| Home | KSAE | E-Submission | Sitemap | Contact Us |  
top_img
International Journal of Automotive Technology > Volume 23(4); 2022 > Article
International Journal of Automotive Technology 2022;23(4): 967-981.
doi: https://doi.org/10.1007/s12239-022-0084-0
HYPERPARAMETERS OF Q-LEARNING ALGORITHM ADAPTING TO THE DRIVING CYCLE BASED ON KL DRIVING CYCLE RECOGNITION
Yanli Yin 1,2, Xuejiang Huang 1, Xiaoliang Pan 3, Sen Zhan 1, Yongjuan Ma 1, Xinxin Zhang 1
1School of Mechatronics & Automobile Engineering, Chongqing Jiao Tong University
2Beiben Trucks Group Co., Ltd.
3Chongqing Changan Automobile Stock Co., Ltd.
PDF Links Corresponding Author.  Yanli Yin  , Email. 990201200009@cqjtu.edu.cn
ABSTRACT
As an effective reinforcement learning (RL) algorithm, Q-learning has been applied to energy management strategy of hybrid electric vehicle (HEV) in recent years. In the existing literatures, the values of three hyperparameters based on Q-learning are all given in advance, which are respectively exploratory rate ε, discount factor γ and learning rate α. However, different values of hyperparameters will influence on fuel economy of the vehicle and offline computation speed. In this paper, it is proposed that the method of optimization on hyperparameters adapting to driving cycle. Firstly, the mathematical model between three hyperparameters and iteration times is established based on inherent regularity of hyperparameters influencing on vehicle performance respectively. Secondly, it is determined that the optimal changing index k_index of iteration number based on Q-learning corresponding to typical driving cycles. Finally, the simulation model of Yubei District in Chongqing is constructed based on the method of Kullback-Leibler (KL) driving cycle identification. The simulation results indicate that equivalent fuel consumption of the proposed strategy is reduced by 0.4 % and the offline operation time is reduced by 6 s. It can be concluded that the proposed strategy can not only improve fuel economy of the vehicle, but also accelerate the computation speed.
Key Words: Q-Learning, Hyperparameters, Adapting to, Kullback-Leibler (KL), Computation speed, Fuel economy
TOOLS
Preview  Preview
Full text via DOI  Full text via DOI
Download Citation  Download Citation
CrossRef TDM  CrossRef TDM
  Print
Share:      
METRICS
0
Scopus
288
View
24
Download
Related article
Editorial Office
21 Teheran-ro 52-gil, Gangnam-gu, Seoul 06212, Korea
TEL: +82-2-564-3971   FAX: +82-2-564-3973   E-mail: manage@ksae.org
About |  Browse Articles |  Current Issue |  For Authors and Reviewers
Copyright © The Korean Society of Automotive Engineers.                 Developed in M2PI
Close layer
prev next