Robust Unit Commitment Considering the Temporal and Spatial Correlations of Wind Farms Using a Data-Adaptive Approach

Abstract

In robust optimization problems, building a proper uncertainty set for the stochastic variables plays an important role. Due to the restricted mathematical formulations of the uncertainty sets, the results derived from conventional two-stage robust optimization are usually over conservative. In this paper, a novel data-adaptive robust optimization method for the unit commitment is proposed for the power system with wind farms integrated. The extreme scenario extraction and the two-stage robust optimization are combined in the proposed method. The data-adaptive set consisting of a few extreme scenarios is derived to reduce the conservativeness by considering the temporal and spatial correlations of multiple wind farms. Numerical results demonstrate that the proposed data-adaptive robust optimization algorithm is less conservative than the current two-stage optimization approaches while maintains the same level of robustness of the solution.