Machine Learning and Deep Learning Approaches for Energy Management in Smart Grid 3.0 DOI
Amitkumar V. Jha, Bhargav Appasani, Deepak Kumar Gupta

et al.

Power systems, Journal Year: 2023, Volume and Issue: unknown, P. 121 - 151

Published: Jan. 1, 2023

Language: Английский

Reinforcement Learning-Based Energy Management for Hybrid Power Systems: State-of-the-Art Survey, Review, and Perspectives DOI Creative Commons

Xiaolin Tang,

Jiaxin Chen, Yechen Qin

et al.

Chinese Journal of Mechanical Engineering, Journal Year: 2024, Volume and Issue: 37(1)

Published: May 17, 2024

Abstract The new energy vehicle plays a crucial role in green transportation, and the management strategy of hybrid power systems is essential for ensuring energy-efficient driving. This paper presents state-of-the-art survey review reinforcement learning-based strategies systems. Additionally, it envisions outlook autonomous intelligent electric vehicles, with learning as foundational technology. First all, to provide macro view historical development, brief history deep learning, presented form timeline. Then, comprehensive are conducted by collecting papers from mainstream academic databases. Enumerating most contributions based on three main directions—algorithm innovation, powertrain environment innovation—provides an objective research status. Finally, advance application future plans positioned “Alpha HEV” envisioned, integrating Autopilot energy-saving control.

Language: Английский

Citations

16
Recent progress on energy management strategies for hybrid electric vehicles DOI
Mingzhang Pan,

Sheng Cao,

Zhiqing Zhang

et al.

Journal of Energy Storage, Journal Year: 2025, Volume and Issue: 116, P. 115936 - 115936

Published: March 7, 2025

Language: Английский

Citations

2
An adaptive traffic signal control scheme with Proximal Policy Optimization based on deep reinforcement learning for a single intersection DOI
Lijuan Wang, Guoshan Zhang, Qiaoli Yang

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 149, P. 110440 - 110440

Published: March 11, 2025

Language: Английский

Citations

1
Deep Deterministic Policy Gradient Virtual Coupling control for the coordination and manoeuvring of heterogeneous uncertain nonlinear High-Speed Trains DOI Creative Commons
Giacomo Basile, Dario Giuseppe Lui, Alberto Petrillo

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108120 - 108120

Published: Feb. 24, 2024

Language: Английский

Citations

7
Remaining driving range prediction for electric vehicles: Key challenges and outlook DOI Creative Commons
Peng Mei, Hamid Reza Karimi, Cong Huang

et al.

IET Control Theory and Applications, Journal Year: 2023, Volume and Issue: 17(14), P. 1875 - 1893

Published: April 30, 2023

Abstract Remaining driving range (RDR) research has continued to consistently evolve with the development of electric vehicles (EVs). Accurate RDR prediction is a promising approach alleviate distance anxiety when power battery technology not yet fully matured. This paper first introduces motivation prediction, summarizes previous progress, and classifies influencing factors RDR. Second, conduct analysis on physical model EVs, mainly including vehicle models. Based model, energy flow problem EVs analyzed discussed. Third, four key challenges are summarized: state estimation, behavior classification recognition, condition speed calculation method. Finally, given faced by RDR, method based vehicle‐cloud collaboration proposed, which combines advantages cloud computing machine learning provide further trends.

Language: Английский

Citations

11
Optimal power-split of hybrid energy storage system using Pontryagin’s minimum principle and deep reinforcement learning approach for electric vehicle application DOI
Praveen Nambisan, Munmun Khanra

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 135, P. 108769 - 108769

Published: June 17, 2024

Language: Английский

Citations

4
Battery state estimation methods and management system under vehicle–cloud collaboration: A Survey DOI Creative Commons
Peng Mei, Hamid Reza Karimi, Jiale Xie

et al.

Renewable and Sustainable Energy Reviews, Journal Year: 2024, Volume and Issue: 206, P. 114857 - 114857

Published: Aug. 30, 2024

With the development of new energy vehicles, EVs have received ever-increasing research attention as an essential strategic orientation for world to face climate change and issues. significant energy-saving emission-reduction advantages, but power battery state estimation accuracy has always been a bottleneck restricting its promotion. Centered on cloud management control methodology, this work systematically examines models, formulates life safety strategies, investigates integration technology within advanced electronic electrical architectures. Firstly, overall framework device–cloud fusion is introduced. Secondly, aiming at complex problem estimation, models methods vehicle are summarized. Then, joint method outlined states, including charge health. Finally, viable cloud-based solution elucidated through comprehensive comparison analysis current technologies' strengths limitations. This offers theoretical advancing technology.

Language: Английский

Citations

4
Optimizing energy management in electric vehicles with hybrid battery systems using the GTOA-DRCNN method DOI

K. V. Kandaswamy,

V. Rengarajan,

Bhavana Narain

et al.

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 100, P. 113352 - 113352

Published: Sept. 18, 2024

Language: Английский

Citations

4
Reinforcement learning algorithm for improving speed response of a five-phase permanent magnet synchronous motor based model predictive control DOI Creative Commons
Ahmed Hassan, Jafar Ababneh,

Hani Attar

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0316326 - e0316326

Published: Jan. 3, 2025

Enhancing the performance of 5ph-IPMSM control plays a crucial role in advancing various innovative applications such as electric vehicles. This paper proposes new reinforcement learning (RL) algorithm based twin-delayed deep deterministic policy gradient (TD3) to tune two cascaded PI controllers five-phase interior permanent magnet synchronous motor (5ph-IPMSM) drive system model predictive (MPC). The main purpose methodology is optimize speed response either constant torque region or power region. responses obtained using RL are compared with those four most recent metaheuristic optimization techniques (MHOT) which Transit Search (TS), Honey Badger Algorithm (HBA), Dwarf Mongoose (DM), and Dandelion-Optimizer (DO) techniques. terms settling time, rise maximum time overshoot percentage. It found that suggested TD3 give minimum relatively low values for max percentage makes provide superior from MHOT. MATLAB SIMULINK package.

Language: Английский

Citations

0
A deep reinforcement learning control framework for a partially observable system: experimental validation on a rotary flexible link system DOI

V. Joshi Kumar,

Vinodh Kumar Elumalai

International Journal of Systems Science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 25

Published: Feb. 28, 2025

Language: Английский

Citations

0