TY  - JOUR
AU  - Manikyam, Naga Raju Hari 
AU  - Thangam, A. 
AU  - Murugachandravel, J. 
AU  - Vimala, K. 
AU  - Swanthana, K. 
AU  - Kanagaraju, P. 
AU  - Bhoopathy, V. 
PY  - 2025
TI  - Enhancing Electric Vehicle Charging Demand Prediction Using a Novel SAE-DNN Neural Network Model for Probabilistic Forecasting
JF  - Journal of Computer Science
VL  - 21
IS  - 10
DO  - 10.3844/jcssp.2025.2400.2411
UR  - https://thescipub.com/abstract/jcssp.2025.2400.2411
AB  - The rapid growth and widespread adoption of Electric Vehicles (EVs) play a crucial role in the progress of intelligent transportation systems, resulting in a significant decrease in environmentally damaging greenhouse gas emissions. The increase in EV usage has made it crucial to develop charging infrastructure to keep up with the growing demand. Precisely predicting EV charging demand is crucial to relieve pressure on electricity systems and offer economical charging options. Simply increasing the number of charging stations is insufficient, as it puts pressure on power infrastructure and is constrained by spatial limits. Researchers are currently working on creating Smart Scheduling Algorithm (SSA) to handle public charging demand using modeling and optimization methods. There is a growing interest in using data-driven methods to model EV charging behaviors. The proposed approach includes preprocessing through normalization, feature extraction using Independent Component Analysis (ICA), and performance assessment with the SAE-DNN framework. The proposed approach compared the method with other two conventional techniques, DNN and SAE-CNN, to show its effectiveness.