Smart Grid Optimization and Electric Vehicle Charging Enhancement with Vehicle to Grid Aggregation Using Hybrid SCOA-MDDNN Approach

The increasing adoption of Electric Vehicles (EVs) gives a promising solution for enhancing power grid stability, especially with the growing integration of renewable energy sources (RES). However, maintaining frequency regulation remains challenging; leading to potential power imbalances and grid failures. To address this, the paper proposes a novel hybrid approach for smart grid optimization and electric vehicle charging enhancement with vehicle-to-grid aggregation. The proposed hybrid approach combines the utilization of the Matrix Diffractive Deep Neural Network (MDDNN) technology with the Single Candidate Optimizer Algorithm (SCOA). The main goal of the proposed technique is to implement an advanced V2G framework that optimizes EVs, enhances grid stability, improves load management, and minimizes battery degradation thereby ensuring a more reliable and resilient power network. The SCOA is utilized to optimize the EV charging and discharging cycle. The MDDNN method is used to predict power consumption accurately. The efficiency of the proposed approach is tested using the MATLAB working platform and compared to a number of other approaches, including the Multi-Agent Deep Reinforcement Learning Algorithm (MADRL), Bald Eagle Search Algorithm (BESA), and Gannet Optimization Algorithm-Tree Hierarchical Deep Convolutional Neural Network (GOA-THDCNN). The EV capacity of the proposed method is 82%and the efficiency for the proposed technique is 94%, which is higher contrasted to other existing methods. The proposed method charging cost is 7.73Rs/unit which is less when contrasted with the existing approaches. The proposed method–s significantly advances smart grid technology by offering a robust solution for integrating EVs into the grid, thereby enhancing sustainable and efficient energy management.