Mitigating congestion management in power systems with high renewable integration using hybrid approach

The substantial penetration of Renewable Energy Sources (RES) makes the electricity grid unstable due to its unpredictable nature, necessitating the development of an Energy Storage System, which has intermittent outputs and poses difficulty in controlling transmission congestion. This manuscript presents a hybrid technique for congestion management in power systems (CMPS) with significant penetration of RES. The proposed scheme is a joined execution of a Similarity-Navigated Graph Neural Network (SNGNN) and Black-Winged Kite Optimization Algorithm (BKOA), which is commonly named as an SNGNN-BKOA approach. The major goal of the study is to reduce minimum relieving congestion costs and power loss. The load demand is predicted using the SNGNN technique. The BKOA is used to optimize the congestion mitigation cost. The proposed method optimizes ESS charging and discharging to eliminate RES-related uncertainty and relieve congestion. A proposed method is used to address congestion, which is viewed as a non-linear problem. The proposed BKOA-SNGNN approach is implemented in the MATLAB platform and compared their performance with various existing strategies. The existing approaches are Salp Swarm Optimization (SSA) and Gray Wolf Optimizer (GWO). The proposed strategy indicates better performance in power system optimization by effectively reducing congestion relief costs and transmission losses. It consistently achieves lower congestion relief costs over time, highlighting its adaptability to varying operational conditions. The method also achieves the lowest system loss of 48.4 MW and the smallest RMSE of 0.164 %, ensuring higher accuracy and reliability. These results underscore its robustness and effectiveness in enhancing overall system performance.