Two-Stage Stochastic Unit Commitment Considering the Uncertainty of Wind Power and Electric Vehicle Travel Patterns

The randomness of wind power output and the uncertainty of electric vehicle (EV) charging demand bring challenges to power system scheduling. On the basis of the traditional deterministic unit combination model, a stochastic optimal dispatch and backup calculation model that fully considers the dual uncertainties of wind power and electric vehicles is proposed for the uncertainty problem faced by power system scheduling. First, for the uncertainty of wind power output, a two-stage stochastic optimization method based on scenario analysis is adopted, and a generative adversarial network (GAN) is used to generate wind power scenarios. Secondly, for the uncertainty of electric vehicle charging demand, it is divided into two categories: Dispatchable and non-dispatchable. The schedulable electric vehicle adopts the stochastic simulation method according to its travel law, and establishes the EV charging agglomeration quotient model; the non-dispatchable electric vehicle obtains its typical load curve through K-means cluster analysis, and incorporates it into the regular load of the system. Finally, a two-stage random unit combination model based on multi-scenario analysis considering EV charging aggregator is established, and the effectiveness of the proposed model is proved by example analysis.