A Two‐Stage Risk‐Averse Optimal Dispatching Strategy During Cold Wave Considering Wind Power Grid Integration

This paper proposes a two‐phase risk‐averse optimisation strategy for pre‐scheduling and rolling dispatch to account for the grid integration of cluster wind power during cold waves. This method aims to address the imbalance between supply and demand in the power system that may be caused by the low output power of cluster wind power and load surges. Initially, a Wasserstein distance‐based generative adversarial network (WGAN) is employed to generate a set of cluster wind power output scenarios. Subsequently, a two‐stage risk‐averse optimisation strategy is proposed for pre‐dispatch–rolling dispatch. At the rolling‐dispatch stage, the conditional value at risk (CVaR) is used to quantify the risk cost of the power system caused by the cold wave, and the stochastic rolling optimisation strategy is formulated to solve the unit redispatch and power shortage in a refined way. Finally, the model is applied to the improved IEEE‐24 node system, and the results are analysed. The results demonstrate that the proposed method can reduce the cost of system risk and power shortage compared to deterministic optimisation, rolling optimisation and deterministic risk‐averse optimisation.