Droop Control-Based Optimization of Hybrid Renewable Energy Systems: Combining Node-Level Capsule Graph Neural Network with Artificial Protozoa Optimizer

Journal of Elliptic and Parabolic Equations · Springer Nature · 2026-02-01 · DOI: 10.1134/S0005117925601204

Аннотация

Abstract Optimization of hybrid renewable energy systems (HRES) using droop control (DC): This research proposes the combination of node-level capsule graph neural network and artificial protozoa optimizer (NLCGNN-APO). First, data from the “Dataset for renewable energy systems” dataset is collected. The success of the proposed method is assessed using performance metrics such as rise time, settling time, and overshoot in contrast to other existing methods, such as droop control combined with a proportional-integral (Droop+PI) controller. Droop control with particle swarm optimization (droop+pso) tuned fractional order proportional-integral (fopi) controller, droop control with fractional order proportional-integral (Droop+FOPI) controller, artificial neural network-based adaptive proportional-integral controller (ANN-APIC), and conventional PI controller. The proposed APO-NLCGNN method achieves 0.078 s rise time, 0.052 s settling time and 0.98% overshoot. Overall, adaptive and optimized controllers outperform traditional droop-based solutions in reducing overshoot and enhancing system stability.

Читать у издателя →

Похожие статьи