Optimal energy management of grid-connected unbalanced microgrids with renewable generation and electric vehicle integration under dynamic operating conditions

Microgrids enable the smart, secure, sustainable, and economical combination of electric vehicles (EVs) and renewable energy sources (RESs). However, energy management is challenging because ofthe unbalanced microgrid structure and the uncertainties associated with RES generation, electricity prices, and EV demand.This manuscript presents anintelligentapproach forsmart energy management for unbalanced microgrids with RESs.The proposed approach combines both the Snooker-Based Optimization Algorithm (SBOA) and Probabilistic Artificial Neural Network (PANN), termed as the SBOA-PANN method.The objectives of the proposed approach are to reduce operating costs, reduce power losses, and enhance network reliability.The SBOA is used for optimal energy scheduling, while the PANN model is employed to predict power flow under dynamic operating conditions.The proposed approach is implemented in MATLAB, and its performance is evaluated against benchmark methods including Modified Harmony Search (MHS), Artificial Bee Colony (ABC), and Modified Multi-objective Salp Swarm Optimization Algorithm (MMOSSA). The results displaythat the proposed method achieves the lowest operating cost of 135$, compared to 138$, 137$, and 136$ for the respective existing methods, demonstrating its superior economic performance over conventional approaches.