Hybrid SNGNN–BKOA framework for intelligent congestion management in renewable-integrated power systems
Abstract
The rapid integration of renewable energy sources (RES), such as wind and solar, introduces significant variability and uncertainty in modern power systems, which often leads to transmission congestion and operational inefficiencies. This paper proposes a hybrid congestion management framework that combines a similarity-navigated graph neural network (SNGNN) with the black-winged kite optimization algorithm (BKOA). The SNGNN model captures complex spatial relationships within the power network to accurately forecast load demand, while BKOA optimizes congestion mitigation by coordinating generator rescheduling and energy storage system (ESS) operations. The proposed framework was evaluated through MATLAB simulations under different renewable penetration levels. Results demonstrate that the SNGNN–BKOA approach achieves superior performance compared with benchmark algorithms such as grey wolf optimizer (GWO) and salp swarm algorithm (SSA). The proposed method reduces system power loss to 48.4 MW, achieves a forecasting RMSE of 0.164%, and lowers congestion mitigation costs to $5800.09/h at 10% renewable penetration and $6823.71/h at 40% penetration. These results indicate that the proposed hybrid learning–optimization framework improves grid stability, reduces operational cost, and enhances decision-making for congestion management in renewable-dominated smart grids.
Keywords
Congestion management; Energy storage system; Graph neural network; Hybrid optimization; Renewable energy integration
Full Text:
PDFDOI: https://doi.org/10.11591/eei.v15i6.11546
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191
,
e-ISSN: 2302-9285
This journal is published by the
Institute of Advanced Engineering and Science (IAES)
.