Temporal Covariance-Involved Distributionally Robust Optimization for Photovoltaic-Hydrogen Integrated Energy System Scheduling Considering Source, Load Sides, and Market Uncertainties

Under the pressures of environmental pollution, solar energy and hydrogen have attracted widespread attention, thus promoting the development of photovoltaic-hydrogen integrated energy system. However, multiple uncertainties seriously interfere with the system's economic and stable operation. Therefore, this article proposes a temporal covariance-involved distributionally robust optimization model for system scheduling considering multiple uncertainties from source, load sides, and market. First, the possible range of the uncertainties distribution is described by a novel moment-based ambiguity set modified with temporal covariances. Second, the objective function is constructed as a min{sup} form to minimize the expected operation cost under the "worst-case" distribution in the ambiguity set. Then, the constraints present a two-stage structure. The first stage guarantees the operation feasibility under the forecasting scenario, and the second stage accounts for forecasting errors to formulate the rescheduling space for resisting uncertainties. Finally, the model is transformed into an easy-to-solve semidefinite programming. Simulation finds that the model 1) significantly reduces the average and standard deviation of system operation cost by 22.35% and 27.41%, respectively; 2) ensures 100% photovoltaic accommodation; and 3) maintains low conservativeness and complexity simultaneously. Above all, this study provides an effective approach for comprehensive ultilization of clean energies under multiple uncertainties.