Wind Farm In China Research Articles

A day-ahead wind speed correction method: Enhancing wind speed forecasting accuracy using a strategy combining dynamic feature weighting with multi-source information and dynamic matching with improved similarity function

Forecasting error of day-ahead wind speed (WS) seriously affects wind power integration and power system security and stability. In this regard, this paper fully considers the spatiotemporal correlation of wind farms (WFs) in different geographical locations, and proposes a day-ahead WS combined correction method that integrates multi-source station dynamic information weighting. Different from the previous WS correction methods, this paper fully considers the dynamic correlation of WS between the WFs, introduces an improved weighted similarity function to screen and dynamically weight the information of WFs with dynamic correlation, and introduces the dynamic weighting feature into the WS correction process. A combined decomposition mechanism is proposed, which combines sequential variational mode decomposition (SVMD) and feature mode decomposition (FMD) models to extract the most relevant trend components and non-stationary components of forecasted and measured WS. A combined correction model is introduced, and a combined architecture of Non-stationary Transformer combined with bidirectional long short-term memory network (Ns-Transformer-BILSTM) is used to correct the stationary WS component. A dynamic matching mechanism of fluctuation components considering improved similarity is proposed for the correction of non-stationary components. The proposed method is applied to several regional WFs in China. The experimental results show that the average correction of NRMSE, NMAE and R can reach 2.4 % ∼ 3.7 %, 2.0 % ∼ 3.0 % and 3.3 % ∼ 9.7 %, respectively. The NRMSE and NMAE corresponding to the corrected WS of certain individual WFs can be reduced by 10 % and 9 %, respectively, and R can be increased by 33 %.

Hybrid wind speed optimization 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.

Identifying the spatio-temporal distribution characteristics of offshore wind turbines in China from Sentinel-1 imagery using deep learning

ABSTRACT Offshore wind power is a crucial clean energy source for coastal countries and advances blue economies. Accurate spatial mapping of offshore wind turbines supports energy assessment and the sustainable development of marine resources. Offshore wind power has developed rapidly in China, but the spatiotemporal distribution characteristics of offshore wind turbines and farms remain poorly understood. Extracting nearshore small targets from Sentinel-1 synthetic aperture radar images remain challenging due to noise from the rough sea surface background and the diverse substrate types in offshore wind turbine (OWT) distributions. Here, to address these issues, we first created a dataset of China’s offshore wind turbines (COWTs) that contained typical substrate types (e.g. seawater and tidal flats). Then, a deep learning model integrating an attention mechanism and receptive fields was used to accurately detect COWTs. The well-trained model was used to detect the changes in COWTs from 2015 to 2022. Our model detected an increase in the number of offshore wind farms in China from 7 to 114 (clusters counted as an offshore wind farm), while COWTs increased from 305 to 6451 from 2015 to 2022. The Taiwan Strait exhibited the highest wind speeds, yet the Jiangsu and Guangdong regions had the most installed turbines. Over 90% of COWTs were located in areas with offshore wind energy resources less than 500 W/m3, indicating a mismatch between COWT installation and wind resource distribution. This study demonstrated temporal and geographical generalizability, which is promising for global wind power detection. Our analysis of spatiotemporal variation in COWTs facilitates informed decision-making for future field establishment and sustainable marine planning.

Physics-informed reinforcement learning for probabilistic wind power forecasting under extreme events

With wind power penetration increases, accurate and reliable wind power forecasting is becoming gradually critical, and data driven model is a promising solution to implement this task. However, limited by deficient data samples under extreme conditions, scarcity of feature measurements fails to meet the number of training samples required, making the forecasting model exhibits low adaptability. This paper proposes a physics-informed reinforcement learning based method for probabilistic forecasting. Analytical physical expression of wind power output under extreme event is established to construct the error evaluation function for abrupt feature. Deep deterministic policy gradient-based quantile fitting model is then proposed, with abrupt feature embedded as the auxiliary input data for neural network. On this basis, parameter training technique under small data set is proposed to deal with the effect of extreme conditions on correction process of network. It extracts key historical transitions from experience replay pool to establish effective training samples, and model parameters are updated through the small-batch learning strategy to minimize long-term error feedback. Test result on the practical cold wave event of wind farms in China shows effectiveness of the proposed method.

The impact mechanisms of intermediate water depth on the coupled dynamic responses of large-capacity floating wind turbines

ABSTRACT The currently planned floating wind farms in China mostly have water depths in the intermediate range. Therefore, investigating the impact mechanisms of intermediate water depths on the coupled dynamic responses of floating wind turbines is of significant importance. In comparison to deep water, mooring systems in intermediate water depths are more prone to experiencing catenary shape loss and stiffness. The contribution of difference-frequency effects increases with decreasing water depth, resulting in a more substantial impact on low-frequency responses. The Full Quadratic Transfer Function (QTF) method accurately captures low-frequency responses. Placing clump weights in the bottom section of the mooring line effectively restricts the displacement range of floating turbines while maintaining average fairlead tensions at levels similar to the other two forms. On this basis, focusing on the most optimal mooring system performance, experiments were conducted to validate the coupled dynamic responses of floating wind turbines in intermediate water depths.

A novel wind power prediction method of the lower upper bound evaluation based on GRU

Compared with the point prediction of the wind power, the interval prediction provides more information to assist power dispatching and optimize quotation strategies in power trading. To improve the accuracy of the prediction intervals, this paper proposes a novel model based on the lower upper bound evaluation (LUBE) by the gate recurrent unit (GRU) network. First, the Pearson correlation coefficient is selected to screen out the variables related to wind power, which can simplify the input variables of the prediction model while preserving the feature information as much as possible. Afterwards, with the consideration of the prediction interval relative deviation ( PIRD), the improved objective function is introduced. Based on the GRU network, the prediction intervals of the wind power can be obtained to minimize the new objective function. Finally, by choosing several mainstream neural networks, experiments are conducted towards a certain wind farm in China. The results show that the proposed model has a significant improvement in both prediction interval width and PIRD under the given prediction interval coverage probability ( PICP).

Two-stage correction prediction of wind power based on numerical weather prediction wind speed superposition correction and improved clustering

The unavoidable wind power prediction error poses a challenge for wind power to participate in day-ahead scheduling plan. This paper proposes a two-stage correction method considering NWP wind speed and power correction. Firstly, this paper fully considers the historical similarity of NWP wind speed, and adopts the improved clustering distance for segment matching and wind speed correction based on the extracted most relevant trend component, which enhances the utilization of NWP information and avoids the randomness and uncertainty of the intelligent correction method, and gram angular field (GAF) and stacked autoencoder (SAE) are used for feature extraction and conditional variational autoencoder (CVA) is used to generate specific samples to ensure the adequacy of the clustering process. Secondly, considering the historical similarity of error of predicted power, the power is further corrected based on the proposed weighted double-constraint to realize the secondary calibration. The Proposed method is applied to several wind farms in China to verify its effectiveness. The results show that the proposed method reduces the NRMSE by 3.82 % and NMAE by 3.40 % compared with direct prediction in the wind farms in western Inner Mongolia, which is important for promoting wind power consumption and maintaining the safe and stable operation of the power system.

A pyramidal residual attention model of short‐term wind power forecasting for wind farm safety

AbstractWind power fluctuation significantly impacts the safe and stable operation of the wind farm power grid. As the installed capacity of grid‐connected wind power expands to a certain threshold, these fluctuations can detrimentally affect the wind farm's operations. Consequently, wind power prediction emerges as a critical technology for ensuring safe, stable and efficient wind power generation. To optimize power grid dispatching and enhance wind farm operation and maintenance, precise wind power prediction is essential. In this context, we introduce a joint deep learning model that integrates a compact pyramid structure with a residual attention encoder, aiming to bolster wind farm operational safety and reliability. The model employs a compact pyramid architecture to extract multi‐time scale features from the input sequence, facilitating effective information exchange across different scales and enhancing the capture of long‐term sequence dependencies. To mitigate vanishing gradients, the residual transformer encoder is applied, augmenting the original attention mechanism with a global dot product attention pathway. This approach improves the gradient descent process, making it more accessible without introducing additional hyperparameters. The model's efficacy is validated using a dataset from an actual wind farm in China. Experimental outcomes reveal a notable enhancement in wind power prediction accuracy, thereby contributing to the operational safety of wind farms.

Cyclic response of laterally loaded pile after storm loading

Offshore wind farms in China are in tropical cyclone zones, where typhoons or tropical revolving storms will pass through every year and can produce huge loads on the offshore wind turbines. Therefore, the stability of OWT foundations after storm loading is critical to ensure the safe operation and design life of turbines. While monopile is the most used foundation type for offshore wind, little studies exist on the cyclic response of monopile after storm loading. To fill the gap, this study presents a unique centrifuge and numerical study on the cyclic deflection response of monopile in medium dense sand after extreme storm loading. The centrifuge test was performed at 100g on a typical monopile with a prototype diameter (D) and embedded depth (L) of 4 m and 60 m, respectively. Finite element (FE) simulations using the advanced hypoplastic model for sand were performed to back-analyze the centrifuge test and provide further insights into the test results. From the centrifuge test, a unique “self-healing” beahviour of monopile was observed for the first time, where the foundation exhibited a deflection recovery response and tilted back to its initial position under the small amplitude cyclic load after the storm loading. This “self-healing” beahviour was also replicated by the FE model. By looking into the computed pile-soil interaction and soil element states around the pile, it was found that the “self-healing” response is attributed to the “lock-in” bending moment after the storm loading. This “lock-in” bending moment generated significant compressive horizontal stress on the soil elements behind the pile and produced more compressive strain under cyclic loading. As a result, the pile exhibited the “self-healing” response and tilted back against the loading direction.

Event-Triggered Federated Learning for Fault Diagnosis of Offshore Wind Turbines With Decentralized Data

Rapid developments of offshore wind industry offer a strong demand opportunity for offshore wind turbine remote diagnosis. As offshore wind turbines are often located in harsh and communication-constrained environments, the collection and transmission of data is severely restricted, which poses a serious challenge to the conventional centralized diagnostic paradigm that relies on data aggregation. To address this challenge, we propose a novel event-triggered federated learning framework for decentralized fault diagnosis of offshore wind turbines. Specifically, federated learning is first employed to learn decentralized local knowledge from geographically distributed offshore wind turbines, so that the communication objects are transformed from massive raw data into learned parameters, thereby relieving the communication burden. Then, we design an event-triggered communication mechanism and incorporate it into federated learning, the core of which is to modify the communication requirement from uploading all trained parameters periodically to communicating only when necessary. The proposed framework is verified by a real-world offshore wind turbine dataset from six large wind farms in China. An ablation study shows that the proposed framework can maintain high diagnostic performance while reducing communication costs. A comprehensive comparison based on three benchmark models demonstrates that the proposed framework can reduce the communication burden by up to 63% while obtaining better diagnostic performance. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This study was motivated by the problem of collaborative diagnosis of distributed offshore wind turbines under the constraints of data privacy and communication overhead. The method employs a federated learning-based fault diagnosis framework, which permits to obtain global fault diagnosis knowledge without aggregating raw data scattered in each end device, thus avoids the risk of data leakage. Moreover, a strategy integrating parameter variation and accuracy gain is designed to avoid communication redundancy for collaborative training. The practicability and superiority of our proposed framework is demonstrated using extensive experiments against actual industrial data collected from six offshore wind farms.

Life cycle environmental analysis of offshore wind power: A case study of the large-scale offshore wind farm in China

China's decarbonization is indispensable for the large-scale utilization of renewable energy. In this process, the development of offshore wind energy has become an important support, because in the eastern region of China, especially the coastal areas, there's the most load requirements but limited onshore renewable resources. Under the goals of both carbon neutral and sustainable development, however, there's still a research gap in evaluating the environmental impacts of large-scale offshore wind plants in China. In this study, the research performed a comprehensive process-based life cycle environmental analysis of a large-scale (400 MW) offshore wind farm with large wind turbine units (5 MW) in China. Global Warming Potential is 25.73 g CO2-eq/kWh and greenhouse gas payback time is calculated as 12.05 months. Fossil fuel consumption amounts to 0.31 MJ/kWh with an energy payback period of 25.56 months. Material resources and ecotoxicity to freshwater need more attention with the values of 1.68 CTUe/kWh and 3.32 10−6 kg Sb-eq/kWh, respectively. The manufacturing stage contributes most to all the impacts examined. The disposal and recycling process shows significant environmental benefits for most impacts but exerts burdens on the particulate matter. Focusing on Global Warming Potential, the wind turbine generation set has the highest effect, among which the blades contribute 73.2% of it. Further, the evolution of electricity and heating mix of China and use of biomass-based precursors could decrease 57% of the blades' greenhouse gas emissions in 2050. This study could provide guidance on the sustainable design and policy-making of offshore wind farms.

A combined interval prediction system based on fuzzy strategy and neural network for wind speed

Wind energy exhibits strong fluctuations and intermittencies. The accurate prediction of wind speed is of considerable significance for the operation and maintenance of wind farms and the safety of the power grid. However, previous studies have often ignored the impact of data noise on trend prediction, and lacked effective data pre-processing methods and adaptive interval prediction schemes, resulting in poor prediction results. To improve the accuracy of prediction, this paper proposes a wind-speed combination interval prediction system based on a fuzzy strategy and neural network. This study used a fuzzy strategy to pre-process the data and proposed a joint optimization algorithm that uses multiple multi-objective metaheuristic algorithms to optimize the neural network jointly. An improved prediction hybrid algorithm was used to reconstruct the predicted results. Finally, based on the fuzzy theory and neural network, interval prediction schemes that can adapt to different situations were proposed. Wind-speed data from the Penglai Wind Farm in China were used for verification. The mean absolute percentage error of the wind-speed point prediction was 3.75%, and the prediction interval coverage probability of the wind-speed interval prediction was 97.92%. The experimental results showed that the proposed model not only outperforms other comparable models but also improves the prediction interval coverage probability by 176.4% compared with the baseline model. This proves that the integrated hybrid model can improve the accuracy and effectiveness of wind-speed prediction. The accurate interval prediction of wind speed can result in the complementary scheduling of renewable energy generation and the sustainable development of the energy field, and support intelligent upgrades.

Research on Evaluation Method of Wind Farm Wake Energy Efficiency Loss Based on SCADA Data Analysis

The large size of wind turbines and wind farm clustering aggravate the effect of wake on output power, resulting in a reduction in the economic benefits of wind farms. This paper took the actual operating turbines of an onshore wind farm in China as the research object and analyzed the influence of wake on energy efficiency loss by combining SCADA data. The research established a complete loss assessment method and proposed the corresponding evaluation criteria. The results showed that typical wind turbines seriously affected by wake accounted for 32.8% of the wind farm. The actual output power was only 84.2% of the theoretical output power at the lowest month, and the wake loss of the wind farm is serious. The economic efficiency of the wind farm is lower in the summer months (June–August). The study can provide a theoretical basis for the arrangement of wind farms and the development of an operation control strategy.

An ultra-short-term wind power prediction method based on spatial-temporal attention graph convolutional model

Accurate and robust wind power forecasting (WPF) is great significance to ensure the safe and stable operation of the power system and promote the transformation of low-carbon energy. However, the high randomness and intermittency of wind power bring great challenges when designing reliable forecasting models. In this paper, a novel spatial-temporal attention graph convolutional network model is proposed. Firstly, the spatial attention mechanism is used to aggregate and extract the spatial correlations of the raw wind power data. Secondly, the temporal attention mechanism is applied to capture the temporal correlations. Then, the extracted spatial-temporal correlations were put into the temporal convolution network and the spatial convolution network to further obtain the temporal and spatial dependencies. Finally, the wind power forecasting results is output through the full connection layer. The proposed method is verified by using wind power data from real wind farm in China. The experimental results reveal that the proposed depth spatiotemporal prediction model has more significant advantages than other advanced models in terms of prediction accuracy and stability.

Study on Meso-Structural Evolution of Bedrock Beneath Offshore Wind Turbine Foundation in Pressurized Seawater

In recent years, offshore wind turbine technology has been widely developed, making a significant contribution to the advancement of renewable energy. Due to the predominant subsurface geological composition characterized by rocky formations in some marine areas, rock-socketed piles are commonly applied as offshore wind turbine foundations. Generally, rock-socketed piles need to be driven into rock layers that have not undergone significant weathering or erosion for optimal load-bearing capacity. This design is essential to ensure structural support for offshore wind turbines. However, during the long-term operation period of offshore wind turbines, the contact surface between the rock-socketed pile and the rock is prone to be detached under multiple dynamic loads. The generated channel makes seawater seep into the unweathered rock layer, resulting in the erosion of rock meso-structure and deterioration of mechanical properties. The reduced load-bearing capacity will adversely affect the operation of the offshore wind turbine. In this study, the meso-structural evolution of bedrock in pressurized seawater is investigated by X-ray CT imaging using tuff samples from the marine areas of an offshore wind farm in China. A cellular automata model is proposed to predict the long-term evolutionary process of tuff meso-structure. Results indicate that the porosity of the tuff sample in the pressurized seawater shows an upward trend over time. Based on the erosion rate of pores obtained from the CT scanning test, the proposed cellular automata model can predict the evolutionary process of tuff meso-structure and corresponding failure strength of the bedrock in the long term.

Numerical and experimental analysis of blade-tower clearance for large-scale wind turbines

With the increase of the rotor diameter and the flexibility of the blade, the efficient blade-tower clearance control becomes increasingly important. As a widely used strategy in the wind power industry to increase the blade-tower clearance, the fine pitch strategy still has the problem of power de-rating under typical operating conditions. Therefore, a novel coupled blade-tower clearance control strategy is proposed, combining the fine pitch strategy with a revised LiDAR monitoring system. Incorporating the LiDAR's characteristics and the operation modes of wind turbines, the LiDAR is designed to be installed at the front of the nacelle to monitor the real-time blade-tower clearance and feed back to adjust the pitch angle, allowing for safe operation of the wind turbine and maximizing output power. The reliability of the proposed strategy and the influence of weather on the strategy are verified through 22-day all-weather field tests on numerous wind turbines in a wind farm in China, nearly 100% of the efficiency can be achieved if conditions permit. Additionally, the strategy’s two trigger modes—the clearance threshold and data validity protection mechanism—are exemplified, demonstrating the efficiency of the proposed coupled blade-tower clearance control strategy.

Analysis of variable system cost and maintenance strategy in life cycle considering different failure modes

Due to the complexity of multi-component systems, components failure modes are intricate. The failure modes lead to maintenance behavior combinations, which lead to a series of maintenance strategies. However, the failure modes of components are mixed in multi-component systems. Few researchers provide component failure modes comprehensively in life cycle, and integrate them into life cycle maintenance strategies for the selection schemes of different phases. In this paper, a variable system cost methodology in life cycle is studied, and maintenance strategies are developed by identifying components failure modes from a life cycle perspective to improve system reliability. One of the keys is determining maintenance behaviors for components in each phase of life cycle. The proposed four failure modes cover all possible failure scenarios of the components in different phases. Then, a selection scheme is developed to determine maintenance behaviors in life cycle. At last, a case of Huaneng wind farm in China is given to demonstrate the proposed method by comparing with a baseline maintenance strategy.

Vibration prediction of offshore wind turbines based on long short-term memory network

ABSTRACT Offshore wind turbines (OWTs) have complex operating conditions and are prone to accidents. Timely and accurate vibration prediction can reduce the probability of failure of OWTs. To address this issue, this study proposed a vibration prediction model based on long short-term memory (LSTM) network. The proposed prediction model was applied to an OWT in an offshore wind farm in China, and three evaluation indicators, i.e. mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), were used to verify the vibration prediction performance of LSTM. The results demonstrated that the prediction accuracy of LSTM was better than that of back propagation (BP) neural network, and LSTM had optimum engineering practicability. The prediction accuracy of LSTM and BP neural networks decreased with an increase in prediction durations. However, the prediction accuracy of LSTM was higher. This study improves the online safety monitoring of OWTs.

Short-Term Wind Power Forecasting Based on VMD and a Hybrid SSA-TCN-BiGRU Network

Wind power generation is a renewable energy source, and its power output is influenced by multiple factors such as wind speed, direction, meteorological conditions, and the characteristics of wind turbines. Therefore, accurately predicting wind power is crucial for the grid operation and maintenance management of wind power plants. This paper proposes a hybrid model to improve the accuracy of wind power prediction. Accurate wind power forecasting is critical for the safe operation of power systems. To improve the accuracy of wind power prediction, this paper proposes a hybrid model incorporating variational modal decomposition (VMD), a Sparrow Search Algorithm (SSA), and a temporal-convolutional-network-based bi-directional gated recurrent unit (TCN-BiGRU). The model first uses VMD to break down the raw power data into several modal components, and then it builds an SSA-TCN-BIGRU model for each component for prediction, and finally, it accumulates all the predicted components to obtain the wind power prediction results. The proposed short-term wind power prediction model was validated using measured data from a wind farm in China. The proposed VMD-SSA-TCN-BiGRU forecasting framework is compared with benchmark models to verify its practicability and reliability. Compared with the TCN-BiGRU, the symmetric mean absolute percentage error, the mean absolute error, and the root mean square error of the VMD-SSA-TCN-BiGRU model reduced by 34.36%, 49.14%, and 55.94%.

Fault detection in wind turbine generators using a meta-learning-based convolutional neural network

Conventional fault detection methods for wind turbine (WT) generators often grapple with inadequate warning times and poor portability. These issues contribute to heightened safety risks and an increased false positive rate (FPR) and false negative rate (FNR). This study introduces a fault detection method for WT generators utilizing a 1D convolutional neural network (1DCNN) based on meta-learning principles. We incorporate the ”learning to learn” concept of model-agnostic meta-learning (MAML) into a 1DCNN, enabling effective fault detection. More specifically, the training data are transformed into numerous tasks through random sampling, and the model is trained task by task. The 1DCNN is utilized as the base learner, leveraging its superior feature extraction capability to discern task features. The first-order gradient of MAML is applied to ascertain the specific initialization parameters for each task, while the second-order gradient of MAML is used to understand the similarities and differences between all tasks’ initialization parameters. This approach equips the 1DCNN-MAML with the ability to adapt to new tasks and converge rapidly, thereby achieving swift regression prediction. We also employ the probability distribution fitting method to analyze the distribution of prediction residuals, thus setting the detection threshold. Based on this threshold, warnings can be issued for faults in WT generators. We used supervisory control and data acquisition (SCADA) data from the Liaoning wind farm in China to validate the robustness and portability of the proposed model. Experimental outcomes indicate that, compared with Reptile, FOMAML, LSTM-MAML, 1DCNN, and LSTM, our proposed method can detect faults earliest across different wind turbines and has the lowest FPR and FNR.