Answers are grounded in this paper and cite their sources.
The necessity for effective decentralized or distributed generation (DG) planning in contemporary power systems has expanded due to increasing grid integration of renewable energy sources, driven by rising fuel costs and environmental concerns. However, optimal DG allocation remains a challenging multi-objective problem due to its nonlinear, nonconvex nature and the high computational burden of load-flow evaluations. This study proposes a novel Machine Learning-assisted hybrid Rhinopithecus Swarm Optimization–Snow Ablation Optimizer (ML–RSO–SAO) framework to address these challenges. The proposed framework transforms conventional stochastic search into an intelligent, data-driven optimization process. A surrogate modelling approach using Artificial Neural Networks is employed to predict active and reactive power losses, significantly reducing computational cost, while a Random Forest-based decision mechanism identifies critical candidate buses, thereby simplifying the search space. The hybrid RSO–SAO algorithm effectively balances exploration and exploitation, leading to faster convergence, avoidance of premature stagnation, and improved solution quality. The method is validated on IEEE 33-bus and IEEE 69-bus test systems with solar and wind DG integration. Compared with PSO, WOA, DEO, and SMA, the proposed approach achieves lower power losses, improved voltage profiles, and enhanced economic and environmental performance, demonstrating its effectiveness for reliable DG planning under uncertainties.
No takes yet. Share an insight, caveat, or question.
Krishnamoorthy et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: