Wind Turbine Power Generation Research Articles

Wind-Mambaformer: Ultra-Short-Term Wind Turbine Power Forecasting Based on Advanced Transformer and Mamba Models

As global climate change accelerates and fossil fuel reserves dwindle, renewable energy sources, especially wind energy, are progressively emerging as the primary means for electricity generation. Yet, wind energy’s inherent stochasticity and uncertainty present significant challenges, impeding its wider application. Consequently, precise prediction of wind turbine power generation becomes crucial. This paper introduces a novel wind power prediction model, the Wind-Mambaformer, which leverages the Transformer framework, with unique modifications to overcome the adaptability limitations faced by traditional wind power prediction models. It embeds Flow-Attention with Mamba to effectively address issues related to high computational complexity, weak time-series prediction, and poor model adaptation in ultra-short-term wind power prediction tasks. This can help to greatly optimize the operation and dispatch of power systems. The Wind-Mambaformer model not only boosts the model’s capability to extract temporal features but also minimizes computational demands. Experimental results highlight the exceptional performance of the Wind-Mambaformer across a variety of wind farms. Compared to the standard Transformer model, our model achieves a remarkable reduction in mean absolute error (MAE) by approximately 30% and mean square error (MSE) by nearly 60% across all datasets. Moreover, a series of ablation experiments further confirm the soundness of the model design.

A bi-level optimization strategy of electricity-hydrogen-carbon integrated energy system considering photovoltaic and wind power uncertainty and demand response

To address the power supply-demand imbalance caused by the uncertainty in wind turbine and photovoltaic power generation in the regional integrated energy system, this study proposes a bi-level optimization strategy that considers the uncertainties in photovoltaic and wind turbine power generation as well as demand response. The upper-level model analyzes these uncertainties by modeling short-term and long-term output errors using robust optimization theory, applies an improved stepwise carbon trading model to control carbon emissions, and finally constructs an electricity-hydrogen-carbon cooperative scheduling optimization model to reduce wind and carbon emissions. The lower-level model incentivizes users to participate in integrated demand response through dynamic energy pricing, thereby reducing the annual consumption cost of load aggregator. The Karush-Kuhn-Tucker conditions and the Big-M method are used to solve the bi-level optimization model. Simulation results indicate that the improved carbon trading model reduces carbon emissions by approximately 40.12 tons per year, a decrease of 1.1%; the prediction accuracy of the short-term error model improves by 6.77%, and the prediction accuracy of the long-term error model improves by 15.16%; the electricity-hydrogen-carbon synergistic dispatch optimization model enhances the total profit of integrated energy system operator by 14.07% and reduces the total cost of load aggregator by 10.06%.

Lift-based offshore vertical-axis wind turbines for power generation: Current status of technology and future direction of numerical research

The vertical-axis wind turbines (VAWTs) are regarded as the best feasible alternative for small-scale power generation due to their design simplicity, ease of installation, good self-starting ability, and independency from wind direction among others. The dilemma of limited land, low onshore wind speed, and the abundance of high-speed wind near the ocean encouraged the researchers to explore the offshore fields. As a result, the lift-based VAWTs are becoming increasingly popular for large-scale offshore wind power production as well as small-scale urban applications. In the present review article, the historical evolution of lift-based offshore VAWTs from their inception to recent advancement has been discussed. The related geometrical and aerodynamic parameters, various loadings, and numerous models utilized in the design and analysis of offshore VAWTs have also been systematically reviewed. Finally, the challenges and the future scope of numerical research have been highlighted.

Validation of Electromechanical Transient Model for Large-Scale Renewable Power Plants Based on a Fast-Responding Generator Method

The requirements for accurate models of renewable energy power plants are urgent for power system operation analysis. Most existing model research in this area is for wind turbine and photovoltaic (PV) power generation units; a rare renewable power plant model validation mainly adopts the single-machine infinite-bus system. The single equivalent machine method is always used, and the interactions between the power plant and the grid are ignored. The voltage at the interface bus is treated as constant, although this is not consistent with its actual characteristics. The phase shifter method of hybrid dynamic simulation has been applied in the model validation of wind farms. However, this method is heavily dependent on phasor measurement units (PMU) data, resulting in a limited application scope, and it is difficult to realize the model error location step by step. In this paper, the fast-responding generator method is used for renewable power plant model validation. The complete scheme comprising model validation, error localization, parameter sensitivity analysis, and parameter correction is proposed. Model validation is conducted based on measured records from a large-scale PV power plant in northwest China. The comparison of simulated and measured data verifies the feasibility and accuracy of the proposed scheme. Compared to the conventional model validation method, the maximum deviation of the active power simulation values obtained by the method proposed in this paper is only 38.8% of that of the conventional method, and the overall simulation curve fits the actual measured values significantly better.

Catch the wind: Optimizing wind turbine power generation by addressing wind veer effects.

Wind direction variability with height, known as "wind veer," results in power losses for wind turbines (WTs) that rely on single-point wind measurements at the turbine nacelles. To address this challenge, we introduce a yaw control strategy designed to optimize turbine alignment by adjusting the yaw angle based on specific wind veer conditions, thereby boosting power generation efficiency. This strategy integrates modest yaw offset angles into the existing turbine control systems via a yaw-bias-look-up table, which correlates the adjustments with wind speed, and wind veer data. We evaluated the effectiveness of this control strategy through extensive month-long field campaigns for an individual utility-scale WT and at a commercial wind farm. This included controlling one turbine using our strategy against nine others in the vicinity using standard controls with LiDAR-derived wind veer data and a separate 2.5 MW instrumented research turbine continuously managed using our method with wind profiles provided by meteorological towers. Results from these campaigns demonstrated notable energy gains, with potential net gains exceeding 10% during extreme veering conditions. Our economic analysis, factoring in various elements, suggests an annual net gain of up to approximately $700 K for a 100-MW wind farm, requiring minimal additional investment, with potential for even larger gains in offshore settings with the power of individual turbines exceeding 10 MW nowadays. Overall, our findings underscore the considerable opportunities to improve individual turbine performance under realistic atmospheric conditions through advanced, cost-effective control strategies.

Loads and fatigue characteristics assessment of wind farm based on dynamic wake meandering model

Loads and fatigue characteristics assessment of wind farm based on dynamic wake meandering model

Global optimization of capacity ratios between electrolyser and renewable electricity source to minimize levelized cost of green hydrogen

This paper presents a novel and effective approach for calculating Levelized Cost of Hydrogen production across the globe, without requiring timely resolved modelling or data. We select characteristic production patterns of photovoltaic and wind turbine power generation based on location qualities indicated by full load hours. These representative patterns are applied worldwide on similar locations to evaluate the proportion of electricity that electrolyzers can use if they have a smaller capacity than the renewable electricity source. Hence, the ratio of capacities is optimized to minimize hydrogen cost. The findings from various worldwide locations reveal that decreasing electrolyzer capacity is economically beneficial across all locations for boosting full load hours and curbing investments, particularly in locations with lower electricity generation. Validation using precise electricity production timeseries in specific locations revealed minimal errors in the methodology, though the quality of the results is impacted by the seasonality index differences between representative and exact location.

Improved machine learning-based pitch controller for rated power generation in large-scale wind turbine

Improved machine learning-based pitch controller for rated power generation in large-scale wind turbine

Analysis of performance improvement methods for offshore wind turbine blades affected by leading edge erosion

Analysis of performance improvement methods for offshore wind turbine blades affected by leading edge erosion

Control of wind energy conversion systems with permanent magnet synchronous generator for isolated green hydrogen production

This paper addresses the design and analysis of the control system for a Wind Energy Conversion System (WECS) with a Permanent Magnet Synchronous Generator (PMSG) and its application for isolated green hydrogen production. The designed control maximizes the wind turbine (WT) power generation by regulating the electrolyzer current consumption, where the electrolyzer operates as a controlled load, ensuring power balance in the system and enabling the generation of maximum power from the WECS without the use of any energy storage system. The system involves directly integrating a WECS with an alkaline electrolyzer (AEL), and its configuration includes a WT with a PMSG, an AC/DC voltage source converter (VSC) acting as the generator side converter (GSC), and a DC/DC converter acting as the electrolyzer side converter (ESC) with Maximum Power Point Tracking (MPPT) control for the WT. The proposed control system has been fully modeled and tested through simulations in Matlab/Simulink, demonstrating its reliable performance under variable wind speeds. Simulation results illustrate how, over rated wind speeds, the pitch control limits the rotational speed and power to their maximum values, and at under rated wind speeds, the ESC control regulates the AEL current following the MPPT of the WT, while the GSC control maintains the DC bus voltage at its designated nominal value. Overall, the proposed control system shows robust and effective performance across the entire range of possible operational points, ensuring no wind generation power losses by following the maximum power point.

Multi-device wind turbine power generation forecasting based on hidden feature embedding

In recent years, the global installed capacity of wind power has grown rapidly. Wind power forecasting, as a key technology in wind turbine systems, has received widespread attention and extensive research. However, existing studies typically focus on the power prediction of individual devices. In the context of multi-turbine scenarios, employing individual models for each device may introduce challenges, encompassing data dilution and a substantial number of model parameters in power generation forecasting tasks. In this paper, a single-model method suitable for multi-device wind power forecasting is proposed. Firstly, this method allocates multi-dimensional random vectors to each device. Then, it utilizes space embedding techniques to iteratively evolve the random vectors into representative vectors corresponding to each device. Finally, the temporal features are concatenated with the corresponding representative vectors and inputted into the model, enabling the single model to accomplish multi-device wind power forecasting task based on device discrimination. Experimental results demonstrate that our method not only solves the data dilution issue and significantly reduces the number of model parameters but also maintains better predictive performance. Future research could focus on using more interpretable space embedding techniques to observe representation vectors of wind turbine equipment and further explore their semantic features.

An Approach to Improve Power System Resiliency in Grid-Connected Wind Turbine Generator Power System

An Approach to Improve Power System Resiliency in Grid-Connected Wind Turbine Generator Power System

Data-driven fault detection framework for offshore wind-hydrogen systems

Data-driven fault detection framework for offshore wind-hydrogen systems

Multidisciplinary design and optimization of journal bearing for high-power wind turbine speed increaser

Multidisciplinary design and optimization of journal bearing for high-power wind turbine speed increaser

Optimal sizing of standalone hybrid renewable energy system based on reliability indicator: A case study

Optimal sizing of standalone hybrid renewable energy system based on reliability indicator: A case study

Growth in turbine size and technological development of modern commercial large scale wind turbines in Türkiye

In this study, in addition to the recent advances and tendencies in wind turbine technology around the world, the progress of commercial wind turbine technology installed in Turkey was also thoroughly examined. In this respect, several metrics for installed wind turbines including number of turbines, installed power capacity (MW), mean rated capacity (MW), mean rotor diameter (m), mean specific power capacity (W/m2), and mean hub height (m) have been obtained between the years of 2011 and 2019. According to the obtained results, the mean rated capacity of Turkey’s annual installed wind turbines advanced from 1.86 MW in 2011 to 3.52 MW in 2019. However, the mean specific power of yearly installed wind turbines declined from 423.7 W/m2 to 314.1 W/m2. Outcomes revealed that the growth in the size and the reduction in the specific power have contributed to the tendency of higher power outputs, and wind turbine capacity factor and power generation capacity have been on the rise in Turkey. In time, wind turbines with greater rotor diameters and hubs started to show up more observable on land. For that purpose, the proposed solution to regulate turbine visibility during site selection is the potential visibility model (PVM), which is meant to be used as an auxiliary variable.

Optimal design of a renewable hydrogen production system by coordinating multiple PV arrays and multiple electrolyzers

Optimal design of a renewable hydrogen production system by coordinating multiple PV arrays and multiple electrolyzers

Fluid–Structure Interaction Simulations of Wind Turbine Blades with Pointed Tips

The aerodynamic shapes of the blades are of great importance in wind turbine design to achieve better overall turbine performance. Fluid–structure interaction (FSI) analyses are normally carried out to take into consideration the effects due to the loads between the air flow and the turbine structures. A structural integrity check can then be performed, and the structural/material design can be optimized accordingly. In this study, three different tip shapes are investigated based on the original blade of the test wind turbine (Phase VI) from the National Renewable Energy Laboratory (NREL). A one-way coupled simulation of FSI is conducted, and results with a focus on stresses and deformations along the span of the blade are investigated. The results show that tip modifications of the blade have the potential to effectively increase the power generation of wind turbines while ensuring adequate structural strength. Furthermore, instead of using more complicated but computationally expensive techniques, this study demonstrates an effective approach to making quality observations of this highly nonlinear phenomenon for wind turbine blade design.

Multi‐dimensional evaluation and diagnostic methods for wind turbine power generation performance based on different influencing factors

AbstractThe power generation performance of wind turbines has consistently been a paramount concern for wind power operators, maintainers, and manufacturers, as it directly determines the profitability of wind farms. However, due to the combined influence of complex environmental conditions within wind farms and inherent deficiencies in wind turbine design, significant variations in power generation performance persist among turbines of the same model. This discrepancy can be attributed to two crucial factors: site conditions and operational efficiency. To achieve more precise and systematic diagnostic work on the power generation performance of wind turbines, this paper focuses on three factors: air density, turbulence intensity, and yaw adaptability. Based on this, three evaluation and diagnosis methods are proposed, including a conversion method for air density based on two‐dimensional interpolation, a turbulence correction method based on the zero‐turbulence curve, and a yaw adaptability diagnosis method based on the convergence degree. Finally, the effectiveness of these proposed methods is verified through the analysis of actual wind field data.

Short-term prediction of the power generation of wind turbines.

Since the erection of the first wind turbine in Hungary in 2001, the proportion of power generated from wind has increased considerably, furthermore an even faster growth is expected in the next years. However, the more widespread use of wind energy plays a role in the fact that deviations from the international exchange schedule are becoming more frequent. In this paper we summarize the present situation concerning the usage of wind power in Hungary, detail the results and the limitations of our investigations carried out on the public data of the meteorological forecasts that are the primary sources of power generation schedules of wind power plants and suggest possible improvements on the reliability of the schedules based on the forecasts.