Home / Current Issue / Paper 1718015
A Comprehensive Survey on Fuel Consumption Optimization: Machine Learning, Energy Management, and Emerging Powertrain Technologies
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
DOI: https://doi.org/10.64388/IREV9I11-1718015
Abstract
This paper presents a comprehensive survey of recent advances in fuel consumption optimization across multiple transportation domains, synthesizing findings from 18 peer-reviewed studies published between 2007 and 2025. The reviewed literature spans data-driven prediction models for marine vessels, equivalent consumption minimization strategies (ECMS) for fuel cell hybrid vehicles (FCHVs), fuzzy logic and particle swarm optimization for range extender vehicles, alternator control strategies for conventional vehicles, energy consumption standard analysis, hydrogen consumption studies under varying state-of-charge (SOC) conditions, sail-assisted ship routing, real-time fuel monitoring systems, comparative powertrain analysis across battery electric (BEV), fuel cell (FCEV), and internal combustion engine (ICEV) vehicles, machine learning models for fuel prediction, eco-driving cooperative strategies, and hardware-in-the-loop (HIL) validation of hybrid architectures. Key findings demonstrate that hybrid machine learning and physics-informed approaches consistently outperform purely rule-based strategies, achieving fuel savings of 7–20% across diverse vehicle and vessel classes. Emerging trends include connected vehicle intelligence (V2X), reinforcement learning-based energy management, and federated learning for privacy-preserving fleet optimization. This survey identifies critical research gaps and outlines a unified framework for next-generation fuel consumption optimization systems.
Keywords
Fuel Consumption Optimization, Machine Learning, Energy Management, Hybrid Electric Vehicles, Fuel Cell Vehicles, Eco-Driving, Neural Networks, ECMS, Particle Swarm Optimization, V2X, Maritime Energy Efficiency
How to cite this paper
@article{1718015,
author = {Shankar G},
title = {A Comprehensive Survey on Fuel Consumption Optimization: Machine Learning, Energy Management, and Emerging Powertrain Technologies},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2963-2972},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718015.pdf},
abstract = {This paper presents a comprehensive survey of recent advances in fuel consumption optimization across multiple transportation domains, synthesizing findings from 18 peer-reviewed studies published between 2007 and 2025. The reviewed literature spans data-driven prediction models for marine vessels, equivalent consumption minimization strategies (ECMS) for fuel cell hybrid vehicles (FCHVs), fuzzy logic and particle swarm optimization for range extender vehicles, alternator control strategies for conventional vehicles, energy consumption standard analysis, hydrogen consumption studies under varying state-of-charge (SOC) conditions, sail-assisted ship routing, real-time fuel monitoring systems, comparative powertrain analysis across battery electric (BEV), fuel cell (FCEV), and internal combustion engine (ICEV) vehicles, machine learning models for fuel prediction, eco-driving cooperative strategies, and hardware-in-the-loop (HIL) validation of hybrid architectures. Key findings demonstrate that hybrid machine learning and physics-informed approaches consistently outperform purely rule-based strategies, achieving fuel savings of 7–20% across diverse vehicle and vessel classes. Emerging trends include connected vehicle intelligence (V2X), reinforcement learning-based energy management, and federated learning for privacy-preserving fleet optimization. This survey identifies critical research gaps and outlines a unified framework for next-generation fuel consumption optimization systems.},
keywords = {Fuel Consumption Optimization, Machine Learning, Energy Management, Hybrid Electric Vehicles, Fuel Cell Vehicles, Eco-Driving, Neural Networks, ECMS, Particle Swarm Optimization, V2X, Maritime Energy Efficiency},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1718015}
}