.png){kind=icon}
.png){kind=icon}
Return
A Learning-Based Method for Generating Synthetic Power Grids
.png){kind=icon}
OA
AI
DOI：10.1109/JSYST.2018.2825785.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Analysis and improvement of power grids resilience and efficiency requires the topologies and geographical coordinates of the real transmission networks. However, due to security reasons, such topologies and particularly the locations of the substations and lines are usually not publicly available. In this work, we thoroughly study the structural properties of the U.S. Western Interconnection grid (WI) and, based on the results, present the network imitating method based on learning (NIMBLE) for generating synthetic spatially embedded networks with similar properties to a given grid. We apply NIMBLE to the WI and show that it can generate networks with similar structural and spatial properties as well the same level of robustness to failures to the WI, without revealing the real locations of the lines and substations. To the best of our knowledge, this is the first attempt to consider the spatial distributions of the buses (nodes) and lines and their importance in generating synthetic grids. Moreover, this is the first time that the power flows and vulnerability against failures are considered in evaluating a synthetic power grid.
Keywords:
Complex networks
data mining
power grids
robustness
topology
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
2.4
Papers:
4.5K
Citations:
387