A Data-Driven Resilience Assessment for Integrated Energy Systems

View at publisher Summarise with VIRAT
Authors: Peng Wang, Xue Li, Tao Jiang, Rufeng Zhang, Changjiang Wang
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In recent years, the frequent occurrence of extreme natural disasters has posed substantial risks to integrated electricity-gas-heat energy systems (IES). Accurate resilience assessment of such systems requires evaluating a vast number of operating states using optimal energy flow (OEF), which are computationally demanding. To address this issue, this paper presents a data-driven method to accelerate resilience assessment. Specifically, a disturbance increment method is first applied to reduce failure scenario dimensionality, enabling the enumeration of only low-order failure cases. Subsequently, a Transformer-based neural network is employed as a surrogate model for the conventional OEF solver, effectively eliminating the need for full energy flow calculations. The proposed approach is validated using a modified Berry Island case study, demonstrating its accuracy and computational efficiency.

Fields of Study & Subjects

Integrated Energy Systems Optimization Optimal Power Flow Distribution Infrastructure Resilience and Vulnerability Analysis

Publication details

Journal / source
IEEE PES International Meeting (PES IM)
Pages
1–5
Publication date
18 January 2026
Language
EN