This paper develops a fully data-driven, missing-data tolerant method for post-fault short-term voltage stability (STVS) assessment of power systems against the incomplete PMU measurements. The super-resolution perception (SRP), based on a deep residual learning convolutional neural network, is employed to cope with the missing PMU measurements. The incremental broad learning (BL) is used to rapidly update the model to maintain and enhance the online application performance. Being different from the state-of-the-art methods, the proposed method is fully data-driven and can fill up missing data under any PMU placement information loss and network topology change scenario. Simulation results demonstrate that the proposed method has the best performance in terms of STVS assessment accuracy and missing-data tolerance among the existing methods on the benchmark testing system.

High intermittence of renewable energy resources (RESs) and restriction for greenhouse gas (GHG) emissions have significantly challenged the operations of traditional diesel generator (DG) based microgirds. This paper considers an emission-free microgid with hybrid hydrogen-battery energy storage (HHBES) and proposes a coordinated operational strategy to minimize its daily operation costs. In addition to the electricity purchase costs in the day-ahead market and the operational costs of RESs, the total degradation cost of HHBES is also included in the cost calculation. The proposed operational strategy consists of two coordinated stages. At the day-ahead stage, the schedule for the tie-line power is exchanged with the main grid, the output power of the fuel cell (FC) and the input power of the electrolysis device (ED) are optimized under the worst case of uncertain power output from RESs and power demand from electricity loads (ELs). At the intra-day stage, the battery power is determined according to the short-term prediction for the power of RESs and ELs. The problem is formulated as a robust optimization model and solved by a two-level column-and- constraint-generation (C&CG) algorithm. Numerical simulations using Australian energy market operator (AEMO) data are carried out to validate the effectiveness of the proposed strategy.