REINFORCEMENT LEARNING–BASED ENERGY MANAGEMENT STRATEGY FOR A SERIES-PARALLEL HYBRID BUS

Han Xuefeng; He Hongwen; Wu Jingda; Peng Jiankun; Chen Rui

doi:10.46855/energy-proceedings-2495

REINFORCEMENT LEARNING–BASED ENERGY MANAGEMENT STRATEGY FOR A SERIES-PARALLEL HYBRID BUS

Han Xuefeng
, He Hongwen
, Wu Jingda
, Peng Jiankun
, Chen Rui

School of Mechanical Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

An energy management strategy based on double deep Q-learning algorithm is proposed for a SeriesParallel Hybrid Bus. The models of powertrain configuration and its main components are first established. Subsequently, a rule-based energy management strategy will be proposed. The China typical urban driving cycle (CTUDC) is used to evaluate the fuel economy performance of the two strategies studied in this paper. The simulation result indicates that the energy management strategy based on reinforcement learning decreased the fuel consumption by 7.3% per 100km compared to rulebased strategy.

Original language	English
Journal	Energy Proceedings
Volume	2
DOIs	https://doi.org/10.46855/energy-proceedings-2495
Publication status	Published - 2019
Event	11th International Conference on Applied Energy, ICAE 2019 - Västerås, Sweden Duration: 12 Aug 2019 → 15 Aug 2019

Keywords

Series-Parallel Hybrid Bus
double deep Q-learning
energy management
rule-based

Access to Document

10.46855/energy-proceedings-2495

Cite this

@article{28b25167d0584cc189c5211c2f560e95,

title = "REINFORCEMENT LEARNING–BASED ENERGY MANAGEMENT STRATEGY FOR A SERIES-PARALLEL HYBRID BUS",

abstract = "An energy management strategy based on double deep Q-learning algorithm is proposed for a SeriesParallel Hybrid Bus. The models of powertrain configuration and its main components are first established. Subsequently, a rule-based energy management strategy will be proposed. The China typical urban driving cycle (CTUDC) is used to evaluate the fuel economy performance of the two strategies studied in this paper. The simulation result indicates that the energy management strategy based on reinforcement learning decreased the fuel consumption by 7.3\% per 100km compared to rulebased strategy.",

keywords = "Series-Parallel Hybrid Bus, double deep Q-learning, energy management, rule-based",

author = "Han Xuefeng and He Hongwen and Wu Jingda and Peng Jiankun and Chen Rui",

note = "Publisher Copyright: {\textcopyright} 2019 ICAE.; 11th International Conference on Applied Energy, ICAE 2019 ; Conference date: 12-08-2019 Through 15-08-2019",

year = "2019",

doi = "10.46855/energy-proceedings-2495",

language = "English",

volume = "2",

journal = "Energy Proceedings",

issn = "2004-2965",

publisher = "Scanditale AB",

}

TY - JOUR

T1 - REINFORCEMENT LEARNING–BASED ENERGY MANAGEMENT STRATEGY FOR A SERIES-PARALLEL HYBRID BUS

AU - Xuefeng, Han

AU - Hongwen, He

AU - Jingda, Wu

AU - Jiankun, Peng

AU - Rui, Chen

PY - 2019

Y1 - 2019

N2 - An energy management strategy based on double deep Q-learning algorithm is proposed for a SeriesParallel Hybrid Bus. The models of powertrain configuration and its main components are first established. Subsequently, a rule-based energy management strategy will be proposed. The China typical urban driving cycle (CTUDC) is used to evaluate the fuel economy performance of the two strategies studied in this paper. The simulation result indicates that the energy management strategy based on reinforcement learning decreased the fuel consumption by 7.3% per 100km compared to rulebased strategy.

AB - An energy management strategy based on double deep Q-learning algorithm is proposed for a SeriesParallel Hybrid Bus. The models of powertrain configuration and its main components are first established. Subsequently, a rule-based energy management strategy will be proposed. The China typical urban driving cycle (CTUDC) is used to evaluate the fuel economy performance of the two strategies studied in this paper. The simulation result indicates that the energy management strategy based on reinforcement learning decreased the fuel consumption by 7.3% per 100km compared to rulebased strategy.

KW - Series-Parallel Hybrid Bus

KW - double deep Q-learning

KW - energy management

KW - rule-based

UR - https://www.scopus.com/pages/publications/85202635387

U2 - 10.46855/energy-proceedings-2495

DO - 10.46855/energy-proceedings-2495

M3 - Conference article

AN - SCOPUS:85202635387

SN - 2004-2965

VL - 2

JO - Energy Proceedings

JF - Energy Proceedings

T2 - 11th International Conference on Applied Energy, ICAE 2019

Y2 - 12 August 2019 through 15 August 2019

ER -

REINFORCEMENT LEARNING–BASED ENERGY MANAGEMENT STRATEGY FOR A SERIES-PARALLEL HYBRID BUS

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this