Real-time optimization in electric vehicle stations using artificial neural networks
M. A. Elkasrawy, Sameh O. Abdellatif, Gamal A. Ebrahim, Hani A. Ghali
Abstract
Abstract The current study proposes a smart decision-making algorithm to be utilized in electric vehicle stations. The suggested approach emphasizes the prediction of queuing delay seeking for minimum total charging time. For this purpose, artificial neural network (ANN) model is used, where a dataset is pre-generated to be seeded into the model. The proposed model effectiveness can be proven when the number of arriving vehicles at the station exceeds the maximum number of charging points at the station. The model accuracy was recorded to reach 89%. For validity, the proposed ANN model was evaluated with respect to a meta-heuristic optimizer, showing a reduced total charging time by 2.5%, and 23.9% with respect to a bare model with no optimization. As a final validation step, a physical realization of the ANN model was conducted by emulating a vehicle as a transmitting node and the station as a receiving node.