Abstract:To mitigate the fluctuations caused by large-scale renewable energy integration，a distributionally robust optimal dispatch model for integrated energy systems with generalized energy storage is proposed，considering renewable energy uncertainties. Firstly，a system model incorporating generalized energy storage （GES） is constructed based on the operational characteristics of physical energy storage，electric vehicles，and virtual energy storage of building. Secondly，a scenario generation method combining the information maximizing generative adversarial network and long short-term memory network is developed to capture the stochastic features of renewable energy outputs. The generated high-fidelity scenarios are utilized as initial inputs to formulate a distributionally robust optimization model for the GES-integrated energy system. which is solved iteratively using the parallelized column and constraint generation algorithm. Finally，the scheme and numerical example analysis verify the effectiveness of this model.