A power system stability assessment framework using machine-learning

Meridji T.; Joos G.; Restrepo J.

首页> 外文期刊>Electric Power Systems Research >A power system stability assessment framework using machine-learning

【24h】

A power system stability assessment framework using machine-learning

机译：A power system stability assessment framework using machine-learning

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

? 2022 Elsevier B.V.With the planned massive integration of renewable energy resources, the electric network is gradually becoming a less predictable system. In such power systems, the set of critical operating points shifts and no longer necessarily coincides with peak and light load conditions. This means that deducing the stability of the system from a restricted analysis of a limited number of operating points becomes very speculative. A methodical approach that covers all hourly operating points throughout a study year is therefore necessary. This paper offers a platform based on supervised and unsupervised machine learning techniques along with optimal power flow, steady-state, and dynamic simulation tools to perform deterministic time-series simulations. The platform allows rapid time-series preliminary assessments of transient stability (i.e., rotor angle stability) in the context of high renewable penetration. As a case study, the proposed platform is tested to assess the transient stability of an IEEE-39 test system augmented with renewable energy resources. Various generation expansion scenarios are considered to show how the platform can be used to conduct grid scenario analyses by investigating the effect of different energy mixes, renewable penetration levels, and renewable siting.

著录项

来源
《Electric Power Systems Research》 |2023年第3期|1-12|共12页
作者
Meridji T.; Joos G.; Restrepo J.;
展开▼
作者单位

Department of Electrical and Computer Engineering McGill University;

SNC-Lavalin Clean Energy Division;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种英语
中图分类
关键词
Deep learning; Machine learning; Renewable energy sources; Times-series analysis; Transient stability; Transmission planning studies;

A power system stability assessment framework using machine-learning

摘要

著录项

相关主题

期刊订阅