Electric Vehicle Fast Charging-Based Modular Multilevel Converter for Enhanced Voltage Gain and Efficiency

Transportation must be rapidly electrified, including recharge infrastructure expansion, to keep up with the fast growth of electric vehicle (EV) technology. As the power levels handled by DC fast converters for electric vehicles rise, there are new challenges that emerge for switching devices to adhere to efficiency standards. This paper proposes a novel approach based on the Modular Multilevel Converter (MMC) for electric vehicle fast charging to overcome these challenges. The innovation of this paper lies in the novelty of the Fossa Optimization Algorithm (FOA) and the Synaptic Intelligent Convolutional Neural Network (SICNN). This combined approach is generally known as the FOA-SICNN method. The main objective of the proposed technique is to reduce switching losses, maximize voltage gain and enhance system efficiency. The proposed FOA technique is employed to optimize the charging speed of the EV, while the SICNN approach predicts the optimal control parameters of the MMC. The approach is implemented on the MATLAB platform, and its performance is analyzed with existing approaches like the Fire Hawk Optimizer (FHO), Social Spider Optimization Algorithm (SSOA) and Genetic Algorithm (GA). The existing converter exhibits switching losses of 6.781, 8.982 and 10.989[Formula: see text]W, while the proposed converter reduces these to 4.132[Formula: see text]W. Regarding voltage gain, the existing converter shows gains of 6, 4 and 2, whereas the proposed converter attains a higher gain of 8. These outcomes demonstrate that the proposed converter not only minimizes switching losses but also increases voltage gain, leading to a significant improvement in efficiency. Overall, the proposed converter outperforms the existing one in both switching loss and voltage gain. This enhanced performance makes the proposed MMC converter more suitable for electric vehicle fast charging applications, ensuring optimized energy transfer with minimized losses and improved overall system efficiency.