Search for: All records

Abstract Existing weather prediction products suffer from low spatiotemporal resolution, which fails to meet the requirements for fine-grained power forecasting and intelligent control of wind farms. This limitation adversely impacts wind turbine load management and the operational reliability of power systems. To tackle this, the study explores four-dimensional wind field superresolution, aiming to reconstruct high-resolution wind fields that fulfill both temporal and spatial resolution requirements through deep learning methods. The study emphasizes model architecture innovations to effectively capture the spatiotemporal coupling characteristics of wind field variations within wind farm regions. A novel model, termed 4dST-DMS, is proposed, comprising a spatial module and a temporal module, both built upon a 3D extension of the downsampled skip-connection/multi-scale framework as the backbone. Additionally, an iterative interpolation prediction method is proposed in the temporal module to extract multi-scale temporal information and capture dynamic variations, ensuring high fidelity in the reconstructed wind field. The proposed method is validated using the WTK-LED-5min dataset under experimental settings, including a 10-fold spatial resolution enhancement (both longitude and latitude), a 4-fold height resolution enhancement, and a 12-fold temporal resolution enhancement. The results demonstrate that the 4dST-DMS outperforms conventional interpolation methods and existing deep learning approaches in terms of numerical accuracy, vector field continuity and smoothness, structural similarity to real wind fields, and physical fidelity. 

Accurate and uncertainty-aware wind power forecasting is essential for reliable and cost-effective power system operations. This paper presents a novel probabilistic forecasting framework based on diffusion probabilistic models. We adopted a two-stage modeling strategy—a deterministic predictor first generates baseline forecasts, and a conditional diffusion model then learns the distribution of residual errors. Such a two-stage decoupling strategy improves learning efficiency and sharpens uncertainty estimation. We employed the elucidated diffusion model (EDM) to enable flexible noise control and enhance calibration, stability, and expressiveness. For the generative backbone, we introduced a time-series-specific diffusion Transformer (TimeDiT) that incorporates modular conditioning to separately fuse numerical weather prediction (NWP) inputs, noise, and temporal features. The proposed method was evaluated using the public database from ten wind farms in the Global Energy Forecasting Competition 2014 (GEFCom2014). We further compared our approach with two popular baseline models, i.e., a distribution parameter regression model and a generative adversarial network (GAN)-based model. Results showed that our method consistently achieves superior performance in both deterministic metrics and probabilistic accuracy, offering better forecast calibration and sharper distributions. 

Abstract Wind turbine reliability monitoring and prediction are crucial for early failure detection, proactive maintenance, performance optimization, and cost reduction, especially as many utility-scale turbines near the midpoint or end of their operational lifespan. We proposed a wind turbine subsystem reliability prediction model to facilitate week-ahead forecasts of the occurrence, duration, and type of potential failures or probability of downtime for major turbine components, including the blade, hub, gearbox, generator, inverter, electrical, and control subsystems. Specifically, we developed an Instance-Normalization Decomposition Linear (IN-DLinear) model, grounded in deep time-series modelling theory. The distribution shifts in turbine state features across the training, validation, and test datasets, as well as across various time scales, were effectively mitigated with IN. The long-term inertia in turbine state features was addressed by decomposing the input time-series data to effectively capture seasonality. The efficacy of IN-DLinear is systematically evaluated using 10-year field measurements from a 2.5-MW wind turbine. IN-DLinear exhibited superior performance, reducing prediction errors by 13%∼30% compared to mean value judgment and other deep time-series models, including Seq2Seq, Transformer, and Autoformer. 

A field campaign was carried out to investigate ice accretion features on large turbine blades (50 m in length) and to assess power output losses of utility-scale wind turbines induced by ice accretion. After a 30-h icing incident, a high-resolution digital camera carried by an unmanned aircraft system was used to capture photographs of iced turbine blades. Based on the obtained pictures of the frozen blades, the ice layer thickness accreted along the blades’ leading edges was determined quantitatively. While ice was found to accumulate over whole blade spans, outboard blades had more ice structures, with ice layers reaching up to 0.3 m thick toward the blade tips. With the turbine operating data provided by the turbines’ supervisory control and data acquisition systems, icing-induced power output losses were investigated systematically. Despite the high wind, frozen turbines were discovered to rotate substantially slower and even shut down from time to time, resulting in up to 80% of icing-induced turbine power losses during the icing event. The research presented here is a comprehensive field campaign to characterize ice accretion features on full-scaled turbine blades and systematically analyze detrimental impacts of ice accumulation on the power generation of utility-scale wind turbines. The research findings are very useful in bridging the gaps between fundamental icing physics research carried out in highly idealized laboratory settings and the realistic icing phenomena observed on utility-scale wind turbines operating in harsh natural icing conditions.