Probabilistic Spatiotemporal Modeling of Day-Ahead Wind Power Generation with Input-Warped Gaussian Processes
This work addresses the need for accurate probabilistic wind power forecasts for grid operators, but it is incremental as it builds on existing Gaussian Process methods with specific adaptations.
The authors tackled the problem of probabilistic day-ahead wind power forecasting by developing a Gaussian Process model with input warping to handle non-stationarity, achieving validated effectiveness in synthetic experiments and applying it to a realistic dataset from Texas wind farms.
We design a Gaussian Process (GP) spatiotemporal model to capture features of day-ahead wind power forecasts. We work with hourly-scale day-ahead forecasts across hundreds of wind farm locations, with the main aim of constructing a fully probabilistic joint model across space and hours of the day. To this end, we design a separable space-time kernel, implementing both temporal and spatial input warping to capture the non-stationarity in the covariance of wind power. We conduct synthetic experiments to validate our choice of the spatial kernel and to demonstrate the effectiveness of warping in addressing nonstationarity. The second half of the paper is devoted to a detailed case study using a realistic, fully calibrated dataset representing wind farms in the ERCOT region of Texas.