Cooperative energy management and eco-driving of plug-in hybrid electric vehicle via multi-agent reinforcement learning

Wang, Yong; Wu, Yao; Tang, Yingjuan; Li, Qin; He, Hongwen

doi:10.1016/j.apenergy.2022.120563

Cited by 72 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Minimizing permanent losses in heat exchangers may enhance energy efficiency in manufacturing operations [49]. Wherein, due to the unpredictability of renewable energy, the fluctuating energy demands of process units, and the rate of failure of energy conversion devices, the dependability of industrial hybrid energy systems is severely compromised, thereby impeding their promotion and implementation [50].…”

Section: Studies Of Industrial Applicationsmentioning

confidence: 99%

Multiple Heat Recovery System for an Industrial Thermal Peeling Press Machine—Experimental Study with Energy and Economic Analyses

Farhat,

Khaled,

Faraj

et al. 2024

Energies

View full text Add to dashboard Cite

The enhancement of energy systems in industrial zones is attracting the attention of researchers from all over the world. At the same time, optimization and advancement in heat recovery systems are now generating major interest in the energy sector. In this context, the present study suggests a new multiple heat recovery system should be applied to an industrial thermal peeling press machine. The new system consists of multiple sources of energy: the heat excess in the chimney, the exhaust gas of the chimney, and the exhaust gas of the boiler. To proceed with testing the potential of the suggested system, a hydraulic thermal peel press machine in the wood industry undergoes different tests to achieve the best configuration that will enable this machine to reach its operational temperature when heating. Five test configurations are proposed, designed, and applied experimentally on this machine. Many parameters were effective during the experimental tests, such as water flow rate, ambient air temperature, and initial water temperature. It was found that the application of the multiple heat recovery system increases the rate of heating from around 7 °C/min to around 13 °C/min. In terms of energy and economy, the “chimney + boiler only” configuration proved to be the best system to apply during the fall and winter seasons.

show abstract

Section: Studies Of Industrial Applicationsmentioning

confidence: 99%

Multiple Heat Recovery System for an Industrial Thermal Peeling Press Machine—Experimental Study with Energy and Economic Analyses

Farhat,

Khaled,

Faraj

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…However, there is still a need for more research and development into how resistant the NMPC model is to uncertainties such as unmodeled dynamics and disturbances. Furthermore, fuel consumption is significantly reduced by the Multi-Agent Reinforcement Learning (MARL) based optimal energy-saving strategy for Hybrid Electric Vehicles (HEVs) presented by [141]. Nonetheless, optimization and practical application issues may impact the method's adaptability, which can be considered for future research.…”

Section: B Development Strategies Of Bcu For Mobility Energy Efficiencymentioning

confidence: 99%

“…Robustness and Real-World Implementation: Robustness of the proposed NMPC has uncertainty concerns like unmodeled dynamics and disturbances, which could be explored in the future to improve the NMPC's robustness [141] Multi-Agent Reinforcement Learning (MARL) based optimal energysaving strategy for Hybrid Electric Vehicle (HEV)…”

Section: Comparison Of Integrated Ecu Algorithms For Mobility Energy ...mentioning

confidence: 99%

Evolving Electric Mobility Energy Efficiency: In-Depth Analysis of Integrated Electronic Control Unit Development in Electric Vehicles

Naqvi,

Jamil,

Iqbal

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The integrated Electronic Control Unit (ECU) plays a pivotal role in optimizing energy efficiency within electric vehicles (EVs) by coordinating various subsystems, including the Vehicle Control Unit (VCU), Electrical Power Steering (EPS), Electronic Stability Control (ESC), and Body Control Unit (BCU). Our comprehensive review deeply explores the various aspects of integrated ECUs and their sub-disciplines, emphasizing development approaches and algorithms specifically designed for mobility energy efficiency.The study shows the effect of various control units on energy efficiency by carefully examining case studies and real-world applications. Employing a critical assessment, the paper examines the advantages and disadvantages of various control systems utilized in electric vehicles (EVs), providing insight into their effectiveness in various situations. The presented study is typically related to the relationship between ECUs and their sub-branches through an integrated approach. By comparing current control approaches, the study offers a deep knowledge of the role of these units in improving vehicle performance, stability, and overall control. Furthermore, we evaluate the strengths and limitations of integrated ECU algorithms in the context of EV control by comparing them in a fair amount of detail. We identify important research gaps by integrating knowledge of multiple control areas in EV. The research effort will give researchers a path forward and make it possible to pinpoint the prospective dimensions that need further exploration in advancing the area of integrated ECUs in EVs.

show abstract

“…This approach speeds up the learning process for HEV energy management while still achieving excellent control performance. Wang et al [4] developed a multiagent RL strategy focused on optimizing energy savings in HEVs. This system enables cooperative control of both the powertrain and car-following behavior, allowing for minimized energy consumption while maintaining a safe following distance.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning-based energy management for hybrid electric vehicle enhanced by velocity prediction

Luo,

Bai,

Wang

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This paper proposes a novel approach for optimal energy management of engine-battery hybrid electric systems. It addresses two limitations in existing research, namely inaccurate speed prediction and low control accuracy. The proposed method integrates Markov theory and clustering theory to achieve high-precision prediction of future velocity under diverse driving styles. Furthermore, a learning-based energy management strategy is developed using a deep deterministic strategy gradient algorithm. This strategy considers the predicted velocity and aims to minimize engine fuel consumption, battery state fluctuations, and engine start-stop occurrences. Simulation results demonstrate that the proposed algorithm achieves near-optimal performance under specific operating conditions.

show abstract

Cooperative energy management and eco-driving of plug-in hybrid electric vehicle via multi-agent reinforcement learning

Cited by 72 publications

References 61 publications

Multiple Heat Recovery System for an Industrial Thermal Peeling Press Machine—Experimental Study with Energy and Economic Analyses

Multiple Heat Recovery System for an Industrial Thermal Peeling Press Machine—Experimental Study with Energy and Economic Analyses

Evolving Electric Mobility Energy Efficiency: In-Depth Analysis of Integrated Electronic Control Unit Development in Electric Vehicles

Reinforcement learning-based energy management for hybrid electric vehicle enhanced by velocity prediction

Contact Info

Product

Resources

About