The participation of battery swapping station (BSS) clusters in grid regulation is significantly constrained by the spatio-temporal uncertainty and climate sensitivity of electric vehicle (EV) demand. To address these issues, this paper proposes an aggregated scheduling method that integrates demand forecasting and rolling optimization. First, a demand forecasting model is established by considering seasonal climate and users’ range anxiety. On this basis, a “day-ahead bidding and intra-day tracking” two-stage scheduling framework is constructed. In the day-ahead stage, the optimal bidding power of the cluster is determined for minimizing the overall cluster cost. In the intra-day stage, taking the bidding power as the tracking index, the demand distribution scheme and station charging/discharging strategies are synergistically optimized to minimize the operational costs. Furthermore, for real-time EV swapping requests, suitable BSS nodes are recommended based on the distribution scheme. To address the stochasticity of user rejection, rolling optimization is applied for real-time adjustments, ensuring reliable grid response and service quality. Finally, a case study using real operational data verifies the effectiveness of the proposed model.
Chen et al. (Wed,) studied this question.