17 October 2024 in Frontiers in Energy Research
This paper proposes a novel two-stage transient stability assessment (TSA) model that integrates ensemble learning with cost sensitivity to address the challenges posed by the integration of renewable energy and load fluctuations. The model employs CNNs as positive and negative classifiers to initially evaluate samples, with consistent results output directly. In cases of inconsistency, the sample is evaluated by a fair classifier, specifically an ELM, trained on critical samples. This approach significantly enhances the classification performance and credibility of the fair classifier, especially under imbalanced conditions, thereby improving the overall efficiency and accuracy of TSA. The proposed model demonstrates superior performance compared to single-stage models and other two-stage models, achieving high accuracy and robustness in transient stability assessment, particularly for critical samples.
6 February 2026 in Journal of Visualized Experiments
Extreme disasters such as typhoons pose a great threat to the operational integrity and stability of power grids, making pre-disaster preventive and control measures increasingly important. Motivated by the limitations of conventional N-1 and N-2 security criteria in addressing spatially correlated and probability-driven failures, this paper proposes a fault-chain-based prevention and control method for typhoon disasters. A typhoon wind field model is combined with a transmission branch vulnerability model to quantify the spatiotemporal failure probabilities of transmission branches, based on which high-risk branches under forecast typhoon scenarios are identified. Taking these branches as initial contingencies, a systematic fault chain search is performed to enumerate critical cascading outage paths, and a risk index is established by integrating the failure probabilities at each stage with the corresponding load shedding. On this basis, a risk-oriented preventive control optimization model is formulated, in which generator outputs and load shedding are coordinated to minimize the expected consequences of high-risk fault chains while satisfying operational constraints. Case studies on the IEEE 39-bus test system and the Hainan power grid under Typhoon Yagi verify that the proposed method can effectively capture typhoon-induced failure characteristics, significantly reduce expected load curtailment, and alleviate excessive control costs compared with traditional deterministic criteria. The results demonstrate that the proposed method provides a practical and economical decision-support tool for online operation of power grids under extreme typhoon conditions.