Document Type

Article

Source of Publication

E Prime Advances in Electrical Engineering Electronics and Energy

Publication Date

6-1-2025

Abstract

The increasing adoption of electric vehicles has led to the installation of charging stations in various locations in major cities worldwide. This study focuses on energy consumption forecasting for Boulder, Nevada, United States electric vehicle charging stations. Efficient management of energy resources at these charging points is crucial for optimizing resource utilization and reducing charging time. While existing literature has focused on energy consumption prediction in smart homes and grids, the significance of electric charging points in smart cities must be considered. The transformers have handled time series forecasting better with larger datasets like the Temporal Fusion Transformer and the Temporal Convolutional Network. However, they still need help with issues, specifically the higher computation cost and larger dataset for the training process. This research proposes a model that enhances energy forecasting for electric vehicles by employing outlier correction and a time series dense encoder as a forecasting technique. The model's novelty is the low computation cost, consideration of the data lagging, and day series past covariates. The model can be trained on limited data to maintain accuracy and effectiveness. Provides precise predictions of electric vehicle energy consumption based on data lagging, resulting in efficient resource management. This research significantly enhances the energy sector's efficiency and long-term viability by pioneering advanced forecasting models and methodologies. The performance evaluation, conducted using metrics like mean squared error and mean absolute deviation, unequivocally underscores the superior forecasting capabilities of the proposed model compared to the transformer-based models.

ISSN

2772-6711

Volume

12

Disciplines

Computer Sciences

Keywords

Electric vehicle charging stations, Energy consumption forecasting, Smart cities, Time series dense encoder

Scopus ID

05003865361

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Gold: This publication is openly available in an open access journal/series

Download

Share

COinS