Intelligent SOC Reference Planning for Hybrid Electric Bus: A Hierarchical Predictive Energy Management Strategy

Ruchen Huang; Hongwen He; Xiangfei Meng

doi:10.46855/energy-proceedings-9445

Intelligent SOC Reference Planning for Hybrid Electric Bus: A Hierarchical Predictive Energy Management Strategy

Ruchen Huang
, Hongwen He^*
, Xiangfei Meng

^*Corresponding author for this work

School of Mechanical Engineering

Beijing Institute of Technology

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

Abstract

This paper proposes a hierarchical predictive energy management strategy (EMS) for hybrid electric bus (HEB) with an intelligent state of charge (SOC) reference planning method. In the cloud layer, future driving cycle is acquired through the intelligent transportation system (ITS) and well-trained neutral networks of deep deterministic policy gradient (DDPG) are extracted to plan the SOC reference trajectory quickly. In the vehicle layer, back propagation neutral network (BP-NN) is used to predict the velocity in a short term and an optimal controller is designed to distribute power flows optimally. Simulation results show that the fuel economy is improved by 2.12% compared with DDPG and reaches 97.43% of dynamic programming (DP).

Original language	English
Journal	Energy Proceedings
Volume	23
DOIs	https://doi.org/10.46855/energy-proceedings-9445
Publication status	Published - 2021
Event	13th International Conference on Applied Energy, ICAE 2021 - Bangkok, Thailand Duration: 29 Nov 2021 → 2 Dec 2021

Keywords

deep deterministic policy gradient
energy management
hybrid electric bus
intelligent SOC reference planning
model predictive control

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.46855/energy-proceedings-9445

Cite this

@article{8f4bfb96034a4a31bf20a6184bca18e2,

title = "Intelligent SOC Reference Planning for Hybrid Electric Bus: A Hierarchical Predictive Energy Management Strategy",

abstract = "This paper proposes a hierarchical predictive energy management strategy (EMS) for hybrid electric bus (HEB) with an intelligent state of charge (SOC) reference planning method. In the cloud layer, future driving cycle is acquired through the intelligent transportation system (ITS) and well-trained neutral networks of deep deterministic policy gradient (DDPG) are extracted to plan the SOC reference trajectory quickly. In the vehicle layer, back propagation neutral network (BP-NN) is used to predict the velocity in a short term and an optimal controller is designed to distribute power flows optimally. Simulation results show that the fuel economy is improved by 2.12\% compared with DDPG and reaches 97.43\% of dynamic programming (DP).",

keywords = "deep deterministic policy gradient, energy management, hybrid electric bus, intelligent SOC reference planning, model predictive control",

author = "Ruchen Huang and Hongwen He and Xiangfei Meng",

note = "Publisher Copyright: {\textcopyright} 2021 ICAE.; 13th International Conference on Applied Energy, ICAE 2021 ; Conference date: 29-11-2021 Through 02-12-2021",

year = "2021",

doi = "10.46855/energy-proceedings-9445",

language = "English",

volume = "23",

journal = "Energy Proceedings",

issn = "2004-2965",

publisher = "Scanditale AB",

}

TY - JOUR

T1 - Intelligent SOC Reference Planning for Hybrid Electric Bus

T2 - 13th International Conference on Applied Energy, ICAE 2021

AU - Huang, Ruchen

AU - He, Hongwen

AU - Meng, Xiangfei

PY - 2021

Y1 - 2021

N2 - This paper proposes a hierarchical predictive energy management strategy (EMS) for hybrid electric bus (HEB) with an intelligent state of charge (SOC) reference planning method. In the cloud layer, future driving cycle is acquired through the intelligent transportation system (ITS) and well-trained neutral networks of deep deterministic policy gradient (DDPG) are extracted to plan the SOC reference trajectory quickly. In the vehicle layer, back propagation neutral network (BP-NN) is used to predict the velocity in a short term and an optimal controller is designed to distribute power flows optimally. Simulation results show that the fuel economy is improved by 2.12% compared with DDPG and reaches 97.43% of dynamic programming (DP).

AB - This paper proposes a hierarchical predictive energy management strategy (EMS) for hybrid electric bus (HEB) with an intelligent state of charge (SOC) reference planning method. In the cloud layer, future driving cycle is acquired through the intelligent transportation system (ITS) and well-trained neutral networks of deep deterministic policy gradient (DDPG) are extracted to plan the SOC reference trajectory quickly. In the vehicle layer, back propagation neutral network (BP-NN) is used to predict the velocity in a short term and an optimal controller is designed to distribute power flows optimally. Simulation results show that the fuel economy is improved by 2.12% compared with DDPG and reaches 97.43% of dynamic programming (DP).

KW - deep deterministic policy gradient

KW - energy management

KW - hybrid electric bus

KW - intelligent SOC reference planning

KW - model predictive control

UR - https://www.scopus.com/pages/publications/85190764748

U2 - 10.46855/energy-proceedings-9445

DO - 10.46855/energy-proceedings-9445

M3 - Conference article

AN - SCOPUS:85190764748

SN - 2004-2965

VL - 23

JO - Energy Proceedings

JF - Energy Proceedings

Y2 - 29 November 2021 through 2 December 2021

ER -

Intelligent SOC Reference Planning for Hybrid Electric Bus: A Hierarchical Predictive Energy Management Strategy

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this