RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dwivedi, Anmol, Tajer, Ali, Paternain, Santiago, Virani, Nurali
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909406172545024
author Dwivedi, Anmol
Tajer, Ali
Paternain, Santiago
Virani, Nurali
author_facet Dwivedi, Anmol
Tajer, Ali
Paternain, Santiago
Virani, Nurali
contents Electricity grid's resiliency and climate change strongly impact one another due to an array of technical and policy-related decisions that impact both. This paper introduces a physics-informed machine learning-based framework to enhance grid's resiliency. Specifically, when encountering disruptive events, this paper designs remedial control actions to prevent blackouts. The proposed Physics-Guided Reinforcement Learning (PG-RL) framework determines effective real-time remedial line-switching actions, considering their impact on power balance, system security, and grid reliability. To identify an effective blackout mitigation policy, PG-RL leverages power-flow sensitivity factors to guide the RL exploration during agent training. Comprehensive evaluations using the Grid2Op platform demonstrate that incorporating physical signals into RL significantly improves resource utilization within electric grids and achieves better blackout mitigation policies - both of which are critical in addressing climate change.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors
Dwivedi, Anmol
Tajer, Ali
Paternain, Santiago
Virani, Nurali
Machine Learning
Artificial Intelligence
Systems and Control
Electricity grid's resiliency and climate change strongly impact one another due to an array of technical and policy-related decisions that impact both. This paper introduces a physics-informed machine learning-based framework to enhance grid's resiliency. Specifically, when encountering disruptive events, this paper designs remedial control actions to prevent blackouts. The proposed Physics-Guided Reinforcement Learning (PG-RL) framework determines effective real-time remedial line-switching actions, considering their impact on power balance, system security, and grid reliability. To identify an effective blackout mitigation policy, PG-RL leverages power-flow sensitivity factors to guide the RL exploration during agent training. Comprehensive evaluations using the Grid2Op platform demonstrate that incorporating physical signals into RL significantly improves resource utilization within electric grids and achieves better blackout mitigation policies - both of which are critical in addressing climate change.
title RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors
topic Machine Learning
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2411.18050