Decentralized Data-Driven Load Restoration in Coupled Transmission and Distribution System With Wind Power

This paper proposes a new decentralized data-driven load restoration (DDLR) scheme for transmission and distribution (TD) systems with high penetration of wind power. Robust DDLR models are constructed in order to handle uncertainties ensure the feasibility schemes. The Wasserstein metric is used describe ambiguity sets probability distributions build complete model realize computationally tractable formulation. A model-nested analytical target cascading (DATC) algorithm developed obtain final result by iteratively solving small-scale mathematical models. proposed provides results adjustable robustness, performance efficiency independent from amount data. makes full use available data while respecting information privacy requirements operated systems, ensures strategy even worst-case condition. effectiveness method validated using TD system large-scale IEEE 118-bus TS thirty IEEE-33 DSs, showing computational superior performance.