New Stochastic Model for One-Month-Ahead Wind Power Forecasting Shows Promising Accuracy
Researchers developed a probabilistic framework using Weibull-stationary stochastic differential equations to forecast wind power one month ahead at ten-minute resolution. The method combines Kalman filtering of wind-speed parameters with three different SDE models, ultimately selecting a computationally efficient diffusion-first approach. The model achieved energy-yield errors below 7.3% and exceedance-probability errors under 2.2 percentage points, providing decision-relevant forecasts for wind farm operations.
A new conditional probabilistic forecasting framework for wind power uses Weibull-stationary stochastic differential equations to predict power generation one month in advance at ten-minute intervals. The approach estimates monthly Weibull distribution parameters from SCADA wind-speed data, applies Godambe covariance corrections, and forecasts these parameters using a heteroskedastic Kalman filter on a bivariate VAR(1) state-space model. Three positive wind-speed SDE models were constructed and compared: an Ornstein-Uhlenbeck-Weibull transform, a Fokker-Planck drift-first diffusion, and a Fokker-Planck diffusion-first model. When tested on January 2021 data from a Senvion MM92 turbine at Kelmarsh Wind Farm, all three formulations showed statistically indistinguishable probabilistic accuracy with mean CRPS values between 1.569 and 1.575 m/s. The diffusion-first model was selected for deployment due to a seven-fold computational speedup, while maintaining Wasserstein distances of 26.1-27.6 kW (below 1.4% of rated capacity) between simulated and observed power distributions.
What's missing
The study acknowledges that full marginalization over the Kalman predictive law of Weibull parameters remains as a natural extension, suggesting this represents a limitation of the current framework. The authors note their results provide probabilistic inputs for operational decisions rather than completed optimization solutions for reserve, storage, market, or fatigue management. Testing was limited to a single turbine and one month of data, which may affect generalizability to other turbines, wind farms, or seasonal conditions.
What different sources said
- arXiv physicsCenter
Weibull-Stationary Stochastic Differential Equations for Conditional Long-Horizon Wind Power Forecasting
Related
Genetic Drift, Not Selection, Drives Rapid Feather Color Evolution in Island Bird Radiation
A new study of an island bird radiation found that rapid evolution of feather coloration is driven primarily by genetic drift in small populations rather than sexual or ecological selection. The research integrated whole-genome data with detailed plumage measurements across complete species sampling to test whether signaling trait evolution correlates with speciation rates. The findings suggest that neutral demographic processes play a central role in generating phenotypic diversity during island radiations, challenging assumptions about the mechanisms driving rapid evolution.
New AI Model Improves Prediction of Therapeutic Peptide Function from Protein Sequences
Researchers developed a lightweight CNN classifier that predicts whether peptide sequences have therapeutic properties, trained on a database of 54,655 peptides across 48 functional categories. The model uses a novel negative sampling strategy to reduce false positive rates from over 60% in previous approaches to 2.1%. This advancement could accelerate drug discovery by enabling faster computational screening of peptide candidates before expensive experimental testing.
Study Shows Different Metabolic Stress Models Produce Distinct Effects on Human Neuronal Networks
Researchers tested three common in vitro metabolic stress models on human-derived neuronal networks and found each produced different patterns of neuronal activity and cell damage. The models tested were hypoxia alone, oxygen-glucose deprivation (OGD), and hypoxia combined with glutamate exposure. The findings suggest that choice of experimental model significantly affects results and that combining electrophysiological and structural analyses is important for accurately assessing metabolic stress in stroke research.