The high penetration of renewable energy and frequent extreme weather events bring significant uncertainty to the operation and planning of power systems. The extreme scenarios exhibit high impact and low probability characteristics, posing a challenge in providing sufficient and reliable samples for power system decision-making. The existing scenario generation methods struggle to balance the generation efficiency and interpretability. The causality between meteorological factors and power system operation has not provided effective guidance for the extreme scenario generation. In this paper, firstly, the mechanism analysis and sample construction of extreme scenarios were achieved through meteorological factor extraction, meteorological-scenario causality test and scenario clustering. Secondly, an enhanced GAN model considering training stability is established. The physical constraints of power systems are used to ensure the effectiveness of generated scenarios. Finally, a statistical analysis considering the individuals and the whole samples is conducted. The accuracy evaluation method of the generated scenarios is proposed. The robustness of the model is validated based on accuracy. The results indicate that the generated scenario have statistical consistency and high accuracy.

The high penetration of renewable energy is becoming an important feature of new power systems. However, the power grid is facing greater threats of failures with the increasing frequency of extreme weather, making it necessary to enhance the resilience of power systems. In this paper, a multi-time-scale energy storage planning system is proposed for power system resilience improvement. Firstly, the characteristics of multi-time-scale energy storage are analyzed, and models of battery energy storage and hydrogen energy storage are established. Secondly, based on an analysis of random extreme weather scenarios, a bi-level stochastic programming model for multi-energy storage aimed at enhancing the resilience of power systems is constructed. Finally, based on the modified IEEE-24 node system, the model solution and example analysis are carried out, and the optimal configuration scheme for multi-energy storage is obtained. The results show that multi-energy storage is able to adjust more flexibly and effectively improve the resilience of the power system. Compared with the configurations of short-term and long-term energy storage systems, adopting multi-timescale energy storage reduces the total cost by 22.77% and 14.08%, respectively, and improves resilience by 4.33% and 0.67%, respectively.

As the proportion of renewable power continues to increase, its inherent intermittency and volatility pose serious challenges to the security and stability of power systems. Scenario generation technology serves as a key tool supporting decision-making methods such as stochastic optimization and risk analysis. By generating representative power output scenarios, it can effectively characterize the uncertainty of renewable power output. This paper systematically reviews mainstream methods for the scenario generation of renewable power output, categorizing them into two major classes: sampling-based methods and model-based methods. Among them, sampling-based methods include Monte Carlo sampling, Latin hypercube sampling (LHS), Markov chains (MCs), and Copula functions. Model-based methods encompass artificial neural networks (ANNs), long short-term memory networks (LSTMs), autoregressive moving average models (ARMAs), generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models and transformer-based models. This paper elaborates on the principles and characteristics of each type of method. Moreover, scenario quality is evaluated from three dimensions: output-based metrics for numerical accuracy, distribution-based metrics for statistical consistency, and event-based metrics for key operational event representation. The current research challenges and future research directions are also summarized to provide a reference for modeling the uncertainty of renewable output.

The transition towards high-renewable power systems introduces high-dimensional nonlinearity and uncertainty, rendering traditional offline look-up table schemes prone to control mismatch against “unseen” contingencies. Meanwhile, existing response-driven approaches face a dilemma between the computational latency of physics-based optimization and the safety risks of end-to-end AI. To bridge this gap, this paper proposes a Response-Driven Optimal Emergency Control Framework that ensures both millisecond-level speed and rigorous physical constraints. First, a deep learning-based predictor is employed to extract spatiotemporal features from real-time PMU data, enabling high-fidelity prediction of stability margins. Crucially, instead of direct black-box control, the data-driven model is utilized to derive linear control sensitivities via a batch-processing perturbation mechanism. This transforms the intractable Transient Stability Constrained Optimal Power Flow (TSC-OPF) problem into a real-time solvable Linear Programming model. Case studies on a regional AC/DC hybrid grid demonstrate that the proposed framework achieves high prediction accuracy and effectively restores stability in mismatch scenarios where traditional schemes fail. Furthermore, the decision speed of the proposed method is significantly improved compared to traditional time-domain simulations, thus strictly satisfying the real-time requirements of the second line of defense.