Actor-Critic TD3-based Deep Reinforcement Learning for Energy Management Strategy of HEV

Basit Öğe Kaydı
dc.contributor.authorYazar, Ozan
dc.contributor.authorCoskun, Serdar
dc.contributor.authorLi, Lin
dc.contributor.authorZhang, Fengqi
dc.contributor.authorHuang, Cong
dc.date.accessioned2025-03-17T12:22:48Z
dc.date.available2025-03-17T12:22:48Z
dc.date.issued2023
dc.departmentTarsus Üniversitesi
dc.description5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023 -- 8 June 2023 through 10 June 2023 -- Istanbul -- 190025
dc.description.abstractIn the last decade, deep reinforcement learning (DRL) algorithms have been employed in the design of energy management strategy (EMS) for hybrid electric vehicles (HEVs). Investigation of the real-time applicability of DRL algorithms as an EMS is critical in terms of training time, fuel savings, and state-of-charge (SOC) sustainability. To this end, we propose a twin delayed deep deterministic policy gradient (TD3) algorithm that is an improved version of the deep deterministic policy gradient (DDPG) algorithm for HEV fuel savings. Compared to the existing Q-learning-based reinforcement learning and the deep Q-network-based and DDPG-based deep reinforcement algorithms, the proposed TD3 provides stable training efficiency, promising fuel economy, and a lower variation range of SOC charge sustainability under various drive cycles. © 2023 IEEE.
dc.description.sponsorshipTurkish Scientific and Technological Research Council, (121E260)
dc.identifier.doi10.1109/HORA58378.2023.10156727
dc.identifier.isbn979-835033752-5
dc.identifier.scopus2-s2.0-85165707248
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/HORA58378.2023.10156727
dc.identifier.urihttps://hdl.handle.net/20.500.13099/1399
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofHORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20250316
dc.subjectactor-critic network
dc.subjectDeep reinforcement learning
dc.subjectenergy management
dc.subjecthybrid electric vehicles
dc.subjectTD3 algoritm
dc.titleActor-Critic TD3-based Deep Reinforcement Learning for Energy Management Strategy of HEV
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu