Intelligent distribution network dynamic reconstruction optimization model based on improved multi-objective genetic algorithm

The increasing saturation of circulated energy resources means that modern distribution networks are experiencing greater complexity, variability, and operational challenges. To address these issues and ensure optimal performance, this research creates an intelligent distribution network dynamic distribution network reconfiguration optimization model using an improved optimization algorithm. The research proposes a Capuchin Search-driven Improved Multi-Objective Genetic Algorithm (CS-IMOGA) to reconfigure the distribution network topology in real time dynamically, optimizing system performance across multiple objectives, including the load balancing index (LBI), the active power loss (APL), and maximum node voltage deviation (MNVD). The CS-IMOGA integrates enhanced genetic operations such as adaptive crossover and mutation strategies, elitism preservation, and diversity control to prevent premature convergence and improve global search capability. Simulation was conducted on the standard IEEE 33-bus distribution system to evaluate the methods’ efficiency. Simulation on the IEEE 33-bus system demonstrates superior performance, achieving APL = 1980.5043 kWh, LBI = 0.03210 p.u., and MNVD = 1.0402 p.u., outperforming existing LDBAS and SBSO methods. The dynamic distribution network reconfiguration process effectively adapts to load fluctuations and distributed energy resources (DER) variability while maintaining the radial network structure and operational constraints. This research contributes a scalable and intelligent result for real-time, Multi-Objective (MO) reconfiguration in smart grid environments, thereby promoting resilience, flexibility, and operational efficiency in evolving power systems. CS-IMOGA optimizes network reconfiguration for reduced losses and improved load balance. Real-time adaptation maintains voltage stability under dynamic load and DER variations. Enhanced GA strategies improve convergence, diversity, and multi-objective performance.