Probabilistic Spatiotemporal Modeling of Day-Ahead Wind Power Generation with Input-Warped Gaussian Processes

TL;DR

This paper introduces a probabilistic spatiotemporal Gaussian Process model with input warping to improve day-ahead wind power forecasts across multiple locations, capturing non-stationarity in the data.

Contribution

It presents a novel input-warped Gaussian Process approach with a separable space-time kernel for modeling non-stationary wind power data.

Findings

Effective in capturing non-stationarity through input warping

Validated with synthetic experiments and real ERCOT data

Improves probabilistic wind power forecasting accuracy

Abstract

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.