# Estimation of energy consumption of electric vehicles using Deep Convolutional Neural Network to reduce driver's range anxiety

arXiv: https://arxiv.org/abs/2008.11112 · HTML: https://mlsanity.com/paper/2008.11112/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Multi-modal Fusion Technology based on Vehicle Information: A Survey](https://mlsanity.com/paper/2211.06080/) (2022)
- [A Review on AI Algorithms for Energy Management in E-Mobility Services](https://mlsanity.com/paper/2309.15140/) (2023)
- [Privacy-Aware Energy Consumption Modeling of Connected Battery Electric Vehicles using Federated Learning](https://mlsanity.com/paper/2312.07371/) (2023)
- [Multistep traffic speed prediction: A deep learning based approach using latent space mapping considering spatio-temporal dependencies](https://mlsanity.com/paper/2111.02115/) (2021)
- [A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles](https://mlsanity.com/paper/2111.12861/) (2021)
- [Machine Learning in Micromobility: A Systematic Review of Datasets, Techniques, and Applications](https://mlsanity.com/paper/2508.16135/) (2025)

## Abstract (arXiv)

The goal of this work is to reduce driver's range anxiety by estimating the real-time energy consumption of electric vehicles using deep convolutional neural network. The real-time estimate can be used to accurately predict the remaining range for the vehicle and hence, can reduce driver's range anxiety. In contrast to existing techniques, the non-linearity and complexity induced by the combination of influencing factors make the problem more suitable for a deep learning approach. The proposed approach requires three parameters namely, vehicle speed, tractive effort and road elevation. Multiple experiments with different variants are performed to explore the impact of number of layers and input feature descriptors. The comparison of proposed approach and five of the existing techniques show that the proposed model performed consistently better than existing techniques with lowest error.