Human-like Energy Management Based on Deep Reinforcement Learning and Historical Driving Experiences

07/16/2020
by   Teng Liu, et al.
0

Development of hybrid electric vehicles depends on an advanced and efficient energy management strategy (EMS). With online and real-time requirements in mind, this article presents a human-like energy management framework for hybrid electric vehicles according to deep reinforcement learning methods and collected historical driving data. The hybrid powertrain studied has a series-parallel topology, and its control-oriented modeling is founded first. Then, the distinctive deep reinforcement learning (DRL) algorithm, named deep deterministic policy gradient (DDPG), is introduced. To enhance the derived power split controls in the DRL framework, the global optimal control trajectories obtained from dynamic programming (DP) are regarded as expert knowledge to train the DDPG model. This operation guarantees the optimality of the proposed control architecture. Moreover, the collected historical driving data based on experienced drivers are employed to replace the DP-based controls, and thus construct the human-like EMSs. Finally, different categories of experiments are executed to estimate the optimality and adaptability of the proposed human-like EMS. Improvements in fuel economy and convergence rate indicate the effectiveness of the constructed control structure.

READ FULL TEXT

page 2

page 4

research
07/16/2020

Transfer Deep Reinforcement Learning-enabled Energy Management Strategy for Hybrid Tracked Vehicle

This paper proposes an adaptive energy management strategy for hybrid el...
research
03/06/2020

Smart Train Operation Algorithms based on Expert Knowledge and Reinforcement Learning

During recent decades, the automatic train operation (ATO) system has be...
research
09/07/2020

Data-Driven Transferred Energy Management Strategy for Hybrid Electric Vehicles via Deep Reinforcement Learning

Real-time applications of energy management strategies (EMSs) in hybrid ...
research
07/16/2020

Transferred Energy Management Strategies for Hybrid Electric Vehicles Based on Driving Conditions Recognition

Energy management strategies (EMSs) are the most significant components ...
research
05/25/2021

Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles

Connected and Automated Hybrid Electric Vehicles have the potential to r...
research
03/16/2023

Energy Management of Multi-mode Plug-in Hybrid Electric Vehicle using Multi-agent Deep Reinforcement Learning

The recently emerging multi-mode plug-in hybrid electric vehicle (PHEV) ...
research
02/13/2023

A Lifetime Extended Energy Management Strategy for Fuel Cell Hybrid Electric Vehicles via Self-Learning Fuzzy Reinforcement Learning

Modeling difficulty, time-varying model, and uncertain external inputs a...

Please sign up or login with your details

Forgot password? Click here to reset