Advanced Neural Network Models for Optimal Energy Management in Microgrids with Integrated Electric Vehicles

EV and BSS are putting a pressure on power networks, and chaotic charging techniques are a major contributor to this. Due to the nonlinear, unpredictable, and energy-intensive character of electric car charging demands, smart microgrids must have optimal energy management. Our regional energy management system optimises operations for electric vehicles and battery storage by orchestrating grid-connected charging using a price-incentive scheme. The system will implement smart microgrids. They hope to achieve this by maximising the profits from battery storage systems and decreasing the costs of charging electric vehicles. To improve search performance, a new method combines GA with NB. Dimensionality reduction, unbalanced dataset classification, and min-max normalisation are all data preprocessing tasks that genetic algorithms are used for. The proposed NBGA hybrid model outperforms previous imputation methods by a whopping 98% in trials where feature selection is not used. In order to make energy management systems better, evolutionary algorithms and naive Bayes classification are used. Through reducing the impact of uncoordinated charging, the suggested method improves the stability and economic feasibility of smart microgrids.