Low-dimensional Models in Spatio-Temporal Wind Speed Forecasting
This addresses the challenge of integrating wind power into the grid by providing more accurate forecasts, though it appears incremental as it builds on existing compressive sensing methods.
The paper tackles short-term wind speed forecasting by proposing a spatio-temporal algorithm that exploits low-dimensional structures in station data, showing significant improvements over benchmarks in a case study on the east coast.
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.