AJUNTAMENT D'ALCOI
Website
Generalitat Valenciana
Website
Ayuntamiento de Valencia
Website
Cicloplast
Website
Ayuntamiento de Onil
Website
Anarpla
Website
Ayuntamiento de Mislata
Website
nlWA, North London Waste Authority
Website
Ayuntamiento de Salinas
Website
Zicla
Website
Fondazione Ecosistemi
Website
PEFC
Website
ALQUIENVAS
Website
DIPUTACI� DE VAL�NCIA
Website
AYUNTAMIENTO DE REQUENA
Website
UNIVERSIDAD DE ZARAGOZA
Website
OBSERVATORIO CONTRATACIÓN PÚBLICA
Website
AYUNTAMIENTO DE PAIPORTA
Website
AYUNTAMIENTO DE CUENCA
Website
BERL� S.A.
Website
CM PLASTIK
Website
TRANSFORMADORES INDUSTRIALES ECOL�GICOS
INDUSTRIAS AGAPITO
Website
RUBI KANGURO
Website
If you want to support our LIFE project as a STAKEHOLDER, please contact with us: life-future-project@aimplas.es
In this section, you can access to the latest technical information related to the FUTURE project topic.
The application of machine learning based energy management strategy in multi-mode plug-in hybrid electric vehicle, part I: Twin Delayed Deep Deterministic Policy Gradient algorithm design for hybrid mode
As the performance of Energy Management Strategy (EMS) is crucial for the energy efficiency of Hybrid Electric Vehicles (HEVs), a Deep Reinforcement Learning (DRL)-based algorithm, namely Twin Delayed Deep Deterministic Policy Gradient (TD3), is adopted to design EMS for the power Charge-Sustained (CS) stage of a multi-mode plug-in Hybrid Electric Vehicle (HEV). In addition, EMS is improved by combining the actor-network of TD3 with Gumbel-Softmax to realize mode selection and torque distribution simultaneously, which is a discrete (mode)-continuous (engine speed) hybrid action space and not applicable in original TD3. To reduce the unreasonable exploration of agents in discrete action, a rule-based mode control mechanism (RBMCM) is designed and involved in EMS. The improved algorithm speeds up the learning process and achieves better fuel economy. Simulation results show that the gap between the proposed strategy and the benchmark dynamic programming (DP) is reduced to 2.55% in the selected training cycle. Regarding the unknown testing cycles, the fuel economy of agents trained by the improved method overperforms traditional DRL-based EMS when it reaches more than 90% of the DP-based benchmarking. In conclusion, the proposed method provides a theoretical foundation for the solution of the hybrid space optimization problem for hybrid systems.
» Author: Changcheng Wu, Jiageng Ruan, Hanghang Cui, Bin Zhang, Tongyang Li, Kaixuan Zhang
» Reference: Energy, Volume 262, Part B
» Publication Date: 01/01/2023
C/ Gustave Eiffel, 4
(València Parc Tecnològic) - 46980
PATERNA (Valencia) - SPAIN
(+34) 96 136 60 40
Project Management department - Sustainability and Industrial Recovery
life-future-project@aimplas.es