Deep Learning-Based Analysis of Power Consumption in Gasoline, Electric, and Hybrid Vehicles

2025-08-11

AI Summary

To address the lack of generalizable, high-accuracy power consumption models for gasoline, electric, and hybrid electric vehicles (HEVs), this paper proposes a scalable, data-driven framework. We first unify the modeling of their distinct powertrain dynamics and construct a dynamic feature set tailored for both instantaneous and cumulative power estimation. A multi-model regression ensemble integrates XGBoost, random forests, LSTM, and Transformer architectures, augmented with uncertainty quantification. Critically, the LSTM–Transformer synergy captures complex energy management strategies, substantially improving prediction robustness—particularly for HEVs and EVs. Experimental results demonstrate an instantaneous power estimation error of order 10⁻³ for gasoline vehicles and cumulative energy errors below 3.0%, 4.1%, and 2.1% for gasoline, hybrid, and electric vehicles, respectively. These outcomes validate the framework’s cross-platform generalizability and engineering applicability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate power consumption prediction is crucial for improving efficiency and reducing environmental impact, yet traditional methods relying on specialized instruments or rigid physical models are impractical for large-scale, real-world deployment. This study introduces a scalable data-driven method using powertrain dynamic feature sets and both traditional machine learning and deep neural networks to estimate instantaneous and cumulative power consumption in internal combustion engine (ICE), electric vehicle (EV), and hybrid electric vehicle (HEV) platforms. ICE models achieved high instantaneous accuracy with mean absolute error and root mean squared error on the order of $10^{-3}$, and cumulative errors under 3%. Transformer and long short-term memory models performed best for EVs and HEVs, with cumulative errors below 4.1% and 2.1%, respectively. Results confirm the approach's effectiveness across vehicles and models. Uncertainty analysis revealed greater variability in EV and HEV datasets than ICE, due to complex power management, emphasizing the need for robust models for advanced powertrains.

Problem

• Accurate power consumption prediction for vehicle efficiency
• Scalable data-driven method for ICE, EV, HEV power estimation
• Robust models needed for complex EV and HEV power management

Innovation

• Deep learning for power consumption prediction
• Dynamic feature sets with machine learning
• Transformer and LSTM models for EVs