基于电动汽车虚拟储能模型的微电网日前优化调度OA

Benefiting from advancements in battery technology and policy incentives,the market penetration and ownership of electric vehicles(EV)have been steadily increasing.To fully leverage the dynamic response capability of EV clusters and optimize the supply/demand balance in microgrids with a high proportion of new energy sources,this paper proposes a day-ahead optimal scheduling strategy based on the virtual energy storage model of clustered EVs and the optimized echoes of the state network(ESN)prediction model utilizing the Black-winged Kite Algorithm(BKA)for microgrids strategy.First,a single EV virtual energy storage model is constructed.The charging and discharging power and energy boundaries of clustered EVs are aggregated by combining the Minkowski sum operation with the Monte Carlo random sampling method.This approach ensures the accuracy of the scheduling plan by retaining the correlation of individual constraints among EVs while downscaling the original data.Second,for the cluster EV power boundary prediction problem,a parameter prediction method based on BKA-ESN is proposed,which significantly reduces data dimensionality by taking the cluster EV power boundary as an input feature.It optimizes the core parameters of the reserve pool through the BKA algorithm,enhancing the accuracy and stability of the prediction model.Further,a day-ahead optimal scheduling model is established with the objectives of minimizing the integrated operation cost of the microgrid and the charging costs of cluster EVs.A linear weighting method is used to transform the multi-objective into a single-objective for solving.The simulation results show that the proposed strategy effectively reduces the demand for gas turbine operation and grid power purchases.It reduces the total microgrid operation cost by 22.0%and lowers the cluster EV charging costs by 8.9%.Additionally,the strategy significantly increase the renewable energy consumption rate while improving the stability of microgrid operation and power supply reliability.This is achieved by coordinating the charging and discharging of energy storage systems with gas turbine power to facilitate peak shaving and valley filling.The simulation results verify the effectiveness of the proposed model in terms of scheduling feasibility,economy and renewable energy consumption capacity,and provide theoretical support for the integration of cluster EVs in microgrid co-optimization.