Wind Speed Forecasting Research Articles

Navigating the Nexus of Artificial Intelligence and Renewable Energy for the Advancement of Sustainable Development Goals

The integration of artificial intelligence (AI) into renewable energy and sustainability represents a transformative approach toward achieving sustainable development goals (SDGs), especially SDG 7 (Affordable and Clean Energy), SDG 9 (Industry, Innovation, and Infrastructure), and SDG 13 (Climate Action). This study utilized the PRISMA framework to conduct a systematic review, focusing on the role of AI in renewable energy and sustainable development. This research utilized Scopus’s curated AI research area, which employs text mining to refine AI concepts into unique keywords. Further refinement via the All Science Journals Classification system and SDG-mapping filters narrowed the focus to publications relevant to renewable energy and SDGs. By employing the BERTopic modeling approach, our study identifies major topics, such as enhancing wind speed forecasts, performance analysis of fuel cells, energy management in elective vehicles, solar irradiance prediction, optimizing biofuel production, and improving energy efficiency in buildings. AI-driven models offer promising solutions to address the dynamic challenges of sustainable energy. Insights from academia-industry collaborations indicate that such partnerships significantly accelerate sustainable-energy transitions, with a focus on AI-driven energy storage, grid management, and renewable-energy forecasting. A global consensus on the critical role of investing in technology-driven solutions for energy sustainability was underscored by the relationship between funding data and global R&D spending patterns. This study serves as a resource for practitioners to harness AI technologies for renewable energy, where for example, AI’s accurate wind speed predictions can increase wind farm efficiency, highlighting the necessity of innovation and collaboration for sustainable development.

Imputation based wind speed forecasting technique during abrupt changes in short term scenario

AbstractIt is tough and complex to forecast wind speed due to its intermittent and stochastic nature as well as sudden and abrupt variations in the wind speed. Further, it is required to handle the variety of scenarios e.g. cyber‐attacks, unexpected power device malfunction, communication/sensor outages etc. that can cause the missing data.This paper proposes and employs a de‐noising autoencoder algorithm for wind speed forecasting to ensure the handling of missing data information. At the next step, the data is processed via variational mode decomposition technique to mitigate the noise and improves the model's prediction accuracy. Furthermore, the bi‐directional long‐short term memory deep learning approach is tied with convolution neural network to increase prediction accuracy and anticipating the sudden/abrupt changes in wind speed accurately. Finally, actual wind speed related data is examined to scrutinize meticulousness of projected forecast methodology particularly during sudden/abrupt changes in the wind speed. The parameter indicators of the wind speed forecasting technique exhibit the capability of improved predictions under the diversified conditions.

Hybrid wind speed optimisation forecasting system based on linear and nonlinear deep neural network structure and data preprocessing fusion

Wind speed time series forecasting has been widely used in wind power generation. However, the nonlinear and non-stationary characteristics of wind speed make accurate wind speed forecasting a difficult task. In recent years, the rapid development of artificial intelligence and machine learning technology provides a new solution to the problem of wind speed forecasting. Combining the advance of artificial intelligence and data analysis strategy, this paper proposes a wind speed forecasting system based on multi-model fusion and integrated learning. Considering the differences in data observation and training principles of various algorithms and exploiting the advantages of each model, a wind speed forecasting system with multiple machine learning algorithms embedded in integrated learning is constructed, which includes three modules: data preprocessing, optimization and forecasting. The data preprocessing module can conduct quantitative analysis through input data decomposition and feature extraction, and the combination of multi-objective intelligent optimization algorithm and combined forecasting method can effectively forecast the wind speed time series. The validity of the algorithm is verified using the data of Shandong wind farm in China. The forecasting results show that compared with the traditional single model forecasting, the proposed integrated wind speed forecasting system based on the fusion of multiple models has higher forecasting accuracy.

A novel hybrid model for multi-step-ahead forecasting of wind speed based on univariate data feature enhancement

Reliable multistep ahead wind speed forecasting (MAWSF) is critical for the energy management of wind farms and the long-term maintenance of wind power systems. However, relying on inherent meteorological features such as temperature and atmospheric pressure often fails to meet the deep learning model’s feature requirements for accurate wind speed forecasting (WSF). This paper introduces a hybrid multistep forecasting model that constructs a univariate wind speed feature enhancement framework, combining random forest (RF) and Transformer models for WSF. Initially, the hybrid enhancement framework decomposes the univariate wind speed data and extracts time-series features, effectively mining the latent features information. Subsequently, the RF feature selector filters out significant features contributing to WSF and eliminates redundant features to provide stable features data. Finally, Transformer model is utilized for both short-term and long-term MAWSF. This study conducted MAWSF on data with sampling intervals of 20 min, 30 min and 1 h. The results indicate that, compared to existing state-of-the-art models, the hybrid model in MAWSF tasks reduces the dependency of models on inherent meteorological features, achieving more accurate forecasting and faster computation speeds. Ultimately, the proposed model can provide reliable technical support for energy management and maintenance guidance in real-world wind farms.

Enhancing Surface Wind Speed and Temperature Prediction Using Surface-Layer Emulator and Transfer Learning

Abstract Accurate prediction of surface wind speed and temperature is crucial for many sectors. Physical schemes in numerical weather prediction (NWP) and data-driven correction approaches have limitations due to uncertainties in parameterization and lack of robustness, respectively. This study introduces a physics-informed data model, PhyCorNet, which combines a deep learning–based physics emulator (PhyNet) and a subsequent correction network (CorNet). PhyNet imitates the revised surface-layer parameterization scheme [default option of the Weather Research and Forecasting (WRF) Model]. CorNet refines predictions by mitigating the difference between PhyNet and observations. PhyCorNet enables gridded forecasts despite the training data being point based. Therefore, PhyCorNet can be regarded as a rediagnostic scheme for surface wind speed at 10 m (WS10) and temperature at 2 m (T2). Compared to WRF, it reduced diagnostic root-mean-square errors in the 24-h forecasts for WS10 and T2 by 40% and 36%, respectively, across China, with unbiased forecasts at almost all sites. PhyCorNet addresses the oversmoothing prediction issue of other deep learning models by providing the ability to represent fine-scale features and perform well in statistically extreme samples. In grid cells without observations for training, PhyCorNet performed much better than WRF, demonstrating the zero-shot learning capability. This study implies that the emulator plus bias correction provided by PhyCorNet could be used as a simple but effective approach to improve the performance of other diagnostic quantities in NWP. Significance Statement We developed a new model called PhyCorNet to improve the surface wind speed and temperature forecasts. Existing weather forecast models have limitations in accurately predicting these variables. PhyCorNet first uses a neural network (PhyNet) to mimic an existing physics-based wind and temperature calculation method. Another neural network [correction network (CorNet)] improves the PhyNet forecasts by comparing them with observations. Across China, PhyCorNet reduced 24-h forecast errors for wind speed by 40% and temperature by 36% compared to a conventional model. It performed well under diverse conditions and overcame the oversmoothing issues faced by other machine learning models. Importantly, PhyCorNet outperformed traditional models in areas without historical observations. We suggest that this new framework can also be used to enhance the forecasts of other atmospheric variables.

On the use of kolmogorov–arnold networks for adapting wind numerical weather forecasts with explainability and interpretability: application to madeira international airport

Abstract This study examines the application of machine learning to enhance wind nowcasting by using a Kolmogorov-Arnold Network model to improve predictions from the Global Forecast System at Madeira International Airport, a site affected by complex terrain. The research addresses the limitations of traditional numerical weather prediction models, which often fail to accurately forecast localized wind patterns. Using the Kolmogorov-Arnold Network model led to a substantial reduction in wind speed and direction forecast errors, with a performance that reached a 48.5% improvement to the Global Forecast System 3 h nowcast, considering the mean squared error. A key outcome of this study comes from the model’s ability to generate mathematical formulas that provide insights into the physical and mathematical dynamics influencing local wind patterns and improve the transparency, explainability, and interpretability of the employed machine learning models for atmosphere modeling.

Analyzing convolutional neural networks and linear regression models for wind speed forecasting in sustainable energy provision

Wind energy's significance lies in its contribution to electricity production. Accurate wind speed prediction is crucial for precisely forecasting electricity generation, enhancing its overall importance. For the wind speed prediction two methods are developed in this paper that are the Linear Regression Method and Convolutional Neural Networks (CNNs). Linear regression makes a linear relation between input and output which are used to predict continuous outcomes. The second proposed leverage hierarchical feature extraction through convolutional layers, enabling them to excel at tasks like pattern recognition by capturing spatial patterns and hierarchies of information. Hyperparameter tuning is applied on both the models to minimize the errors. Then both the model’s performances are compared under different error matrices including MAE, RMSE, MSE and MAPE. The observations indicate that both the Linear Regression Model and CNN models are capable of forecasting wind speed However, the Linear Regression Model after Hyperparameter tuning performs better in terms of the calculated errors.

Enhanced offshore wind resource assessment using hybrid data fusion and numerical models

Wind resource assessments are crucial for pre-construction planning of wind farms, especially offshore. This study proposes a novel hybrid model integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Empirical Wavelet Transform (EWT) for enhanced wind speed forecasting. This secondary decomposition reduces forecasting complexity by processing high-frequency signals. A Bidirectional Long Short-Term Memory (BiLSTM) neural network optimized with the Grey Wolf Optimizer (GWO) is then employed for forecasting. The model’s accuracy is evaluated using simulated wind speeds along the coast of Denmark, combined with lidar measurements through data fusion. This approach demonstrates significant improvements in prediction accuracy, highlighting its potential for offshore wind resource assessment.

Windformer: A novel 4D high-resolution system for multi-step wind speed vector forecasting based on temporal shifted window multi-head self-attention

Accurate wind speed forecasting (WSF) plays a pivotal role in anticipating the power output of wind farms. Nevertheless, the stochastic and variable nature of wind speed presents a significant challenge in achieving accurate WSF. Hence, this study proposes a novel 4D high-resolution system, Windformer, for wind speed vector forecasting (WSVF). Windformer combines the ability of convolutional neural networks (CNNs) for feature extraction and transformers based on attention mechanisms for information fusion. In the Windformer, the input and output layers are mainly composed of 3D CNNs. The input layer is employed for feature extraction and information compression, while the output layer is tasked with recovering the WSV field. The key components of the model consist of encoders and decoders built upon temporal shifted window multi-head self-attention. This architecture is capable of effectively integrating spatio-temporal information. Trained on 39 years of regional reanalysis data, Windformer obtains the most accurate forecast results compared to 5 WSF baseline models. Most importantly, within the next 6 hours, Windformer demonstrates higher accuracy compared to the High-Resolution Deterministic Forecast (HRES) from the European Centre for Medium-Range Weather Forecasts (ECMWF).

Enhanced prediction model of short-term sea surface wind speed: A multiscale feature extraction and selection approach coupled with deep learning technique

Accurate prediction of short-term sea surface wind speed is essential for maritime safety and coastal management. Most conventional studies encounter challenges simply in analyzing raw wind speed sequences and extracting multiscale features directly from the original received data, which result in lower efficiency. In this paper, an enhanced hybrid model based on a novel data assemble method for original received data, a multiscale feature extraction and selection approach, and a predictive network, is proposed for accurate and efficient short-term sea surface wind speed forecasting. Firstly, the received original data including wind speed are assembled into correlation matrices in order to uncover inherent associations over varied time spans. Secondly a novel Multiscale Wind-speed Feature-Enhanced Convolutional Network (MW-FECN) is designed for efficient and selective multiscale feature extraction, which can capture comprehensive characteristics. Thirdly, a Random Forest Feature Selection (RF-FS) is employed to pinpoint crucial characteristics for enhanced prediction of wind speed with higher efficiency than the related works. Finally, the proposed hybrid model utilized a Bidirectional Long Short-Term Memory (BiLSTM) network to achieve the accurate prediction of wind speed. Experimental data are collected in Weihai sea area, and a case study consist of five benchmarks and three ablation models is conducted to assess the proposed hybrid model. Compared with the conventional methods, experiment results illustrate the effectiveness of the proposed hybrid model and demonstrate effective balancing prediction accuracy and computational time. The proposed hybrid model achieves up to a 28.45% MAE and 27.27% RMSE improvement over existing hybrid models.

An Integrated CEEMDAN to Optimize Deep Long Short-Term Memory Model for Wind Speed Forecasting

Accurate wind speed forecasting is crucial for the efficient operation of renewable energy platforms, such as wind turbines, as it facilitates more effective management of power output and maintains grid reliability and stability. However, the inherent variability and intermittency of wind speed present significant challenges for achieving precise forecasts. To address these challenges, this study proposes a novel method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a deep learning-based Long Short-Term Memory (LSTM) network for wind speed forecasting. In the proposed method, CEEMDAN is utilized to decompose the original wind speed signal into different modes to capture the multiscale temporal properties and patterns of wind speeds. Subsequently, LSTM is employed to predict each subseries derived from the CEEMDAN process. These individual subseries predictions are then combined to generate the overall final forecast. The proposed method is validated using real-world wind speed data from Austria and Almeria. Experimental results indicate that the proposed method achieves minimal mean absolute percentage errors of 0.3285 and 0.1455, outperforming other popular models across multiple performance criteria.

Estimating the Wind Power by Using K-Nearest Neighbors (KNN) and Python

In recent years the production and distribution of renewable energy has become a popular trend in power generation, and renewable energy sources such as hydro, solar, and wind energy are examples of natural and clean energy sources. Among the renewable energy sources, wind energy source is one of the trending and crucial energy sources that has outstanding electricity power generation. This research investigates an estimation model of wind power to address the real-life issues in renewable energy power generation by estimating an accurate amount of wind power production by applying the machine learning (ML) K-Nearest Neighbors (KNN) technique integrated with Python programming. To achieve the expected outcome for this research, it is expected to collect data from wind energy, wind speed forecasts, and all the relevant information that supports the research in analyzing the technique. There are various meteorological methods to evaluate the performance of wind power generation, but in this research, the methodology is to employ machine learning techniques such as KNN integrated with Python coding to achieve estimated wind energy output. Python is a software program and is diversely used for coding various algorithmic formulas to obtain results. In this research, Python is best suited for investigating the performance of the KNN technique for estimating the most accurate result for wind power generation. Here, the report presents the methods of applying the KNN technique and displaying the outcome on screen by a graph representation. The outcome of the research showed that the KNN is a more reliable technique to make an accurate prediction on wind power generation. A similar approach can be implemented in various renewable energy data to estimate an accurate energy output.

Study on Downscaling Correction of Near-Surface Wind Speed Grid Forecasts in Complex Terrain

Accurate forecasting of wind speeds is a crucial aspect of providing fine-scale professional meteorological services (such as wind energy generation and transportation operations etc.). This article utilizes CMA-MESO model forecast data and CARAS-SUR_1 km ground truth grid data from January, April, July, and October 2022, employing the random forest algorithm to establish and evaluate a downscaling correction model for near-surface 1 km resolution wind-speed grid forecast in the complex terrain area of northwestern Hebei Province. The results indicate that after downscaling correction, the spatial distribution of grid forecast wind speeds in the entire complex terrain study area becomes more refined, with spatial resolution improving from 3 km to 1 km, reflecting fine-scale terrain effects. The accuracy of the corrected wind speed forecast significantly improves compared to the original model, with forecast errors showing stability in both time and space. The mean bias decreases from 2.25 m/s to 0.02 m/s, and the root mean square error (RMSE) decreases from 3.26 m/s to 0.52 m/s. Forecast errors caused by complex terrain, forecast lead time, and seasonal factors are significantly reduced. In terms of wind speed categories, the correction significantly improves forecasts for wind speeds below 8 m/s, with RMSE decreasing from 2.02 m/s to 0.59 m/s. For wind speeds above 8 m/s, there is also a good correction effect, with RMSE decreasing from 2.20 m/s to 1.65 m/s. Selecting the analysis of the Zhangjiakou strong wind process on 26 April 2022, it was found that the downscaled corrected forecast wind speed is very close to the observed wind speed at the station and the ground truth grid points. The correction effect is particularly significant in areas affected by strong winds, such as the Bashang Plateau and valleys, which has significant reference value.

Observations and Simulations of the Winds at a Bridge in Hong Kong during Two Tropical Cyclone Events in 2023

The impact of tropical cyclones on the operation of bridges and railways are mostly dependent on the forecast wind speed trend (upward, downward or staying steady) at present in Hong Kong. There are requests to forecast the exceedance of wind speed thresholds for such operations with a lead time of many hours ahead. This study considers the technical feasibility of forecasting the wind speed along a recently built bridge in Hong Kong with a coupled mesoscale numerical weather prediction (NWP)–computational fluid dynamics (CFD) model. This bridge features numerous anemometers where the coupled model can be verified. It is found that these two tropical cyclone cases are very challenging, especially in representing the wind structure of the cyclone because of its relatively small circulation. As such, the timing of the maximum wind could be 2 to 4 h earlier than the actual observation. The maximum wind speed from CFD modeling could be higher than that from the NWP model alone by 5 to 10 m/s, which shows that CFD modeling could add value in the forecasting of wind speed exceedance, although the maximum simulated value is still lower than the actual observation by as much as 10 m/s. As a result, while the general wind speed trend may be forecast, the exceedance of definite values of wind speed limits is still practically rather challenging, given the present two cases of tropical cyclones.

Forecasting Wind Speed Using Clustering of Trend-Based Time Series Data

Accurate forecasting of wind speed is crucial for the efficient operation of wind energy systems. As a time-series concern, wind forecasting may help determine how much electricity a proposed wind farm might produce annually. The majority of forecasting techniques perform differently depending on seasonal and trends variation. For this reason, time series data frequently have seasonal and nonlinear trend components eliminated in order to simplify wind forecasting approach. The application function used to remove the seasonality and trend determines accuracy. The proposed method begins by identifying and extracting underlying trends from historical wind speed data, segmenting the time series into distinct trend-based components. This paper proposes a hybrid method for predicting time series. A method for clustering data has been designed that identifies clusters of time series data with similar trend components. Statistical procedures, such as generalized autoregressive and autoregressive integrated moving average scoring approaches, are used to each individual cluster after the appropriate clusters of related trend components have been identified. Ultimately, the components that are made are combined. The datasets collected from the NREL site. The experiment demonstrates that when compared to current statistical approaches, the cluster-based forecasting approach performs better. This research makes contribution towards the field of renewable energy forecasting by providing a robust and scalable method for wind speed prediction, which can be integrated into existing energy management systems for improving the efficiency and stability of wind energy generation. The research paper examines the trend features of time series data of wind employing the suggested hybrid technique on wind forecasting. Performance calculated in terms of RMSE and MAE shows that the proposed technique succeeds as compared to other state of the art techniques.

Graph neural network incorporating time-varying frequency domain features with application in spatial wind speed field prediction

Precise forecasting of wind speed is vital to guarantee safe travel on bridges. Nevertheless, current research primarily concentrates on single-point prediction. When it comes to forecasting spatial wind fields, graph neural networks prove to be powerful methods, but many of them have yet to take into account the impact of frequency domain attributes. To address this, a novel model called the graph neural network with time-varying frequency features (GTF) is proposed. Its core layer employs wavelet transforms in matrix form to extract various frequency sub-series, followed by the use of adaptive adjacency matrices to identify their spatial characteristics. Furthermore, aggregating all frequency band information and exploring spatial features further through multi-kernel convolutions. The predictive performance of different models for wind speed forecasting is assessed by utilizing spatial wind field data collected on a large-span bridge. Experimental results demonstrate that spatiotemporal model GTF outperforms the other models in terms of predictive accuracy. The quantity of wind observation points and their level of correlation exert a certain impact on the GTF model, while hyperparameters such as stacking depth and wavelet decomposition parameters have minimal effects. Finally, recommended parameters for the GTF model are provided.

Evaluating Wind Speed Forecasting Models: A Comparative Study of CNN, DAN2, Random Forest and XGBOOST in Diverse South African Weather Conditions

The main source of electricity worldwide stems from fossil fuels, contributing to air pollution, global warming, and associated adverse effects. This study explores wind energy as a potential alternative. Nevertheless, the variable nature of wind introduces uncertainty in its reliability. Thus, it is necessary to identify an appropriate machine learning model capable of reliably forecasting wind speed under various environmental conditions. This research compares the effectiveness of Dynamic Architecture for Artificial Neural Networks (DAN2), convolutional neural networks (CNN), random forest and XGBOOST in predicting wind speed across three locations in South Africa, characterised by different weather patterns. The forecasts from the four models were then combined using quantile regression averaging models, generalised additive quantile regression (GAQR) and quantile regression neural networks (QRNN). Empirical results show that CNN outperforms DAN2 in accurately forecasting wind speed under different weather conditions. This superiority is likely due to the inherent architectural attributes of CNNs, including feature extraction capabilities, spatial hierarchy learning, and resilience to spatial variability. The results from the combined forecasts were comparable with those from the QRNN, which was slightly better than those from the GAQR model. However, the combined forecasts were more accurate than the individual models. These results could be useful to decision-makers in the energy sector.

Wind Speed Forecasting Based on Phase Space Reconstruction and a Novel Optimization Algorithm

The wind power generation capacity is increasing rapidly every year. There needs to be a corresponding development in the management of wind power. Accurate wind speed forecasting is essential for a wind power management system. However, it is not easy to forecast wind speed precisely since wind speed time series data are usually nonlinear and fluctuant. This paper proposes a novel combined wind speed forecasting model that based on PSR (phase space reconstruction), NNCT (no negative constraint theory) and a novel GPSOGA (a hybrid optimization algorithm that combines global elite opposition-based learning strategy, particle swarm optimization and the genetic algorithm) optimization algorithm. SSA (singular spectrum analysis) is firstly applied to decompose the original wind speed time series into IMFs (intrinsic mode functions). Then, PSR is employed to reconstruct the intrinsic mode functions into input and output vectors of the forecasting model. A combined forecasting model is proposed that contains a CBP (cascade back propagation network), RNN (recurrent neural network), GRU (gated recurrent unit), and CNNRNN (convolutional neural network combined with recurrent neural network). The NNCT strategy is used to combine the output of the four predictors, and a new optimization algorithm is proposed to find the optimal combination parameters. In order to validate the performance of the proposed algorithm, we compare the forecasting results of the proposed algorithm with different models on four datasets. The experimental results demonstrate that the forecasting performance of the proposed algorithm is better than other comparison models in terms of different indicators. The DM (Diebold–Mariano) test, Akaike’s information criterion and the Nash–Sutcliffe efficiency coefficient confirm that the proposed algorithm outperforms the comparison models.

A Short-Term Wind Speed Forecasting Framework Coupling a Maximum Information Coefficient, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, Shared Weight Gated Memory Network with Improved Northern Goshawk Optimization for Numerical Weather Prediction Correction

In line with global carbon-neutral policies, wind power generation has received widespread public attention, which can enhance the security of supply and social sustainability. Since wind with non-stationarity and randomness makes power systems unstable, precise wind speed forecasting is an integral part of wind farm scheduling and management. Therefore, a compound short-term wind speed forecasting framework based on numerical weather prediction (NWP) is proposed coupling a maximum information coefficient (MIC), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), shared weight gated memory network (SWGMN) with improved northern goshawk optimization (INGO). Firstly, numerical weather prediction is adopted to acquire the predicted variables with different domains, including the predicted wind speed and other predicted meteorological variables, after which the error is calculated using the predicted and actual wind speeds. Then, the correlation between the predicted variables and the error is obtained using the MIC to select the correlation factors. Subsequently, CEEMDAN is employed to decompose the correlation factors, corresponding the actual factors and the error into a series of subsequences, which are regarded as the input series. After that, the input series is fed into the proposed SWGMN to forecast each subsequent error, respectively, in which the shared gate is proposed to replace the input gate, the forgetting gate and the output gate. Meanwhile, the proposed INGO based on northern goshawk optimization (NGO), the levy flight disturbance strategy and the nonlinear contraction strategy is applied to calibrate the parameters of the SWGMN. Finally, the forecasting values are acquired by summing the forecasted error and the predicted wind speed from the NWP. The experimental results depict that the errors are small among all the models. Compared with the traditional method, the proposed framework achieves higher prediction accuracy and efficiency. The application of this framework not only assists in optimizing the operation and management of wind farms, but also reduces the dependence on fossil fuels, thereby promoting environmental protection and the sustainable use of resources.

STELLM: Spatio-temporal enhanced pre-trained large language model for wind speed forecasting

As a renewable and clean energy source, wind energy has caught worldwide attention. To ensure the reliability and stability of wind energy production, wind speed forecasting is of great importance. Although existing forecasting models have shown promising results, they remain relatively small in scale and are incapable of learning comprehensive sequential representations from large-scale data to reason intricate spatio-temporal patterns obscured in entangled wind series. Recently, pre-trained large models have demonstrated impressive performance in natural language processing (NLP) and computer vision (CV). However, large models are rarely applied to wind speed forecasting due to the lack of large-scale wind data for training. To resolve this issue, we propose Spatio-Temporal Enhanced Pre-Trained Large Language Model, namely STELLM, innovatively leveraging the powerful reasoning ability of Large Language Models (LLMs) for accurate wind speed forecasting. Specifically, we first perform the series decomposition to separate wind series data into seasonal and trend components, capturing the distinct properties from disentangled patterns. Then, to empower LLMs with the spatio-temporal modeling capability, we introduce the spatial and temporal prompts, which fuse the geographic distribution information and short-term temporal patterns of wind turbines to enrich the input wind series. Moreover, we leverage an autoregressive fine-tuning strategy to align LLMs with wind series data and learn patch-level representations. Afterwards these representations are fed into a localized spatial module to capture the spatial dependencies between wind turbines. Extensive experiments on four public wind datasets demonstrate the performance superiority of STELLM.