Low-dimensional Models in Spatio-Temporal Wind Speed Forecasting

TL;DR

This paper introduces a novel low-dimensional, compressive sensing-based spatio-temporal wind speed forecasting algorithm that leverages the intrinsic structure among multiple stations to improve short-term prediction accuracy.

Contribution

It proposes a new structured-sparse recovery approach for wind speed forecasting that exploits low-dimensional structures across stations, outperforming existing benchmark models.

Findings

Significant improvement over benchmark models in case study

Effective exploitation of low-dimensional structures in wind data

Novel structure-sparse recovery algorithms for forecasting

Abstract

Integrating wind power into the grid is challenging because of its random nature. Integration is facilitated with accurate short-term forecasts of wind power. The paper presents a spatio-temporal wind speed forecasting algorithm that incorporates the time series data of a target station and data of surrounding stations. Inspired by Compressive Sensing (CS) and structured-sparse recovery algorithms, we claim that there usually exists an intrinsic low-dimensional structure governing a large collection of stations that should be exploited. We cast the forecasting problem as recovery of a block-sparse signal $\boldsymbol{x}$ from a set of linear equations $\boldsymbol{b} = A\boldsymbol{x}$ for which we propose novel structure-sparse recovery algorithms. Results of a case study in the east coast show that the proposed Compressive Spatio-Temporal Wind Speed Forecasting (CST-WSF) algorithm significantly improves the short-term forecasts compared to a set of widely-used benchmark models.