Optimizing simultaneous energy management for slow- and fast-charging electric vehicles: a hybrid approach

This manuscript introduces a hybrid technique designed to enhance the simultaneous energy management (EM) of slow and fast-charge electric vehicles (EVs) within a smart parking lot. The proposed hybrid method combines the Archerfish Hunting Optimizer (AHO) and the Tree Hierarchical Deep Convolutional Neural Network (THDCNN), collectively referred to as the AHO-THDCNN technique. The primary objective of the AHO-THDCNN method is to reduce costs and alleviate the strain on the electrical grid. The THDCNN, a neural network model, plays a crucial role in forecasting valuable data by learning from and recognizing patterns within the training input-data samples. The AHO Approach is responsible for effectively managing the distribution of resources and addressing the energy requirements of both slow- and fast-charging EVs. The performance of the AHO-THDCNN approach is rigorously evaluated using the MATLAB software and compared with different existing approaches. The proposed method reaches its maximum energy level of 260 KW at 18 h, outperforming other existing methods in the comparison. In the proposed method, the efficiency is about 97% which is much better than the all other existing methods. This paper showcases the success of the AHO-THDCNN technique in achieving cost reduction and effective energy power management. It introduces an improvement strategy that modifies the existing algorithm for more efficient EM in smart parking lots.