With the advancement of the “dual carbon” goals, a high proportion of renewable energy sources are being widely integrated into the power grid, resulting in a power system characterized by numerous uncertainties, rapid changes in supply and demand, and strong multi-dimensional randomness. These characteristics pose new challenges to the safe and stable operation of the power grid. However, traditional power system reliability assessment methods are constrained by computational complexity, making it difficult to meet the demands for rapid assessment. To address this issue, this paper designs a data-assisted intelligent model to achieve rapid and accurate reliability assessment of power systems under the context of high-penetration renewable energy integration. Firstly, based on the coupling relationship between the unavailability rate of transmission lines and their operating conditions as well as aging effects, this paper establishes a model for the unavailability rate of transmission lines and proposes a method for selecting key components in the power grid. Subsequently, an analytical model for power grid reliability indicators concerning the reliability parameters of key components is constructed. By utilizing this analytical model to generate a large number of data samples, a Physics-Informed Neural Network (PINN) model is constructed and trained to enable rapid calculation of reliability indicators. Finally, the effectiveness and feasibility of the proposed method are validated through the IEEE standard test system. After analysis, the single-evaluation time of the proposed method is approximately 10 ms, representing a computational efficiency improvement of up to 63.2% compared to existing artificial intelligence models such as MGAT, TCN-BiGRU, etc.
Against the background of China’s dual carbon goals, high-renewable-power systems suffer severe resilience threats from destructive ice disasters, and existing recovery approaches fail to fully exploit multi-type flexible resources with unsatisfying computational efficiency. Targeting this gap, this work establishes a resilience enhancement framework for ice-affected power grids. This model quantifies line failure probability considering time-varying ice thickness and wind load, generates representative fault scenarios via sequential Monte Carlo and K-means clustering, and innovatively incorporates mobile energy storage systems (MESSs) and low-temperature-corrected PEM electrolyzers into coordinated post-fault dispatch; an improved parrot optimization (PO) algorithm with Chebyshev chaos, random mutation and adaptive t-distribution is designed to boost solving efficiency. Tested on the IEEE 39-bus system, the proposed method reduces average load shedding to 3.7% and raises renewable accommodation to 95.6%, outperforming fixed energy storage and literature-based strategies by cutting load curtailment by 45.6% and 30.2% respectively, while multi-condition sensitivity analyses validate its stable applicability under varying disaster intensity and renewable penetration. This coordinated scheduling strategy supplies feasible technical support for practical anti-icing resilience promotion of new-type power grids.