MGRU-LSTM Combined Model for Wind Speed Prediction

Research on short-term wind speed prediction based on deep learning model in multi-fan scenario of distributed generation

A novel hybrid model based on GA-VMD, sample entropy reconstruction and BiLSTM for wind speed prediction

Taiwan, being located on a path in the west Pacific Ocean where typhoons often strike, is often affected by typhoons. The accompanying strong winds and torrential rains make typhoons particularly damaging in Taiwan. Therefore, we aimed to establish an accurate wind speed prediction model for future typhoons, allowing for better preparation to mitigate a typhoon’s toll on life and property. For more accurate wind speed predictions during a typhoon episode, we used cutting-edge machine learning techniques to construct a wind speed prediction model. To ensure model accuracy, we used, as variable input, simulated values from the Weather Research and Forecasting model of the numerical weather prediction system in addition to adopting deeper neural networks that can deepen neural network structures in the construction of estimation models. Our deeper neural networks comprise multilayer perceptron (MLP), deep recurrent neural networks (DRNNs), and stacked long short-term memory (LSTM). These three model-structure types differ by their memory capacity: MLPs are model networks with no memory capacity, whereas DRNNs and stacked LSTM are model networks with memory capacity. A model structure with memory capacity can analyze time-series data and continue memorizing and learning along the time axis. The study area is northeastern Taiwan. Results showed that MLP, DRNN, and stacked LSTM prediction error rates increased with prediction time (1–6 hours). Comparing the three models revealed that model networks with memory capacity (DRNN and stacked LSTM) were more accurate than those without memory capacity. A further comparison of model networks with memory capacity revealed that stacked LSTM yielded slightly more accurate results than did DRNN. Additionally, we determined that in the construction of the wind speed prediction model, the use of numerically simulated values reduced the error rate approximately by 30%. These results indicate that the inclusion of numerically simulated values in wind speed prediction models enhanced their prediction accuracy.

Wind power is a popular renewable energy source, and the accurate prediction of wind speed plays an important role in improving the power generation efficiency of wind turbines and ensuring the normal operation of wind power equipment. Due to the instability and randomness of wind speed, it is difficult to achieve accurate prediction by traditional prediction methods. To improve the power generation efficiency of wind turbines and realize the predictability of wind speed, a hybrid wind speed prediction model based on GRUs (gated recurrent units) was constructed in this paper based on a deep neural network and feature extraction method. The hybrid model feature extraction module was implemented based on a combination of Tsfresh (a python package for time series feature extraction) and sparse PCA (sparse principal component analysis), and the network structure and other hyperparameters of the GRU module were determined through experiments. The model was validated using actual wind measurement data from a wind farm on the west coast of the United States. The results showed that the proposed model had less computational time and higher computational accuracy than the SARIMAX (seasonal auto-regressive integrated moving average with exogenous factors) and LSTM (long short-term memory) models.

Floating offshore wind turbines hold great potential for future solutions to the growing demand for renewable energy production. Thereafter, the prediction of the offshore wind power generation became critical in locating and designing wind farms and turbines. The purpose of this research is to improve the prediction of the offshore wind power generation by the prediction of local wind speed using a Deep Learning technique. In this paper, the future local wind speed is predicted based on the historical weather data collected from National Oceanic and Atmospheric Administration. Then, the prediction of the wind power generation is performed using the traditional methods using the future wind speed data predicted using Deep Learning. The network layers are designed using both Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM), known to be effective on capturing long-term time-dependency. The selected networks are fine-tuned, trained using a part of the weather data, and tested using the other part of the data. To evaluate the performance of the networks, a parameter study has been performed to find the relationships among: length of the training data, prediction accuracy, and length of the future prediction that is reliable given desired prediction accuracy and the training size.

The wind is a highly complex phenomenon that depends on geographical and environmental conditions. Wind speed depends on many variables such as temperature, pressure, humidity, and other lower atmospheric conditions, and thus mathematical modeling is highly complex and requires high computational power and time for wind speed prediction. Over the years, data-driven models for multi-step ahead time-series predictions have been gaining attention and are still in the evolutionary stage. Improvements in prediction models help the wind generation systems to operate efficiently. The accumulation of errors in the multi-step prediction creates a challenge in formulating novel prediction models. A prediction model based on long short-term memory (LSTM) is proposed in this study for short-term wind prediction up to a prediction horizon of 3 hours ahead. Hyperparameters of the LSTM model are tuned by Bayesian optimization. The wind speed data of two different sites are considered for the evaluation of the proposed model. Further, Support vector Regression based on the Multiple Input Multiple Output (MIMO) strategy is used to compare the performance of the proposed model. Bayesian optimized Long Short Term Memory (BO-LSTM) model shows nearly 30% and 16 % improvement in the MSE and RMSE scores, respectively, over the SVR model.

Combinations of physical and statistical wind speed forecasting models are frequently used in wind speed prediction problems arising in wind farms management. Artificial neural networks can be used in these models as a final step to obtain accurate wind speed predictions. The aim of this work is to determine the potential of evolutionary product unit neural networks (EPUNNs) for improving the accuracy and interpretation of these systems. Traditional neural network and EPUNN approaches have been used to develop different wind speed prediction models. The results obtained using different EPUNN models show that the functional model and the hybrid algorithms proposed provide very accurate prediction compared with standard neural networks used to solve this regression problem. One of the main advantages of the application of these EPUNNs has been the possibility of obtaining some interpretation of the non-linear relation predicted by the model, as will be shown in real data of a wind farm in Spain.

Accurate and stable wind speed prediction is crucial for the safe operation of large-scale wind power grid connections. Existing methods are typically limited to a certain fixed area when learning the information of the wind speed sequence, which cannot make full use of the spatiotemporal correlation of the wind speed sequence. To address this problem, in this paper we propose a new wind speed prediction method based on collaborative filtering against a virtual edge expansion graph structure in which virtual edges enrich the semantics that the graph can express. It is an effective extension of the dataset, connecting wind turbines of different wind farms through virtual edges to ensure that the spatial correlation of wind speed sequences can be effectively learned and utilized. The new collaborative filtering on the graph is reflected in the processing of the wind speed sequence. The wind speed is preprocessed from the perspective of pattern mining to effectively integrate various information, and the k-d tree is used to match the wind speed sequence to achieve the purpose of collaborative filtering. Finally, a model with long short-term memory (LSTM) as the main body is constructed for wind speed prediction. By taking the wind speed of the actual wind farm as the research object, we compare the new approach with four typical wind speed prediction methods. The mean square error is reduced by 16.40%, 11.78%, 9.57%, and 18.36%, respectively, which demonstrates the superiority of the proposed new method.

This paper presents systems and algorithms for the low-voltage ride-through control of wind power systems. The low-voltage ride-through (LVRT) requirement which is included in the grid-code regulates wind power systems to maintain their operation and supply reactive power during grid fault. When the grid fault arises some problems occur in wind power systems, such as over voltage and over current by transient conditions or surplus power. This paper proposes the LVRT strategy for a stable operation of wind power systems under the grid-fault condition. Proposed LVRT methods include a fault detection method, a design of dynamic braking resistor, and a flexible power control under various fault conditions. The simulation results show a validity of the proposed LVRT strategy with a 2-MW wind power system model.

Insufficient access and unreliable grid service are among emerging communities' most significant challenges. Consequently, these communities rely on fossil fuel-based technologies to provide for their electrical needs, resulting in substantial socioeconomic implications for society. Accurate and reliable wind speed forecasting is essential for effectively using wind energy, a Renewable Energy Source (RES) with considerable developing potential. Forecasting wind speed (FWS) is essential for the safe and effective operation of the power grid. Despite considerable study on various processing and validation methodologies, its application to realistic forecasting remains problematic due to the substantial influence of newly acquired data on the outcomes of the initial fragmented sub-sequences. A Long Short-Term Memory (LSTM) neural network-based model for wind speed prediction, validated by the A Day Ahead Chaining (ADAC) approach, has been proposed to address this problem. A FWS model using LSTM has been developed, ADAC has been implemented for validation, and a comparison study has been conducted to identify a superior methodology for application on bigger datasets, enhancing accuracy and forecasting efficiency. The proposed model emphasizes real-time data characterized by abrupt transitions and dependence on the wind speed.

Wind speed forecasting has great significance to the improvement of wind turbine intelligent control technology and the stable operation of power system. In this paper, the Long Short-term Memory (LSTM) mode combined with deep learning ability which with the fuzzy-rough set theory has been proposed for short-term wind speed prediction. Using the fuzzy-rough set to reduce input and space features firstly. Then find the main factors that influencing the wind speed as the input for the LSTM neural network prediction model. Finally achieve the forecast of data trends through the strong generalization ability on massive of data learning. The experimental results show that the FRS-LSTM model has higher prediction accuracy than traditional neural network.

Many countries around the globe, including Tanzania, are investing in renewable energy, partly because of the need to increase electric power generation and meet the ever-increasing electricity demands, and partly because of the need to combat global climate change caused by carbon emissions from fossil fuel-based electricity production. Kishapu Solar Project, located in Kishapu District, Shinyanga Region, Tanzania, is one of the renewable energy projects with a planned generation of 150 MW of electric power once completed, using solar photovoltaic technology. Accurate forecasting of solar radiation is important in managing and maintaining solar energy plants. Inaccurate forecasting of solar radiation can lead to poor harvest of solar energy and poor management of solar energy plants, which directly impacts electricity contribution to the national electricity grid. Long Short-Term Memory (LSTM) and its variant, PeepHole LSTM, are examples of Deep Learning models that can be used to predict solar radiation. The purpose of PeepHole LSTM is to introduce “peephole” connections in the LSTM model, which allow LSTM gates to directly inspect memory cell state and hence have richer information to process. However, there is still a research gap on the impact of “peephole” connections on the prediction performance of the LSTM model, especially in the context of forecasting solar radiation in Kishapu District, where the Kishapu Solar Project is located. The purpose of this study is to fill this research gap by developing both LSTM and PeepHole LSTM models and comparing their performances in forecasting solar radiation in Kishapu District. The 14-year Kishapu District daily solar radiation (Downward Shortwave Radiation) dataset was first pre-processed by scaling (normalizing) it using Standard Scaler and then split into training set (the first 70%), validation set (the next 15%) and test set (the last 15%) before being utilized to train and test the developed LSTM and PeepHole LSTM models. Both LSTM and PeepHole LSTM models used the previous 5 days' solar radiation values as inputs to predict the output (next day (6th day) solar radiation value). The trained and better-performing model between the two was finally saved in .h5 format and integrated with a Gradio based Web Application to provide a user interface for officials in Kishapu District and at Kishapu Solar Project to predict daily solar radiation. The findings from performance evaluation revealed that the LSTM model outperformed the PeepHole LSTM model in predicting solar radiation by achieving test Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) scores of 26.22 W/m2 and 36.65 W/m2, respectively, compared to MAE and RMSE scores of 30.84 W/m2 and 41.88 W/m2, respectively, achieved by the PeepHole LSTM model, concluding that “peephole” connections reduce the performance of the LSTM model rather than increasing it when used to forecast solar radiation in Kishapu District. This study’s recommendation to Artificial Intelligence (AI) software developers and researchers is to use the LSTM rather than the PeepHole LSTM Deep Learning model when forecasting solar radiation in Kishapu District and in locations with similar climatic conditions

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William & Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William & Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy. Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task. Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning. Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters. Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

Wind speed prediction with spatio–temporal correlation is among the most challenging tasks in wind speed prediction. In this paper, the problem of predicting wind speed for multiple sites simultaneously is investigated by using spatio–temporal correlation. This paper proposes a model for wind speed prediction with spatio–temporal correlation, i.e., the predictive deep convolutional neural network (PDCNN). The model is a unified framework, integrating convolutional neural networks (CNNs) and a multi-layer perceptron (MLP). Firstly, the spatial features are extracted by CNNs located at the bottom of the model. Then, the temporal dependencies among these extracted spatial features are captured by the MLP. In this way, the spatial and temporal correlations are captured by PDCNN intrinsically. Finally, PDCNN generates the predicted wind speed by using the learnt spatio–temporal correlations. In addition, three error indices are defined to evaluate the prediction accuracy of the model on the wind turbine array. Experiment results on real-world data show that PDCNN can capture the spatio–temporal correlation effectively, and it outperforms the conventional machine learning models, including multi-layer perceptron, support vector regressor, decision tree, etc.

Short‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting.