scholarly journals An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yanli Yin ◽  
Yan Ran ◽  
Liufeng Zhang ◽  
Xiaoliang Pan ◽  
Yong Luo
Keyword(s):  
Reinforcement Learning ◽  
Electric Vehicle ◽  
Energy Management ◽  
Control Strategy ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Power Demand ◽  
Energy Management Strategy ◽  
Driving Cycles ◽  
Mild Hybrid

For global optimal control strategy, it is not only necessary to know the driving cycle in advance but also difficult to implement online because of its large calculation volume. As an artificial intelligent-based control strategy, reinforcement learning (RL) is applied to an energy management strategy of a super-mild hybrid electric vehicle. According to time-speed datasets of sample driving cycles, a stochastic model of the driver’s power demand is developed. Based on the Markov decision process theory, a mathematical model of an RL-based energy management strategy is established, which assumes the minimum cumulative return expectation as its optimization objective. A policy iteration algorithm is adopted to obtain the optimum control policy that takes the vehicle speed, driver’s power demand, and state of charge (SOC) as the input and the engine power as the output. Using a MATLAB/Simulink platform, CYC_WVUCITY simulation model is established. The results show that, compared with dynamic programming, this method can not only adapt to random driving cycles and reduce fuel consumption of 2.4%, but also be implemented online because of its small calculation volume.

scholarly journals Research on energy management strategy considering battery life for plug-in hybrid electric vehicle

2018 ◽  
Vol 10 (9) ◽  
pp. 168781401879776 ◽  
Author(s):  
Jianjun Hu ◽  
Zhihua Hu ◽  
Xiyuan Niu ◽  
Qin Bai
Keyword(s):  
Fuel Consumption ◽  
Electric Vehicle ◽  
Energy Management ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Battery Life ◽  
Energy Management Strategy ◽  
Driving Cycles ◽  
Comprehensive Test ◽  
Hybrid Electric

To improve the fuel efficiency and battery life-span of plug-in hybrid electric vehicle, the energy management strategy considering battery life decay is proposed. This strategy is optimized by genetic algorithm, aiming to reduce the fuel consumption and battery life decay of plug-in hybrid electric vehicle. Besides, to acquire better drive-cycle adaptability, driving patterns are recognized with probabilistic neural network. The standard driving cycles are divided into urban congestion cycle, highway cycle, and urban suburban cycle; the optimized energy management strategies in three representative driving cycles are established; meanwhile, a comprehensive test driving cycle is constructed to verify the proposed strategies. The results show that adopting the optimized control strategies, fuel consumption, and battery’s life decay drop by 1.9% and 3.2%, respectively. While using the drive-cycle recognition, the features of different driving cycles can be identified, and based on it, the vehicle can choose appropriate control strategy in different driving conditions. In the comprehensive test driving cycle, after recognizing driving cycles, fuel consumption and battery’s life decay drop by 8.6% and 0.3%, respectively.

scholarly journals Energy Management Strategy for a Hybrid Electric Vehicle Based on Deep Reinforcement Learning

2018 ◽  
Vol 8 (2) ◽  
pp. 187 ◽  
Author(s):  
Yue Hu ◽  
Weimin Li ◽  
Kun Xu ◽  
Taimoor Zahid ◽  
Feiyan Qin ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Electric Vehicle ◽  
Energy Management ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Energy Management Strategy ◽  
Hybrid Electric

Energy management strategy of intelligent plug-in split hybrid electric vehicle based on deep reinforcement learning with optimized path planning algorithm

2021 ◽  
pp. 095440702110368
Author(s):  
Shengguang Xiong ◽  
Yishi Zhang ◽  
Chaozhong Wu ◽  
Zhijun Chen ◽  
Jiankun Peng ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Electric Vehicle ◽  
Energy Management ◽  
Management Strategy ◽  
Hybrid Electric Vehicle ◽  
Energy Management Strategy ◽  
Planning Algorithm ◽  
Hybrid Electric ◽  
Path Planning Algorithm

Energy management is a fundamental task and challenge of plug-in split hybrid electric vehicle (PSHEV) research field because of the complicated powertrain and variable driving conditions. Motivated by the foresight of intelligent vehicle and the breakthroughs of deep reinforcement learning framework, an energy management strategy of intelligent plug-in split hybrid electric vehicle (IPSHEV) based on optimized Dijkstra’s path planning algorithm (ODA) and reinforcement learning Deep-Q-Network (DQN) is proposed to cope with the challenge. Firstly, a gray model is used to predict the traffic congestion of each road and the length of each road calculated in the traditional Dijkstra’s algorithm (DA) is modified for path planning. Secondly, on the basis of the predicted velocity of each road, the planned velocity is constrained by the vehicle dynamics to ensure the driving security. Finally, the planning information is inputted to DQN to control the working mode of IPSHEV, so as to achieve energy saving of the vehicle. The simulation results show the optimized path planning algorithm and proposed energy management strategy is feasible and effective.

scholarly journals Energy Management for a Power-Split Plug-In Hybrid Electric Vehicle Based on Reinforcement Learning

2018 ◽  
Vol 8 (12) ◽  
pp. 2494 ◽  
Author(s):  
Zheng Chen ◽  
Hengjie Hu ◽  
Yitao Wu ◽  
Renxin Xiao ◽  
Jiangwei Shen ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Electric Vehicle ◽  
Energy Management ◽  
Control Strategy ◽  
Hybrid Electric Vehicle ◽  
Gasoline Engine ◽  
Energy Management Strategy ◽  
Optimal Control Strategy ◽  
Power Split ◽  
Hybrid Electric

This paper proposes an energy management strategy for a power-split plug-in hybrid electric vehicle (PHEV) based on reinforcement learning (RL). Firstly, a control-oriented power-split PHEV model is built, and then the RL method is employed based on the Markov Decision Process (MDP) to find the optimal solution according to the built model. During the strategy search, several different standard driving schedules are chosen, and the transfer probability of the power demand is derived based on the Markov chain. Accordingly, the optimal control strategy is found by the Q-learning (QL) algorithm, which can decide suitable energy allocation between the gasoline engine and the battery pack. Simulation results indicate that the RL-based control strategy could not only lessen fuel consumption under different driving cycles, but also limit the maximum discharge power of battery, compared with the charging depletion/charging sustaining (CD/CS) method and the equivalent consumption minimization strategy (ECMS).

Sign in / Sign up

Export Citation Format

Share Document