Critical Weather Scenario Screening Using Weather

Electrical Engineering and Systems Science > Systems and Control
[Submitted on 24 Aug 2026]
Title:Critical Weather Scenario Screening Using Weather-to-Voltage (W2V) Predictive Modeling
View PDF HTML (experimental)Abstract:This paper proposes a critical weather scenario screening framework for identifying weather conditions that can trigger high-voltage (HV) events in the power grid. Unlike conventional weather-aware contingency analysis limited to component-level outage risk, our framework screens weather scenarios as potential drivers of grid-level voltage violations. Given a non-critical weather scenario, we seek the perturbation over the high-dimensional weather space to maximize a pre-defined voltage criticality score, by using a differentiable weather-to-voltage (W2V) predictive model to facilitate the gradient update over a compact latent space. Specifically, a non-negativity constraint is used for achieving physically-consistent perturbations, with another L1-norm based constraint for bounded perturbation. The latter could promote sparse and interpretable perturbations, and this uniform budget also yields a sensitivity-aware vulnerability ranking across different weather scenarios. Numerical experiments on a 6717-bus synthetic Texas system have effectively demonstrated the potential of weather uncertainty in triggering HV events, and this potential cannot be represented by the voltage analysis of individual weather scenarios. Interestingly, the most vulnerable scenarios are characterized by wind-dominated perturbation patterns concentrated in high wind-capacity regions, coinciding with observations from actual power flow data and experiences in real system operations.
Current browse context:
eess.SY
References & Citations
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Facts Only

* A framework for critical weather scenario screening is proposed.
* The goal is to identify weather conditions triggering high-voltage (HV) events in the power grid.
* The framework screens weather scenarios as drivers of grid-level voltage violations, unlike component-level outage analysis.
* A differentiable weather-to-voltage (W2V) predictive model is used for gradient updates over a latent space.
* Non-negativity constraints are used for physically consistent perturbations.
* An L1-norm constraint is applied for bounded perturbation to promote sparse and interpretable perturbations.
* Numerical experiments were conducted on a 6717-bus synthetic Texas system.
* Experiments demonstrated the potential of weather uncertainty in triggering HV events.
* Vulnerable scenarios are characterized by wind-dominated perturbation patterns concentrated in high wind-capacity regions.

Executive Summary

A framework is proposed for screening critical weather scenarios that can trigger high-voltage (HV) events in the power grid. This approach moves beyond conventional component-level outage risk by analyzing weather conditions as drivers of grid-level voltage violations. The method utilizes a differentiable weather-to-voltage (W2V) predictive model to navigate the high-dimensional weather space. The goal is to find perturbations that maximize a predefined voltage criticality score. Constraints are applied to ensure physical consistency, using non-negativity constraints and an L1-norm constraint for bounded perturbation, which aims to yield sparse and interpretable results. Experiments on a synthetic Texas system demonstrated that weather uncertainty significantly impacts HV events, revealing vulnerability patterns characterized by wind-dominated perturbations in high wind-capacity regions, aligning with real system operations data.

Full Take

The methodology blends machine learning techniques with physical constraints to operationalize complex climate risk assessment in energy systems. The core innovation lies in shifting the analytical focus from assessing individual outage risks to proactively identifying systemic vulnerabilities stemming from environmental perturbations across the entire system state. The use of differentiable modeling suggests an attempt to find a continuous, gradient-based path toward criticality, which is a significant step beyond discrete contingency analysis. However, the effectiveness hinges on the quality and faithfulness of the W2V model in capturing the non-linear physics of power flow under stochastic weather inputs. The finding that vulnerability aligns with actual wind patterns suggests that empirical data can refine predictive models, moving from purely theoretical risk to observable operational realities. A critical consideration is ensuring that the regularization constraints (non-negativity and L1 norm) do not inadvertently suppress or misrepresent truly high-impact, albeit less obvious, physical scenarios when seeking sparse solutions for vulnerability ranking. Future work must rigorously test the sensitivity of the derived perturbation patterns against real-world observational discrepancies to ensure the framework translates theoretical potential into actionable resilience strategies rather than merely mapping observed correlations.

Sentinel — Human

Confidence

This text appears to be a direct excerpt from a peer-reviewed or submitted research paper, displaying the structured logic and specific detail characteristic of human scientific writing.

Signals Detected

Sentence length variance is appropriate for technical academic writing; no extreme uniformity detected.

Text exhibits strong logical flow connecting the abstract proposal to the numerical results and implications without unnecessary hedging.

The technical terminology and structure align with established academic presentation (Problem -> Method -> Results -> Implication).

Specific details (6717-bus system, W2V model use, constraints) appear highly specific and characteristic of actual research documentation.

Human Indicators

The precise technical framing and the inclusion of self-referential context (arXiv submission date, reference to related tools) suggest an authentic academic context.