Accurate Wind Speed Prediction Research Articles

Quaternion convolutional long short-term memory neural model with an adaptive decomposition method for wind speed forecasting: North aegean islands case studies

An accurate prediction of short-term and long-term wind speed is necessary in order to integrate wind energy into large-scale grid power. However, wind speed presents diverse and complex seasonal and stochastic characteristics that impose challenges on wind speed forecasting models. This study proposes a Quaternion Convolutional Neural Network combined with a Bi-directional Long Short-Term Memory recurrent network to forecast wind speed. Quaternion Convolutional Neural Network is used to elicit more effective features from the stochastic sub-signals of wind speed. A new decomposition method is also proposed, comprising variational mode decomposition to decompose the wind speed data into optimal signal components, and an improved arithmetic optimisation algorithm to optimise the parameters of the variational mode decomposition. Furthermore, a fast and effective hyper-parameters tuner is introduced in order to adjust the hyper-parameters and architecture of the proposed hybrid forecasting model. The proposed forecasting model is developed based on data collected from Lesvos and Samothraki Greek islands located in the North Aegean Sea with the forecasting range in one-day ahead (long-term) and achieved considerable accuracy improvements in these case studies compared with the bi-directional long short-term memory model at 13% and 20%, respectively. The experimental outcomes confirm that, first, the proposed hybrid forecasting model considerably outperforms the five existing machine learning and two hybrid models in terms of precision and stability.

Robustified extreme learning machine regression with applications in outlier-blended wind-speed forecasting

Wind energy is a core sustainable source of electric power, and accurate wind-speed forecasting is pivotal to enhancing the power stability, efficiency, and utilization. The existing forecasting methods are still limited by the influence of outliers and the modelling difficulties caused by complex features in wind speed series. This paper proposes a new wind speed forecasting system based on a designed adaptive robust extreme learning machine (ARELM) model and signal decomposition algorithms. Firstly, the ARELM is designed to sufficiently lessen the violation of normality assumptions and contamination by outliers. ARELM takes an adaptive scaled Huber’s loss as its objective function, which can limit the influence of outliers and adaptively determine an appropriate mixture distribution of normal distribution and Laplace distribution at the same time. Secondly, the empirical mode decomposition (EMD) method and its improved methods (EEMD, CEEMD and CEEMDAN) are introduced to our wind-speed forecasting system, where the low-frequent sub-series are modelled by basic ELM and the high-frequent ones are modelled by ARELM. This can decompose the modelling complex wind speed series into modelling several simple sub-series and reduce the difficulty of modelling. Experimental results show that our combined forecasting system, ELM-ARELM, obtains up to 78% improvement in forecasting performance comparing with the methods using general Huber’s loss and other comparison methods, which show the superiority of the adaptive scaled Huber’s loss. The error indexes (MAE and RMSE) by the proposed system, which are (0.25, 0.34), (0.32, 0.45) and (0.38, 0.53) for 5 min head, 15 min ahead and 25 min ahead experiments respectively, demonstrate the effectiveness of decomposition methods on improving accuracy of wind speed prediction.

A novel offshore wind farm typhoon wind speed prediction model based on PSO–Bi-LSTM improved by VMD

Accurate typhoon wind speed prediction is significant because it enables wind farms to take advantage of high wind speeds and to simultaneously protect wind turbines from damage. However, the wind characteristics of the typhoon are highly random, fluctuating, and nonlinear, which makes precise prediction difficult. One-year wind data collected from a wind farm on the southeast coast of China are employed in the study. The characteristics of the typhoon are analyzed, and a sensitivity study is carried out by comparing two groups of training datasets. This study proposes a hybrid approach that considers both the physical model and the artificial neural network (ANN) model to accurately predict the short-term typhoon wind speed. The variational mode decomposition (VMD) algorithm is selected to decompose wind speed, and the particle swarm optimization (PSO) method is employed to optimize the bidirectional, long short-term memory (Bi-LSTM) prediction model. The results show that the proposed PSO-VMD-Bi-LSTM has strong robustness for making uncertainty predictions and can be utilized to predict the wind speed of typhoons. This study demonstrates the potential of an innovative ANN method to predict wind speed during the typhoon period.

Exploring Wind Speed for Energy Considerations in Eastern Jerusalem-Palestine Using Machine-Learning Algorithms

Wind energy is one of the fastest growing sources of energy worldwide. This is clear from the high volume of wind power applications that have been increased in recent years. However, the uncertain nature of wind speed induces several challenges towards the development of efficient applications that require a deep analysis of wind speed data and an accurate wind energy potential at a site. Therefore, wind speed forecasting plays a crucial rule in reducing this uncertainty and improving application efficiency. In this paper, we experimented with several forecasting models coming from both machine-learning and deep-learning paradigms to predict wind speed in a metrological wind station located in East Jerusalem, Palestine. The wind speed data were obtained, modelled, and forecasted using six machine-learning techniques, namely Multiple Linear Regression (MLR), lasso regression, ridge regression, Support Vector Regression (SVR), random forest, and deep Artificial Neural Network (ANN). Five variables were considered to develop the wind speed prediction models: timestamp, hourly wind speed, pressure, temperature, and direction. The performance of the models was evaluated using four statistical error measures: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R2). The experimental results demonstrated that the random forest followed by the LSMT-RNN outperformed the other techniques in terms of wind speed prediction accuracy for the study site.

A Deep Attention Convolutional Recurrent Network Assisted by K-Shape Clustering and Enhanced Memory for Short Term Wind Speed Predictions

Due to the increasing penetration of wind energy in nowadays power grids, the accurate wind speed prediction (WSP) is critical to more efficient and reliable operations of power systems containing wind turbines. This paper presents a novel deep attention convolutional recurrent network with K-Shape and enhanced memory (DACRN-KM) for more accurate short-term WSP. To well capture spatial-temporal information among wind speeds measured across the wind farm, a DACRN is firstly developed to extract latent representations. Next, an auto-updated memory module is developed to rebuild latent representations based on historical records. A K-shape clustering algorithm is applied to derive K patterns of rebuilt latent representations and the final prediction layer (FPL) is developed to generate the WSP result for latent representations assigned to one out of K patterns each time. The effectiveness of the proposed DACRN-KM is validated with data collected from 25 wind turbines (WTs) in multiple wind farms, in which a part of them is publicly accessible, by benchmarking against a set of the commonly considered and recently reported methods.

An Improved Mixture Density Network Via Wasserstein Distance Based Adversarial Learning for Probabilistic Wind Speed Predictions

This paper develops a novel improved mixture density network via Wasserstein distance-based adversarial learning (WA-IMDN) for achieving more accurate probabilistic wind speed predictions (PWSP). The proposed method utilizes the historical supervisory control and data acquisition (SCADA) system data collected from multiple wind turbines (WTs) in different wind farms to predict the wind speed probability density function (PDF) of a targeted WT at the next timestamp. To better capture the fluctuation pattern of historical wind speed sequences and estimate parameters of the probability mixture model for approximating the wind speed PDF, an improved mixture density network (IMDN) is proposed. To address drawbacks of the traditional maximum likelihood estimation (MLE) on training the mixture density network, a Wasserstein distance (WD)-based adversarial learning is developed and the reparameterization trick is employed for the gradient delivery. The effectiveness of the proposed WA-IMDN is validated based on SCADA data (One dataset is publicly accessible) by benchmarking against a set of the commonly considered and recently reported PWSP methods, such as the mixture density network (MDN), maximum likelihood estimation (MLE) based mixture density attention network (MLE-IMDN), recent DMDNN and Improved Deep Mixture Density Network (IDMDN). Results demonstrate the superior performance of the proposed WA-IMDN on the PWSP. To demonstrate the repeatability of the presented research, we release our code at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/IkeYang/WA-IMDN-</uri> .

A short-term wind speed interval prediction method based on WRF simulation and multivariate line regression for deep learning algorithms

The accurate wind speed prediction is of significant importance to decrease the adverse impact of wind randomness on the power systems and help wind power grid-tied. However, the previous studies mainly focus on the point forecast, and the uncertainties of the prediction accuracy have been ignored. Moreover, utilizing WRF numerous variables to construct wind speed prediction interval (PI) based on multivariate line regression theory has rarely been studied. Therefore, a novel wind speed PI method is proposed, including three modules: data collection, decomposition, and interval prediction. Specifically, various variables, such as wind speed, wind direction, temperature, pressure, and relative humidity, are first obtained from weather research and forecasting (WRF) simulation. Secondly, variational mode decomposition (VMD) is applied to decompose these variables and actual wind speed into respective intrinsic mode functions (IMFs). Lastly, generative adversarial network (GAN) captures temporal and spatial correlation features and realizes wind speed PI based on multivariate line regression theory. Four datasets are selected to verify the performance of the proposed model. The experimental results indicate that this novel model achieves better PI accuracy compared to several baseline methods. In the case of wind speed PI of dataset1, the PI normalized average width (PINAW) values improve by 49.53%, 15.21% over VMD-back propagation (BP), VMD-long short-term memory (LSTM) in the seventh-step prediction. In summary, the proposed model outperforms other comparative models due to the lower PINAW and coverage width-based criterion (CWC) with similar PI coverage probability (PICP).

A novel hybrid model for short-term prediction of wind speed

Due to the randomness and contingency of wind speed size and direction, it is difficult to predict the wind speed accurately, which seriously affects the stable operation of the power system. To improve the operation stability of power system, the accurate prediction of wind speed is very important. In this paper, a new hybrid model based on gray wolf algorithm (GWO) and support vector machine (SVM) for wind speed prediction is proposed. Firstly, Neo4j(NE) is utilized to identify the data and preprocess the data. Secondly, k-means clustering(KC) is utilized to analyze data and eliminate invalid data. Thirdly, GWO is utilized to optimize the kernel function parameters and penalty factors of SVM to improve the prediction results. Fourthly, The four modules are combined into NE-KC-GWO-SVM model to predict the wind speed accurately. Finally, to verify the effectiveness of the proposed model, the prediction accuracy of the model is experimentally analyzed from two parts. One is to analyze the superiority of the model itself by using the method of single model removed. The results show that the proposed model is the best, and has high accuracy, and can reflect the characteristics of wind speed well and truly. The other one is that models similar to those proposed in the literature are selected for comparative analysis. The experimental results show that compared with the other two models, the proposed model has the best accuracy. At the same time, the proposed model has good prediction stability and acceptable time complexity. Based on all the experimental results, it can be obtained that the proposed model has better prediction effect, which can provide a scientific basis for the macro-control of power system and improve the operation security and stability of power system.

A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting

The accuracy of the wind speed prediction is of crucial significance for the operation and dispatch of the power grid system reasonably. However, wind speed is so random and intermittent that the accuracy of wind speed prediction always remains unsatisfactory. Moreover, the coupling relationship between other meteorological variables and wind speed in the time and frequency domains has rarely been studied. Subsequently, a hybrid wind speed prediction model based on weather research and forecasting (WRF) simulation is proposed according to a multivariate data decomposition method and deep learning algorithm optimized by an attention mechanism and a grid search algorithm. Firstly, the WRF simulation is utilized to obtain the predicted wind speed and other meteorological variables are also extracted from WRF different domains. Furthermore, the pearson correlation coefficient (PCC) method is adopted to select principal meteorological variables as the input series. Additionally, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method decomposes input series and historical data into respective intrinsic mode functions (IMFs). Then, a new hybrid deep learning model, combining a convolutional neural network (CNN) and a bidirectional long short-term memory network (BLSTM) optimized via an attention mechanism (AM) and a grid search method (GS), is proposed to predict the error and correct the wind speed from WRF innermost domain. Finally, the validation case study is conducted to verify the effectiveness of the proposed model. The results indicate that the proposed model outperforms other comparative models in terms of single-step and multi-step wind speed prediction. Specifically, the values of the mean absolute error (MAE), the mean absolute percentage error (MAPE), and the root mean square error (RMSE) are 0.1042 m/s, 4.63% and 0.1309 m/s after correction, decreased by 94.13%, 91.75% and 93.93%, respectively, compared to those without correction.

An optimized complementary prediction method based on data feature extraction for wind speed forecasting

Wind speed prediction has a great significance to energy development. However, accurate wind speed prediction is a challenge owing to characteristics of wind series: randomness, fluctuation and nonlinearity. In this study, an optimized decomposed and ensemble multi-feature complementary forecasting method for wind speed is proposed, that mainly includes feature extraction and reconstruction, complementary prediction and nonlinear integration optimization. Firstly the Stacked Autoencoder (SAE) algorithm reconstructs characteristic series of wind speed sequence decomposed by the Variational Mode Decomposition (VMD), and then the Cuckoo Search (CS) algorithm finds weights of Linear Weighted Sum Method (LWSM) which integrates fitting results of the Support Vector Regression (SVR) and Bidirectional Long Short-term Memory (BiLSTM), finally the Bidirectional Gated Recurrent Unit (BiGRU) integrates the results of the Linear Weighted Sum Method, which corrects the errors of the complementary prediction results to optimize the prediction results. Two wind speed sequences are used to verify the proposed method obtained from Hexi Corridor area, China. Compared with other models, the model proposed in this paper has higher accuracy and stronger generalization ability than others.

Wind speed prediction based on CEEMD-SE and multiple echo state network with Gauss-Markov fusion.

The purpose of this study is to improve the prediction accuracy of wind speed. The wind speed has the characteristics of unstable, non-stationary, and non-linear, so it is difficult to predict the wind speed. This study proposes a prediction model based on the complementary ensemble empirical mode decomposition-sample entropy and multiple echo state network (ESN) with Gauss-Markov fusion for wind speed. The proposed prediction model consists of the following steps: (a) using the complementary ensemble empirical mode decomposition algorithm, it decomposes the initial wind speed time series and obtains some components with different scales, and (b) using the sample entropy algorithm, it determines the complexity of each component. The components whose entropy is larger than the original wind speed remain unchanged, while the components whose entropy is smaller than the original wind speed are merged into one. The reconstructed component greatly reduces the number of prediction models. (c) After reconstruction, the ESN has good regression prediction ability, so it is chosen as the prediction model of each component. The gray wolf optimization algorithm is introduced to optimize the parameters of the ESN. (d) The Gauss-Markov algorithm is adopted to fuse the predicted values of multiple ESN models. The variance of the predicted value obtained using the Gauss-Markov fusion is less than that of the single ESN model, which significantly increases the prediction accuracy. In order to verify the prediction performance of the proposed model, the actual ultra-short-term and short-term wind speed sample data are compared. At the same time, seven prediction models are chosen as the comparison model. Finally, through the comparison of the prediction error and its histogram distribution, eight performance indicators, Pearson's correlation coefficient, and Diebold-Mariano test, all the results show that the proposed prediction model has high prediction accuracy.

Predviđanje brzine vetra zasnovano na dugotrajnoj memoriji primenom nelinearne autoregresivne neuronske mreže

Globally, wind power is a technologically matured and commercially accepted technology. However, intermittent and fluctuating wind speed makes it difficult to connect it directly to the grid. It becomes less attractive from the quality and continuous power supply point of view. Nevertheless, the wind speed is affected by meteorological parameters like temperature, pressure, and relative humidity and may be predicted better using all of these parameters or some of the theses as inputs. Since the weather conditions of a particular month repeat approximately after ten years and sometimes even year to year depending on geographical location. This study investigates the errors associated with predicting the wind speed of a particular calendar month using the historical data of the same calendar month in the previous years. Authors propose a strategy for long-term prediction of wind speed based on two nonlinear autoregressive neural network models, (i) nonlinear autoregressive neural network and (ii) nonlinear autoregressive neural networks with exogenous inputs. The models are developed by training the networks with hourly mean wind speed values for seven years, from 2011 to 2017, for three sites in the Eastern Province of Saudi Arabia. These models are used to predict the wind speed for 2018, and the results are compared with the measured data. Both models' effectiveness is evaluated by considering the impact of the exogenous parameters (temperature and atmospheric pressure). The study found that the prediction accuracy of wind speed in long-term forecasting depends not only on the location but also on the repeatability of training samples across the years.

Short Term Wind Speed Prediction Based on VMD and DBN Combined Model Optimized by Improved Sparrow Intelligent Algorithm

Accurate wind speed prediction can help the power department to perceive the change rule of wind power in advance, reduce the impact of wind power grid connection, and then improve the wind power consumption rate. Therefore, an optimized variational modal decomposition (OVMD) method combined with optimized depth belief neural network (ODBN) is proposed to predict wind speed. First, the original wind speed data are processed by OVMD method, then the decomposed data are predicted by ODBN method, and the predicted component values are superimposed to obtain the wind speed prediction results. Taking the actual wind speed data of a certain area in Northwest China as an example, the proposed combined model is compared with common prediction methods such as DBN, long short term memory (LSTM), extreme learning machine (ELM), BP neural network, etc. The experimental results show that its RMSE decreases by 0.4494, 0.4778, 0.6217 and 0.6587, and its MAPE decreases by 10.3554%, 11.5484%, 14.6226% and 15.9493% respectively. The results verify the effectiveness of the prediction model.

Accurate Solar Wind Speed Prediction with Multimodality Information

When the solar wind passes over the Earth, it will cause geomagnetic storms, affect short-wave communications, and threaten the safety of pipelines such as electricity and oil. Accurate prediction of the solar wind speed will allow people to make adequate preparations to avoid wasting resources and affecting people’s life. Most existing methods only use single-modality data as input and do not consider the information complementarity between different modalities. This paper proposes a multimodality prediction (MMP) method that jointly learns vision and sequence information in a unified end-to-end framework for solar wind speed prediction. MMP includes three modules: Vmodule, Tmodule, and Fusion module. Vmodule, which uses pretrained GoogLeNet, is proposed to learn visual representations from the extreme ultraviolet (EUV) images. Tmodule combining one-dimensional CNN with bidirectional long short-term memory (BiLSTM) is applied for learning sequence representation from multivariate time series. Finally, a multimodality fusion method is applied to improve the overall performance. We adopt the EUV images observed by the solar dynamics observatory (SDO) satellite and the OMNIWEB dataset measured at Lagrangian point 1 (L1) to experiment. Comparative experiments have shown that the proposed MMP achieves best performance in many metrics. The ablation experiments also verify the validity of each module and the rationality of the hyperparameter setting.

Spatio-Temporal Wind Speed Prediction Based on Variational Mode Decomposition

Improving short-term wind speed prediction accuracy and stability remains a challenge for wind forecasting researchers. This paper proposes a new variational mode decomposition (VMD)-attention-based spatio-temporal network (VASTN) method that takes advantage of both temporal and spatial correlations of wind speed. First, VASTN is a hybrid wind speed prediction model that combines VMD, squeeze-and-excitation network (SENet), and attention mechanism (AM)-based bidirectional long short-term memory (BiLSTM). VASTN initially employs VMD to decompose the wind speed matrix into a series of intrinsic mode functions (IMF). Then, to extract the spatial features at the bottom of the model, each IMF employs an improved convolutional neural network algorithm based on channel AM, also known as SENet. Second, it combines BiLSTM and AM at the top layer to extract aggregated spatial features and capture temporal dependencies. Finally, VASTN accumulates the predictions of each IMF to obtain the predicted wind speed. This method employs VMD to reduce the randomness and instability of the original data before employing AM to improve prediction accuracy through mapping weight and parameter learning. Experimental results on real-world data demonstrate VASTN’s superiority over previous related algorithms.

Integrated framework of extreme learning machine (ELM) based on improved atom search optimization for short-term wind speed prediction

Wind energy plays an important role in terms of renewable energy. Accurate and reliable wind speed prediction is essential for effective use of wind energy. However, the uncertainty of wind speed becomes a challenging task. Aiming at these problems of wind speed prediction, this paper proposes a method based on variational mode decomposition (VMD), partial least squares (PLS), improved atom search optimization (IASO) and extreme learning machine (ELM). VMD is first employed to decompose the original wind speed data from high frequency to low frequency into multiple sub-series. Then this paper uses PLS for feature extraction and gets the best test set. And IASO is used to optimize the ELM to enhance the performance of the basic ELM model. The simulated annealing algorithm is added to the atom search optimization to enhance the local searchability. This paper employs the original wind speed data of the Sotavento Galicia wind farm in Spain as case study. Comparing results between the proposed model and the other benchmark models demonstrate the superiority of the proposed model in short-term wind speed prediction.

Long-term wind speed interpolation using anisotropic regression kriging with regional heterogeneous terrain and solar insolation in the United States

Wind speed is an important meteorological factor and is a parameter used to determine the air pollution assessment and the economic feasibility of wind energy as a renewable resource. In particular, the measurement of long-term average wind speed plays a role in the estimating of chronic exposure of air pollution and the siting of wind turbines; thus this study focuses on annual and monthly wind speed. However, due to spatially sparse and irregular meteorological stations, interpolation methods are used to predict unsampled areas. Therefore, the purpose of this study is to determine the optimal interpolation method among deterministic and geostatistical interpolation techniques. While most interpolation methods rely on spatial coverage and do not give an accurate characterization of small-area variations, cokriging and regression kriging (RK) can resolve the drawback by containing regional heterogeneity as auxiliary variables. In addition, this study applied isotropic and anisotropic approaches to geostatistical interpolations. This study showed that among the sampled methods, anisotropic RK with regional heterogeneous terrains and solar insolation was most likely to produce the best estimate for the highest accuracy for annual and monthly wind speeds with relatively unbiased spatial errors. In addition, while extreme wind speed decreases the accuracy of wind speed prediction, the number, range, and variance of observed wind speed significantly influence the accuracy of wind speed prediction.

Hybrid Deep Learning Model for Short-Term Wind Speed Forecasting Based on Time Series Decomposition and Gated Recurrent Unit

Accurate wind speed prediction has been becoming an indispensable technology in system security, wind energy utilization, and power grid dispatching in recent years. However, it is an arduous task to predict wind speed due to its variable and random characteristics. For the objective to enhance the performance of forecasting short-term wind speed, this work puts forward a hybrid deep learning model mixing time series decomposition algorithm and gated recurrent unit (GRU). The time series decomposition algorithm combines the following two parts: (1) the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and (2) wavelet packet decomposition (WPD). Firstly, the normalized wind speed time series (WSTS) are handled by CEEMDAN to gain pure fixed-frequency components and a residual signal. The WPD algorithm conducts the second-order decomposition to the first component that contains complex and high frequency signal of raw WSTS. Finally, GRU networks are established for all the relevant components of the signals, and the predicted wind speeds are obtained by superimposing the prediction of each component. Results from two case studies, adopting wind data from laboratory and wind farm, respectively, suggest that the related trend of the WSTS can be separated effectively by the proposed time series decomposition algorithm, and the accuracy of short-time wind speed prediction can be heightened significantly mixing the time series decomposition algorithm and GRU networks.

A Fast and Accurate Wind Speed and Direction Nowcasting Model for Renewable Energy Management Systems

To plan operations and avoid any grid disturbances, power utilities require accurate power generation estimates for renewable generation. The generation estimates for wind power stations require an accurate prediction of wind speed and direction. This paper proposes a new prediction model for nowcasting the wind speed and direction, which can be used to predict the output of a wind power plant. The proposed model uses perturbed observations to train the ensemble networks. The trained model is then used to predict the wind speed and direction. The paper performs a comparative assessment of three artificial neural network models. It also studies the performance of introducing perturbed observations to the model using six different interpolation techniques. For each technique, the computational efficiency is measured and assessed. Furthermore, the paper presents an exhaustive investigation of the performance of neural network types and several techniques in training, data splitting, and interpolation. To check the efficacy of the proposed model, the power output from a real wind farm is predicted and compared with the actual recorded measurements. The results of the comprehensive analysis show that the proposed model outperforms contending models in terms of accuracy and execution time. Therefore, this model can be used by operators to reliably generate a dispatch plan.

A novel reinforced online model selection using Q-learning technique for wind speed prediction

An accurate wind speed prediction is a fundamental prerequisite for enhanced wind energy integration with grid. Existing forecasting models are trained on the wind speed data. And these models rely on global accuracy without considering local variation of wind. Due to the local variation of wind, performance of each model varies for every time-step. As a result, this paper implements a robust and novel hybrid framework i.e. online model selection using Q-learning (OMS-QL) provided forecasting model pool (FMP). The proposed framework is the first model developed for online selection of best forecasting model dynamically using reinforcement learning (RL) approach. The proposed framework is mainly clustered into two parts: FMP, and Q-learning agent for online model selection. First, FMP is constructed using nine robust approaches, which are trained on the wind speed data. Then, Q-learning agent is developed to dynamically select the best prediction approach at every time-step for improved accuracy. Two experiments are conducted using the real-time wind speed datasets. Experimental results indicate that the proposed OMS-QL framework improved by 47% and 48% in both case studies compared to benchmark models.