Search Results (83)

Wind farm performance monitoring has traditionally relied on deterministic models, such as power curves or machine learning approaches, which often fail to account for farm-wide behavior and the uncertainty quantification necessary for the reliable detection of underperformance. To overcome these limitations, we propose a probabilistic methodology for turbine-level active power prediction and uncertainty estimation using high-frequency SCADA data and farm-wide autoregressive information. The method leverages a Stochastic Variational Gaussian Process with a Linear Model of Coregionalization, incorporating physical models like manufacturer power curves as mean functions and enabling flexible modeling of active power and its associated variance. The approach was validated on a wind farm in the Belgian North Sea comprising over 40 turbines, using only 15 days of data for training. The results demonstrate that the proposed method improves predictive accuracy over the manufacturer’s power curve, achieving a reduction in error measurements of around 1%. Improvements of around 5% were seen in dominant wind directions (200°–300°) using 2 and 3 Latent GPs, with similar improvements observed on the test set. The model also successfully reconstructs wake effects, with Energy Ratio estimates closely matching SCADA-derived values, and provides meaningful uncertainty estimates and posterior turbine correlations. These results demonstrate that the methodology enables interpretable, data-efficient, and uncertainty-aware turbine-level power predictions, suitable for advanced wind farm monitoring and control applications, enabling a more sensitive underperformance detection. Full article

Power system stability (PSS) refers to the capacity of an electrical system to maintain a consistent equilibrium between the generation and consumption of electric power. In this paper, the PSS is evaluated for a “hybrid power plant” (HPP) which combines thermal, wind, solar photovoltaic (PV), and hydropower generation in Niigata City. A new method for estimating its PV power generation is also introduced based on NHK (the Japan Broadcasting Corporation)’s cloud distribution forecasts (CDFs) and land ratio settings. Our objective is to achieve frequency stability (FS) while reducing CO₂ emissions in the power generation sector. So, the PSS is evaluated according to the results in terms of the FS variable. Six-minute autoregressive wind speed prediction (6ARW) support is used for wind power (WP). One-hour GPV wind farm (1HWF) power is computed from the Grid Point Value (GPV) wind speed prediction data. The PV power is predicted using autoregressive modelling and the CDFs. In accordance with the daily power curve and the prediction time, we can support thermal power generation planning. Actual data on wind and solar are measured every 10 min and 1 min, respectively, and the hydropower is controlled. The simulation results for the electricity frequency fluctuations are within ±0.2 Hz of the requirements of Tohoku Electric Power Network Co,. Inc. for testing and evaluation days. Therefore, the proposed system supplies electricity optimally and stably while contributing to reductions in CO₂ emissions. Full article

Accurate load prediction is critical for boosting high-quality electricity use, as well as safety in energy and power systems. However, the power system is fraught with uncertainty, and cyber-attacks on electrical loads result in inaccurate estimates. In this study, a probability density prediction method is proposed to provide reliable predictions in the face of false data injection (FDI) attacks. The method effectively integrates data-driven and statistical algorithms such as double-layer long short-term memory (DL-LSTM) networks, quantile regression (QR), and kernel density estimation (KDE). To acquire predicted values under diverse conditional quartiles, the FDI-attacked data of different types were first simulated and then utilized as the training set for the QR-DL-LSTM model. A probability density curve was drawn using the Gaussian kernel function, and interval estimates were used to more thoroughly analyze and assess predictive capability. Power load data from a wind farm in northeast China were used to confirm the availability and effectiveness of the QR-DL-LSTM model. The final results show that the proposed model has a 1.13 and 0.26 reduction in MAPE and MSE compared to the original LSTM. According to our research, the suggested model can successfully describe future power systems full of possible risks and uncertainties with great accuracy. Full article

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. Full article

In this study, we investigate a yaw control strategy in a two-turbine wind farm with 3.5 MW turbines, aiming to optimize power management. The wind farm is equipped with a nacelle-mounted multi-plane LiDAR system for wind speed measurements. Using an analytical model and integrating LiDAR and SCADA data, we estimate wake effects and power output. Our results show a 2% power gain achieved through optimal yaw control over a year-long assessment. The wind predominantly blows from the southwest, perpendicular to the turbine alignment. The optimal yaw and power gain depend on wind conditions, with higher turbulence intensity and wind speed leading to reduced gains. The power gain follows a bell curve across the range of wind inflow angles, peaking at 1.7% with a corresponding optimal yaw of 17 degrees at an inflow angle of 12 degrees. Further experiments are recommended to refine the estimates and enhance the performance of wind farms through optimized yaw control strategies, ultimately contributing to the advancement of sustainable energy generation. Full article

The southeastern rock base sea area is the most abundant wind resource area, and it is also the mainstream construction site of offshore wind farms (OWFs) in China. The weathered residual soil is the main seabed component in the rock base area, which is the important bearing stratum of the offshore wind turbine foundation. Previous studies on the mechanical properties of seabed materials and bearing characteristics of the pile foundations in OWFs have mainly focused on the submarine soil-based seabed, resulting in a lack of direct reference for the construction of offshore wind power in the rocky seabed. Therefore, the mechanical properties of weathered residual soil and the bearing behaviors of monopile foundations are mainly investigated in this study. Firstly, dynamic triaxial tests are conducted on the weathered residual soil, and experiments analyze insight into the evolution law of the hysteresis curve, cumulative strain, and stiffness attenuation. Then, the horizontal loading behaviors of monopile foundations in residual soil are analyzed by numerical simulations; more critically, the service performances under wind and wave coupling loads are evaluated, which provide a direct theoretical basis for the construction and design of offshore wind turbine foundations in rock base seabeds. Full article

Power output from wind turbines is influenced by wind speed, but the traditional theoretical power curve approach introduces uncertainty into wind energy forecasting models. This is because it assumes a consistent power output for a given wind speed. To address this issue, a new nonparametric method has been proposed. It uses K-means clustering to estimate wind speed intervals, applies kernel density estimation (KDE) to establish the probability density function (PDF) for each interval and employs Monte Carlo simulation to predict power output based on the PDF. The method was tested using data from the MERRA-2 database, covering five wind farms in Brazil. The results showed that the new method outperformed the conventional estimation technique, improving estimates by an average of 47 to 49%. This study contributes by (i) proposing a new nonparametric method for modeling the relationship between wind speed and power; (ii) emphasizing the superiority of probabilistic modeling in capturing the natural variability in wind generation; (iii) demonstrating the benefits of temporally segregating data; (iv) highlighting how different wind farms within the same region can have distinct generation profiles due to environmental and technical factors; and (v) underscoring the significance and reliability of the data provided by the MERRA-2 database. Full article

The wind power curve serves as a critical metric for assessing wind turbine performance. Developing a model based on this curve and evaluating turbine efficiency within a defined health region, derived from the statically optimized power curve, holds significant value for wind farm operations. This paper proposes an optimized wind power curve segmentation modeling method based on an improved PCF algorithm to address the inconsistency between the function curve and the wind power curve, as well as the issues of prolonged curve modeling training time and susceptibility to local optima. A health region optimization method based on data increment inflection points is developed, which enables the delineation of the health performance evaluation region for wind turbines. Through the aforementioned optimization, the performance evaluation method for wind turbines is significantly improved. The effectiveness of the performance evaluation method is validated through experimental case studies, combining the wind power curve with the rotational speed stability, power characteristic consistency coefficient, and power generation efficiency indicators. The proposed modeling technique achieves a precision level of 0.998, confirming its applicability and effectiveness in practical engineering scenarios. Full article

Offshore wind power stands as a prime exemplar of high-end technological innovation in the renewable energy sector and is poised to be one of the high-growth industries of the future. In this study, a static mechanics and fatigue characteristic curve approach was utilized, employing both Abaqus and Fe-safe for the simulation analysis of the braced foundation transition sections in an offshore wind farm project in Shantou, Guangdong. The analysis revealed vulnerabilities in the stiffener plates and base plates of the transition sections. By increasing the thickness of the stiffener plates and adding sub-beams to the base plates, the structural stress was effectively reduced by 10–50%, thus ensuring the safety and suitability of the turbines. This provides a reference for the design of similar engineering transition sections. Full article

The development and utilization of clean energy is becoming more extensive, and wind power generation is one of the key points of this. Occasionally, wind turbines are faced with various extreme environmental impacts such as icing, lightning strikes and so on. In particular, the icing of wind turbines increases icing–wind loads, and results in a reduced power output. And blades broken down lead to large-area shutdown accidents caused by high-speed rotating, which seriously affects the reliability and equipment safety of wind power generation. Relevant institutions and researchers at home and abroad have carried out a lot of research on this. This paper summarizes the formation and influencing factors of wind turbine icing, the influence of icing on wind power generation, and defense technologies. First, it introduces the formation conditions and mechanisms of icing in wind farm regions and the relationship between meteorological and climatic characteristics and icing, and analyzes the key influence factors on icing. Then, the impact of icing on wind turbines is explained from the aspects of mechanical operation, the power curve, jeopardies and economic benefits. And then the monitoring and safety status of wind turbines icing is analyzed, which involves collecting the relevant research on anti-de-icing in wind power generation, introducing various anti/de-icing technologies, and analyzing the principle of icing defense. Finally, this paper summarizes wind turbine icing and its defense technologies, and puts forward the future research direction based on the existing problems of wind power generation icing. Full article

As the power market system gradually perfects, the increasingly fierce competition not only drives industry development but also brings new challenges. Reactive power optimization is crucial for maintaining stable power grid operation and improving energy efficiency. However, the implementation of plant–grid separation policies has kept optimization costs high, affecting the profit distribution between power generation companies and grid companies. Therefore, researching how to effectively reduce reactive power optimization costs, both technically and strategically, is not only vital for the economic operation of the power system but also key to balancing interests among all parties and promoting the healthy development of the power market. Initially, the study analyzes and compares the characteristic curves of synchronous generators and DFIGs, establishes a reactive power pricing model for generators, and considering the randomness and volatility of wind energy, establishes a DFIG reactive power pricing model. The objective functions aimed to minimize the cost of reactive power purchased by generators, the price of active power network losses, the total deviation of node voltages, and the depreciation costs of discrete variable actions, thereby establishing a dynamic reactive power optimization model for power systems including doubly-fed wind farms. By introducing Logistic chaotic mapping, the CSA is improved by using the highly stochastic characteristics of chaotic systems, which is known as the Chaotic Cuckooing Algorithm. Meanwhile, the basic cuckoo search algorithm was improved in terms of adaptive adjustment strategies and global convergence guidance strategies, resulting in an enhanced cuckoo search algorithm to solve the established dynamic reactive power optimization model, improving global search capability and convergence speed. Finally, using the IEEE 30-bus system as an example and applying the improved chaotic cuckoo search algorithm for solution, simulation results show that the proposed reactive power optimization model and method can reduce reactive power costs and the number of discrete device actions, demonstrating effectiveness and adaptability. When the improved chaotic cuckoo algorithm is applied to optimize the objective function, the optimization result is better than 7.26% compared to the standard cuckoo search algorithm, and it is also improved compared to both the PSO algorithm and the GWO algorithm. Full article

Accurately predicting the active power output of offshore wind power is of great significance for reducing the uncertainty in new power systems. By utilizing the spatiotemporal correlation characteristics among wind turbine unit outputs, this paper embeds the Diffusion Convolutional Neural Network (DCNN) into the Gated Recurrent Unit (GRU) for the feature extraction of spatiotemporal correlations in wind turbine unit outputs. It also combines graph structure learning to propose a sequence-to-sequence model for ultra-short-term power prediction in large offshore wind farms. Firstly, the electrical connection graph within the wind farm is used to preliminarily determine the reference adjacency matrix for the wind turbine units within the farm, injecting prior knowledge of the adjacency matrix into the model. Secondly, a convolutional neural network is utilized to convolve the historical curves of units within the farm along the time dimension, outputting a unit connection probability vector. The Gumbel–softmax reparameterization method is then used to make the probability vector differentiable, thereby generating an optimal adjacency matrix for the prediction task based on the probability vector. At the same time, the difference between the two adjacency matrices is added as a regularization term to the loss function to reduce model overfitting. The simulation of actual cases shows that the proposed model has good predictive performance in ultra-short-term power prediction for large offshore wind farms. Full article

Accurate power curve modeling is essential to continuously evaluate the performance of a wind turbine (WT). In this work, we characterize the wind power curves using SCADA data acquired at a frequency of 5 min in a wind farm (WF) consisting of five WTs. Regarding the non-parametric methods, we select artificial neural networks (ANNs) to make curve estimations. Given that, we have the curves provided by the manufacturer of the WTs given by some very precisely measured pair of wind speed and power points. We can evaluate the difference between the manufacturer characterization and the ones estimated with the data provided by the SCADA system. Before the estimation, we propose a method of filtering the anomalies based on the characteristics provided by the manufacturer. We use three-quarters of the available data for curve estimation and one-quarter for the test. One WT suffered a break in the test part, so we can check how the test estimates reflect this problem in its wind-power curve compared to the estimations obtained in the WTs that worked adequately. Full article

Wakes between neighboring wind turbines are a significant source of energy loss in wind farm operations. Extensive research has been conducted to analyze and understand wind turbine wakes, ranging from aerodynamic descriptions to advanced control strategies. However, there is a relatively overlooked research area focused on characterizing real-world wind farm operations under wake conditions using Supervisory Control And Data Acquisition (SCADA) parameters. This study aims to address this gap by presenting a detailed discussion based on SCADA data analysis from a real-world test case. The analysis focuses on two selected wind turbines within an onshore wind farm operating under wake conditions. Operation curves and data-driven methods are utilized to describe the turbines’ performance. Particularly, the analysis of the operation curves reveals that a wind turbine operating within a wake experiences reduced power production not only due to the velocity deficit but also due to increased turbulence intensity caused by the wake. This effect is particularly prominent during partial load operation when the rotational speed saturates. The turbulence intensity, manifested in the variability of rotational speed and blade pitch, emerges as the crucial factor determining the extent of wake-induced power loss. The findings indicate that turbulence intensity is strongly correlated with the proximity of the wind direction to the center of the wake sector. However, it is important to consider that these two factors may convey slightly different information, possibly influenced by terrain effects. Therefore, both turbulence intensity and wind direction should be taken into account to accurately describe the behavior of wind turbines operating within wakes. Full article

Wind energy is a growing industry in Canada to meet the demand for a renewable supply of energy. However, wind turbine operation represents a high mortality risk for bat populations, and regulators often require that steps are taken to mitigate this risk. The result is concern among operators about lost revenue potential. This study was, therefore, designed to estimate the theoretical financial impact of curtailing turbine operations to mitigate for bat mortality for all wind farms that were constructed and operating in Ontario, Canada, as of 1 January 2020 (n = 87 wind farms). Empirical data from the Canadian Wind Farm SCADA and meteorological systems are not publicly available; thus, we were compelled to use data from the Canadian Wind Turbine database, the Environment and Climate Change Canada Wind Atlas, and the Independent Electricity System Operator to calculate the total theoretical energy production for all wind turbines in the province using manufacturer power curves and a measure–correlate–predict linear regression method. We estimated the financial impacts for all wind farms on the assumption that operations were curtailed when the Wind Atlas modelled local wind speed was <5.5 m/s between 6 pm of one day and 6 am the following day, between 15 July and 30 September, using the lower and upper limits of power-purchase agreement rates for Ontario wind farms: 115 and 150 CAD/MWh. We used generalized linear modelling to test whether the variability in production loss was predicted based on factors related to turbine design and site wind speeds. We estimated that total annual wind energy production would be reduced from 12.09 to 12.04 TWh if all Ontario wind farms implemented operational curtailment, which is equivalent to a difference of 51.2 GWh, or 0.42%. Production loss was related to turbine cut-in speeds and average site wind speeds recorded between 15 July and 30 September. The estimated profit losses were 6.79 ± 0.9 million CAD compared to estimated earnings of 1.6 ± 0.21 billion CAD, which suggests that mitigating bat mortality may represent a small cost to the industry relative to the conservation benefits for bat populations. Full article