Golden eagle optimization algorithm embedded in gated Kolmogorov-Arnold network for transient stability preventive control of power systems

Linfei Yin, Wei Ge and Rongkun Liu

Energy, 2025, vol. 318, issue C

Abstract: With the expansion of the power grid-scale and intelligent development, the investigation of transient stability preventive control (TSPC) is becoming more and more essential. The traditional TSPC contains the solution of nonlinear differential-algebraic equations (NDEs), which is a complex and time-consuming computational process that fails to meet the real-time requirements of TSPC. Therefore, this study combines the gated cyclic unit with the Kolmogorov-Arnold network (KAN) and proposes a transient stability prediction (TSP) model based on the gated Kolmogorov-Arnold network (GKAN) instead of the NDEs and combines this model with the golden eagle optimization (GEO) algorithm for the TSPC. The GKAN-based TSP model and GEO are compared and experimented on two systems, IEEE 39–46 system and IEEE 145–453 system, respectively. The experimental results show that in the IEEE 39–46 system, the root mean square error, mean absolute error, and mean absolute percentage error of the GKAN-based TSP model are 53.03 %, 70.67 %, and 66.00 % lower than the suboptimal model, respectively, and the coefficient of determination is 1.30 % higher, and the value of the objective function of GEO is 4.05 % lower than that of the suboptimal algorithm; for the IEEE 145–453 system, the corresponding values are 56.59 %, 80.96 %, 77.12 %, 0.76 % and 4.30 %, respectively.

Keywords: Deep learning; Kolmogorov-Arnold network; Transient stabilization preventive control; Neural networks (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225005730
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:318:y:2025:i:c:s0360544225005730

DOI: 10.1016/j.energy.2025.134931

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().