method are 11.944, 0.987, and 0.613, respectively, which are better than all the compared models. The main contribution of this paper is twofold, on the one hand, it indirectly proves that the wind power dataset is formed by the superposition of linear and nonlinear features, and on the other hand, it puts forward a theoretical model and research paradigm for predicting short-term wind power and presents a scientific basis for grid scheduling.

LSTM Short-Term Wind Power Prediction Method Based on Data Preprocessing and Variational Modal Decomposition for Soft Sensors.

Soft sensors have been extensively utilized to approximate real-time power prediction in wind power generation, which is challenging to measure instantaneously. The short-term forecast of wind power aims at providing a reference for the dispatch of the intraday power grid. This study proposes a soft sensor model based on the Long Short-Term Memory (LSTM) network by combining data preprocessing with Variational Modal Decomposition (VMD) to improve wind power prediction accuracy. It does so by adopting the isolation forest algorithm for anomaly detection of the original wind power series and processing the missing data by multiple imputation. Based on the process data samples, VMD technology is used to achieve power data decomposition and noise reduction. The LSTM network is introduced to predict each modal component separately, and further sum reconstructs the prediction results of each component to complete the wind power prediction. From the experimental results, it can be seen that the LSTM network which uses an Adam optimizing algorithm has better convergence accuracy. The VMD method exhibited superior decomposition outcomes due to its inherent Wiener filter capabilities, which effectively mitigate noise and forestall modal aliasing. The Mean Absolute Percentage Error (MAPE) was reduced by 9.3508%, which indicates that the LSTM network combined with the VMD method has better prediction accuracy.

Short-term wind power prediction method based on CEEMDAN-GWO-Bi-LSTM

In order to improve the short-term prediction accuracy of wind power and provide the basis for power grid dispatching, a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) -grey wolf optimization (GWO) -bidirectional long short-term memory network (Bi-LSTM) prediction model is proposed to predict the short-term output power of wind farms. Firstly, the original wind power data is preprocessed, and then the original wind power data is decomposed into components that are easy to extract features by using CEEMDAN. The Bi-LSTM prediction model is established for each component, and then the grey wolf optimization algorithm is used to optimize the parameters of the Bi-LSTM model. The optimized hyperparameters are brought into the Bi-LSTM model to output the prediction results of each component. Finally, the prediction results of each component are superimposed and reconstructed to obtain the final prediction results of wind power. The simulation analysis of the power data of a wind farm in Gansu Province shows that the CEEMDAN-GWO-Bi-LSTM model has better accuracy in short-term wind power prediction.

Short-Term Wind Power Prediction Based on Multi-Parameters Similarity Wind Process Matching and Weighed-Voting-Based Deep Learning Model Selection

Sufficiently accurate short-term wind power prediction is important for the grid dispatch of the power system. To improve the accuracy by selecting suitable model for each piece of wind processes, this paper presents a short-term wind power prediction method based on multi-parameters similarity wind process matching and weighed-voting-based deep learning model selection. First, a novel multi-parameters similarity wind process matching method is presented to match each forecast target sample with groups of highly similar historical wind processes, in which each 96h-time-scale sample is divided into multiple wind processes by a tumbling time window, and a combinational similarity matching algorithm that consider four similarity indexes is proposed to judge the similarity among wind processes. Second, a weighed-voting-based deep learning model selection method, in which the matched highly similar historical wind processes are introduced to vote the optimal candidate deep learning model, is proposed to select the optimal model from LSTM, BLSTM, CNN, CNN-LSTM, CNN-BLSTM, and SDAE for each forecast target wind process. Case studies are presented to verify the effectiveness and superiority of the proposed method. Based on this new method, the 24h-day-ahead and 96h-short-term prediction RMSE can be decreased by 0.69% to 1.7% and 1.15% to 2.2% respectively compared to single deep learning model, which demonstrates the effectiveness of the proposed method.

Adaptive short-term wind power forecasting with concept drifts

The instability of wind power has a serious impact on the power grid system, and an accurate wind power forecasting is greatly demanded in practice. Due to the time-varying nature, the distribution of weather variables such as wind speed, wind direction and temperature and/or the functional relationship of the power output relating to these weather variables are likely to change over time, which are often known as “concept drifts”. However, most of the prediction models usually fail to adapt to such concept drifts. This would deteriorate the prediction accuracy, especially for the short-term prediction with high accuracy requirements. Motivated by this, this paper proposes an adaptive short-term wind power prediction method, aimed at automatically detecting the occurrence of concept drifts and updating the forecast model accordingly. The proposed method consists of three main steps, extract sample-related and sequence-related features of the weather data, cluster the data based on the similarity of the features extracted, and develop a new power prediction model with automatic drift detection and adaptation for each cluster. The comparison results show that the prediction performance of the proposed method is superior to that of the competitive methods.

A short-term wind power prediction method based on dynamic and static feature fusion mining

Wind power is a kind of time-varying time series with fluctuation characteristics. To take full advantage of the time-varying value provided by wind power fluctuations, a short-term wind power prediction method based on dynamic and static feature fusion mining is proposed. First, three statistical features are manually constructed to characterize the dynamic fluctuation of wind speed, these features provide more valuable patterns for the input data. Then, we construct a residual network structure that incorporates the bidirectional gate recurrent unit, and incorporate temporal and spatial attention mechanisms in the network structure. This network structure is used to train the wind power prediction model, which has great advantages in reducing the degradation and overfitting problems caused by increasing the depth of the network. Finally, a wind power prediction index is proposed to quantify the proportion of NWP link error and modeling link error in the total error. Simulation experiments were conducted on a wind farm with an installed capacity of 400.5 MW in Jilin Province, China, and the predicted NRMSE is 0.1581.

Short-term Wind Power Prediction Method Based on Genetic Algorithm Optimized XGBoost Regression Model

In order to solve the problem of accuracy and rapidity of short-term prediction of wind power output, the eXtreme Gradient Boosting (XGBoost) regression model is used in this paper to predict wind power output. For the models commonly used at the present stage, such as Long Short Term Memory (LSTM), random forest and ordinary XGBoost model, the modelling time is long, and the accuracy is not enough. In this paper, a genetic algorithm (GA) is introduced to improve the accuracy and speed of prediction of the XGBoost regression model. Firstly, the learning rate of the XGBoost model is optimized by using the good searching ability and flexibility of the genetic algorithm. Then variable weight combination prediction is carried out. The objective function for this problem is the mean square error that occurs between the value that is predicted and the value that actually occurs in the training set. GA is responsible for determining the model’s final weight. The historical output data of the wind plant is used in this paper to verify the XGBoost regression model based on a genetic algorithm and get the predicted value, which is then compared with the prediction results of LSTM and random forest algorithm. Example simulation and analysis show that the XGBoost regression model optimized by the genetic algorithm can be more significantly in solving the accuracy and rapidity of the prediction of short-term wind power output.

Short-Term Wind Power Prediction Method Based on Combination of Meteorological Features and CatBoost

As one of the hot topics in the field of new energy, short-term wind power prediction research should pay attention to the impact of meteorological characteristics on wind power while improving the prediction accuracy. Therefore, a short-term wind power prediction method based on the combination of meteorological features and CatBoost is presented. Firstly, morgan-stone algebras and sure independence screening(MS-SIS) method is designed to filter the meteorological features, and the influence of the meteorological features on the wind power is explored. Then, a sort enhancement algorithm is designed to increase the accuracy and calculation efficiency of the method and reduce the prediction risk of a single element. Finally, a prediction method based on CatBoost network is constructed to further realize short-term wind power prediction. The National Renewable Energy Laboratory (NREL) dataset is used for experimental analysis. The results show that the short-term wind power prediction method based on the combination of meteorological features and CatBoost not only improve the prediction accuracy of short-term wind power, but also have higher calculation efficiency.

Short-term wind power prediction method based on deep clustering-improved Temporal Convolutional Network

Carbon neutrality has become the global consensus, and wind power is one of the key technologies to achieve carbon neutrality in the power system. However, the randomness and fluctuation of wind energy pose a great challenge to the safe and stable operation of the power system. Accurate wind power prediction results can effectively reduce the adverse effects of wind power uncertainty on power system operation. The high proportion of wind power connected to the grid requires higher prediction accuracy. However, the existing wind power prediction methods exist the problems of inaccurate classification of numerical weather prediction (NWP) and insufficient consideration of actual characteristics. Therefore, a short-term wind power prediction method based on deep clustering-improved Temporal Convolutional Network (TCN) is proposed in this paper. First, 22 typical features of NWP are extracted (including maximum and minimum wind speed, maximum and minimum temperature, etc.). Then, a deep clustering model based on Categorical Generative Adversarial Network is constructed to classify the extracted NWP features accurately. Finally, to address the problem of partial feature loss in the training process of traditional TCN, a gating mechanism is introduced to improve the activation function of its residual block, and an improved TCN prediction model for each class is established. The actual operation data of three wind farms are used to verify the effectiveness and robustness of the proposed wind power prediction method. The results show that the proposed method can reduce the prediction error (Root Mean Squared Error) from 7.18% to 12.87% in three wind farms, compared with other traditional prediction methods.

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.

Short-term Wind Power Prediction Method Based on UAV Patrol and Deep Confidence Network

At present, wind power has become the most promising energy supply. However, the intermittent and fluctuating wind power also poses a huge challenge to accurately adjust the electrical load. In order to find a method capable of forecasting wind power generation in a short period of time, we propose a short-term wind power generation forecasting method based on an optimized deep belief network approach. Based on GEFCom2012 competition dataset, by continuously tuning the parameters of the deep belief network for 15 sets of experiments, we obtained three optimal laboratory combinations: Experiment 4, Experiment 10, and Experiment 12. The results show that the R-squared values of Experiment 4, Experiment 10 and Experiment 12 are the highest, which are 0.955, 0.93 and 0.98, respectively. The average R-squared value of these three tuned experiments is 0.2342 higher than the average of the other 12 experiments. At the same time, it is concluded that when the learning frequency is low, the linear function can learn the most obvious features more directly; When the learning frequency is high, the nonlinear function can learn the internal latent features more directly.

A CNN-LSTM-LightGBM based short-term wind power prediction method based on attention mechanism

This paper proposes a CNN-LSTM-LightGBM based short-term wind power prediction method based on the attention mechanism, which contains three main parts: data preprocessing, model training and model prediction. In the data preprocessing stage, the historical environment and historical wind power data are collected, then data cleaning and normalization and other preprocessing on the data are performed; in the model training stage, we first build a CNN-LSTM model (model 1) that includes an attention mechanism. CNN network includes the Conv1D layer, the MaxPooling1D layer and the LSTM network includes the basic LSTM layer, the attention layer, the Dropout layer and the final Dense layer. Secondly, we build the LightGBM model (model 2), using the training set and the validation set for the two models above separately. In the model prediction stage, the trained model 1 and model 2 are used to make parallel predictions on the test set, and the MAPE-RW algorithm is employed to linearly combine model 1 and model 2 to form the final combined prediction model. The proposed prediction method considers various environmental factors including weather, wind speed, wind direction, temperature, pressure, humidity, etc., effectively extracts the local characteristics and time series characteristics of the data, and allocates the feature weights reasonably, thus can realize the accurate prediction of wind power.

Short-term wind power prediction using an improved grey wolf optimization algorithm with back-propagation neural network

Abstract A short-term wind power prediction method is proposed in this paper with experimental results obtained from a wind farm located in Northeast China. In order to improve the accuracy of the prediction method using a traditional back-propagation (BP) neural network algorithm, the improved grey wolf optimization (IGWO) algorithm has been adopted to optimize its parameters. The performance of the proposed method has been evaluated by experiments. First, the features of the wind farm are described to show the fundamental information of the experiments. A single turbine with rated power of 1500 kW and power generation coefficient of 2.74 in the wind farm was introduced to show the technical details of the turbines. Original wind power data of the whole farm were preprocessed by using the quartile method to remove the abnormal data points. Then, the retained wind power data were predicted and analysed by using the proposed IGWO–BP algorithm. Analysis of the results proves the practicability and efficiency of the prediction model. Results show that the average accuracy of prediction is ~11% greater than the traditional BP method. In this way, the proposed wind power prediction method can be adopted to improve the accuracy of prediction and to ensure the effective utilization of wind energy. A short-term wind power prediction method is designed and tested with experimental results obtained from a wind farm located in Northeast China. In order to improve the accuracy of the prediction method, the improved grey wolf optimization algorithm has been adopted to optimize its parameters.

Short-term wind power prediction based on multidimensional data cleaning and feature reconfiguration

Wind power prediction decreases the uncertainty of the entire energy system, which is essential for balancing energy supply and demand. In order to improve the prediction accuracy, a short-term wind power prediction method based on data cleaning and feature reconfiguration is proposed. A large number of historical samples consisting of wind direction, wind speed, and wind power are mapped into a multidimensional sample space, and the distribution of wind data in different dimensions are analyzed in depth. By calculating the local density of each sample, outliers are effectively detected. The features of wind are reconfigured into a global information map combined with the time series information, which reflects the variation of the wind process in the short term. The features of the original data are greatly enriched, providing a high-quality training set for the prediction model. A redesigned convolutional neural network was used to predict short-term wind power, and the proposed methods were trained and tested based on a dataset of a real wind farm in China. Data cleaning and feature reconfiguration reduce the average single-point error by 1.38% and 2.56%, respectively, while the combined method reduced it by 6.24%. Plenty of experimental results show that the proposed methods achieve good performance and effectively improve the accuracy of short-term wind power prediction.

Multisource Wind Speed Fusion Method for Short-Term Wind Power Prediction

Wind is the dominant factor for wind power generation. However, wind, which is intermittent and fluctuating all the time, is hard to be accurately forecasted, especially only by single-source numerical weather prediction. This article presents a short-term wind power prediction method based on multisource wind speed fusion. First, the relationships among the weather factors and wind power, and the characteristics of three independent forecasted wind speed (FWS) provided by three organizations are analyzed. Next, a weighted naive Bayes method is described to fuse the three FWSs in order to estimate an accurate wind speed according to their characteristics. Then, a backpropagation neural network is designed to predict the wind power based on the fused wind speed. Finally, application results show that the method accurately predicts wind power generation, and the accuracy is much higher than that predicted by conventional methods.

Short-term Wind Power Prediction Method Based on Wavelet Packet Decomposition and Improved GRU

Accurately predicting wind power in wind farms is of great significance to ensure the safe and stable operation of the power system. A novel short-term wind power forecasting method (WPD-GRU-SELU) based on wavelet packet decomposition (WPD) and improved gated recurrent unit (GRU) is proposed. Firstly, this method uses WPD to decompose the time series of wind power into several sub-sequences with different frequencies. Then the sub-sequences of different frequency components are predicted by using the improved GRU neural network, which uses the scaled exponential linear units(SELU) as the activation function to squash the hidden states to calculate the output. Finally, the output datum of GRU neural networks are reconstructed to obtain the complete wind power predicting results. Experiments illustrate that the WPD-GRU-SELU model have a more accurate forecast to the short-term wind power prediction compared with other RNN models.

Short-term wind power prediction using differential EMD and relevance vector machine

As a renewable energy source, wind turbine generators are considered to be important generation alternatives in electric power systems because of their nonexhaustible nature. With the increase in wind power penetration, wind power forecasting is crucially important for integrating wind power in a conventional power grid. In this paper, a short-term wind power output prediction model is presented from raw data of wind farm, and prediction of short-term wind power is implemented using differential empirical mode decomposition (EMD) and relevance vector machine (RVM). The differential EMD method is used to decompose the wind farm power to several detail parts associated with high frequencies [intrinsic mode function (IMF)] and an approximate part associated with low frequencies (r). Then, RVM is used to predict both the IMF components and the r. Finally, the short-term wind farm power is forecasted by summing the RVM-based prediction of both the IMF components and the r. Simulation results have shown that the proposed short-term wind power prediction method has good performance.