A Deep Reinforcement Learning Based Energy Management Strategy for Fuel-Cell Electric UAV

Gao, Qinxiang; Lei, Tao; Deng, F.; Min, Zhihao; Yao, Wenli; Zhang, Xiaobin

doi:10.1109/icopesa54515.2022.9754414

2022 International Conference on Power Energy Systems and Applications (ICoPESA) 2022

DOI: 10.1109/icopesa54515.2022.9754414

|View full text |Cite

A Deep Reinforcement Learning Based Energy Management Strategy for Fuel-Cell Electric UAV

Qinxiang Gao

Tao Lei

F. Deng

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2024

Publication Types

Select...

Article6

Relationship

Self Cite0

Independent6

Authors

Journals

Cited by 6 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also reports of some of the other significant energy management solutions for HPS. Adaptive control [17], heuristic algorithm modeling [18], artificial neural network [19], dynamic optimum control [20] and Hinfinity control [21] are among them. These techniques are relatively difficult and need enormous analyses, which may influence the smart energy platform's reaction time.…”

mentioning

confidence: 99%

Design and Analysis of a Fuel Cell and Batteries in Energy Production for Electric Vehicle

Deb

Alam

Rahman

et al. 2023

IJEE

View full text Add to dashboard Cite

The world's most economically developed countries are facing an energy crisis caused by geopolitical instability, rising energy costs, global stock disruptions, and a shift towards lowcarbon energy sources that has yet to be fully realized. Electrification of the transportation industry offers the advantages of increased energy efficiency and reduced local pollutants. Electric Vehicles (EVs) are environmentally friendly because they reduce fossil fuels usage even zero consumption, need fewer maintenance requirements, and lower operating costs than the vehicles powered by gasoline or diesel. However, this study focuses on comparing various energy management strategies (EMS) for a backup energy supply system for EVs. The hybrid power system (HPS) considered in this study includes DC-DC and DC-AC synchronous converters, as well as supercapacitors, batteries, and fuel cells. The EMS analyzed includes state machine control, classical proportional-integral control, equivalent consumption minimization, frequency decoupling, rule-based fuzzy logic, and fuzzy logic control. The HPS's efficiency, hydrogen fuel, supercapacitor or battery state of charge levels, and overall performance are evaluated as primary efficiency criteria. Additionally, the HPS not only increases system energy but also reduces the number of pack batteries required. This study designs and constructs the combined power systems to enhance EV power schemes with rechargeable battery power supplies. The results show that a 6-kW fuel cell hybrid increases the power system capacity to 408 kWh. Moreover, a novel method based on wavelet transforms of the instantaneous power of each energy source is used to quantify the stressors on each energy source that impact its life cycle. To validate all analyses and performance, a simulation model and an experimental test bench are created. Finally, simulation results demonstrate a synchronous converter with a 6-kW output power and 96% efficiency, validating the optimization results.

show abstract

mentioning

confidence: 99%

Design and Analysis of a Fuel Cell and Batteries in Energy Production for Electric Vehicle

Deb

Alam

Rahman

et al. 2023

IJEE

View full text Add to dashboard Cite

show abstract

Critical review on integrated real-time energy management strategy and digital twin applied to hybrid electric UAVs

Cyrille,

Jean Calvin,

Ghislain

et al. 2024

Electr Eng

View full text Add to dashboard Cite

Artificial intelligence (AI) advancements for transportation security: in-depth insights into electric and aerial vehicle systems

Kumar,

Altalbe

2024

Environ Dev Sustain

View full text Add to dashboard Cite

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

A Deep Reinforcement Learning Based Energy Management Strategy for Fuel-Cell Electric UAV

Cited by 6 publications

References 20 publications

Design and Analysis of a Fuel Cell and Batteries in Energy Production for Electric Vehicle

Design and Analysis of a Fuel Cell and Batteries in Energy Production for Electric Vehicle

Critical review on integrated real-time energy management strategy and digital twin applied to hybrid electric UAVs

Artificial intelligence (AI) advancements for transportation security: in-depth insights into electric and aerial vehicle systems

Contact Info

Product

Resources

About