Dynamic modeling for VSG cluster by using data-physical driven method

Li, Yunlu; Ma, Guiqing; Yang, Junyou; Xu, Yan

doi:10.1016/j.egyr.2022.02.106

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [94] combines neural networks to achieve equivalent impedance identification at different operating points under fixed control modes.…”

Section: Data-assisted Physics-inspired Model Constructionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven modeling of power system dynamics: Challenges, state of the art, and future work

Huang,

Lin,

Zhou

et al. 2023

iEnergy

View full text Add to dashboard Cite

With the continual deployment of power-electronics-interfaced renewable energy resources, increasing privacy concerns due to deregulation of electricity markets, and the diversification of demand-side activities, traditional knowledge-based power system dynamic modeling methods are faced with unprecedented challenges. Data-driven modeling has been increasingly studied in recent years because of its lesser need for prior knowledge, higher capability of handling large-scale systems, and better adaptability to variations of system operating conditions. This paper discusses about the motivations and the generalized process of datadriven modeling, and provides a comprehensive overview of various state-of-the-art techniques and applications. It also comparatively presents the advantages and disadvantages of these methods and provides insight into outstanding challenges and possible research directions for the future.

show abstract

“…Ref. [94] combines neural networks to achieve equivalent impedance identification at different operating points under fixed control modes.…”

Section: Data-assisted Physics-inspired Model Constructionmentioning

confidence: 99%

“…Ref. [94] uses physics informed neural network (PINN) for online parameter identification of equivalent impedances. A migration learning approach is also used to accelerate the training by applying a large amount of simulation data.…”

Section: Online Parameter Identificationmentioning

confidence: 99%