Weather-Transition-Aware Dynamic Mixture-of-Experts for Day-Ahead Probabilistic Wind Power Forecasting
Open Access
Abstract
Wind power forecasting under transitional weather conditions is crucial for the secure operation and dispatch of power systems. However, existing methods have limited ability to perceive and adapt to the rapid, nonstationary changes in the weather–power mapping caused by transitional weather, resulting in substantially increased forecasting errors and uncertainty. To address this issue, this paper proposes a day-ahead probabilistic wind power forecasting method based on a weather-transition-aware mixture-of-experts network. First, based on numerical weather prediction (NWP) sequences of wind speed and temperature, a progressive analysis of trends and abrupt changes and a turning-point localization mechanism based on symmetric-ratio minimization are introduced to identify potential transitional periods and generate a weather-transition mask. The binary transition indicator is then concatenated with the NWP features at each time step, and cross-attention is employed to fuse meteorological forecasts with historical power information. Finally, a gated mixture-of-experts (MoE) network dynamically fuses conventional-weather and transitional-weather experts according to the daily transition fraction. Quantile regression is subsequently used to generate prediction intervals at multiple coverage levels. A case study of a wind farm shows that the proposed method achieves a normalized mean absolute error (NMAE) of 5.79%, a coefficient of determination () of 0.88, and a 21.36% reduction in the normalized average width of the 95% prediction interval relative to the baseline with the lowest mean normalized average interval width.
Keywords
Funding Information
- China Huaneng Group Technology Project (HNKJ24-H130)
This publication has 20 references indexed in Scilit:
- A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GANEnergy, 2023
- A contrastive learning-based framework for wind power forecastExpert Systems with Applications, 2023
- Analysing wind power ramp events and improving very short‐term wind power predictions by including wind speed observationsWind Energy, 2023
- A direct prediction method for wind power ramp events considering the class imbalanced problemEnergy Science & Engineering, 2023
- An algorithm for forecasting day-ahead wind power via novel long short-term memory and wind power ramp eventsEnergy, 2022
- A novel few-shot learning approach for wind power prediction applying secondary evolutionary generative adversarial networkEnergy, 2022
- Development of a wind power ramp forecasting system via meteorological pattern analysisWind Energy, 2022
- Conformalized temporal convolutional quantile regression networks for wind power interval forecastingEnergy, 2022
- Wind power ramp event detection using a multi-parameter segmentation algorithmEnergy Reports, 2021
- Short-term prediction of wind power and its ramp events based on semi-supervised generative adversarial networkInternational Journal of Electrical Power & Energy Systems, 2021