Receding horizon control-based energy management for plug-in hybrid electric buses using a predictive model of terminal SOC constraint in consideration of stochastic vehicle mass

Guo, Hongwei; Lu, Silong; Hui, Hongzhong; Bao, Chunjiang; Shangguan, Jinyong

doi:10.1016/j.energy.2019.03.192

Cited by 26 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 1 Similar to, Reference a series of combined driving cycles constituted by historical driving cycles, stochastic distributions of passenger mass and the road slope are firstly constructed. They are combined by stochastic combination method, and the stochastic vehicle mass is summed by the curb weight of the vehicle and the stochastic passenger mass.…”

Section: The Formulation Of the Self‐learning Energy Managementmentioning

confidence: 99%

“…The SOC is taken as the first state, because the strong relationship between the SOC and the reward. Since the average velocity has great relationship with the co‐state, it is taken as the second state. Since the driving distance has relationship with the SOC, the normalized driving distance is taken as the last state.…”

Section: The Formulation Of the Self‐learning Energy Managementmentioning

confidence: 99%

See 1 more Smart Citation

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Guo¹,

Zhao²,

Guo³

et al. 2020

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

A self-learning energy management is proposed for plug-in hybrid electric bus, by combining Q-Learning (QL) and Pontryagin's minimum principle algorithms. Different from the existing strategies, the expert experience and generalization performance are focused in the proposed strategy. The expert experience is designed as the approximately optimal reference state-of-charge (SOC) trajectories, and the generalization performance is enhanced by a multiply driving cycle training method. In specific, an efficient zone of SOC is firstly designed based on the approximately optimal reference SOC trajectories. Then, the agent of the QL is trained off-line by taking the expert experience as reference SOC trajectories.Finally, an adaptive strategy is proposed based on the well-trained agent. Specially, two different reward functions are defined. That is, the reward function in the off-line training mainly considers the tracking performance between the expert experience and the SOC, while mainly considering the punishment in the adaptive strategy. Simulation results show that the proposed strategy has good generalization performance and can improve the fuel economy by 22.49%, compared to a charge depleting-charge sustaining (CDCS) strategy. K E Y W O R D Senergy management, expert experience, generalization performance, plug-in hybrid electric bus, Q-learning

show abstract

Section: The Formulation Of the Self‐learning Energy Managementmentioning

confidence: 99%

Section: The Formulation Of the Self‐learning Energy Managementmentioning

confidence: 99%

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Guo¹,

Zhao²,

Guo³

et al. 2020

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar to Ref. [23], the stochastic distributions of the vehicle mass were designed as follows: Firstly, as shown in Figure 6, 25 road segments are defined based on the number of the neighbored bus stops. Because the distributions of the passenger in different road segments are stochastic, 25 factors with respect to the road segments were defined to describe the stochastic distribution of the vehicle mass over the bus route.…”

Section: The Combined Driving Cyclementioning

confidence: 99%

“…Therefore, a reference SOC model should be designed. Since a series of optimal SOCs with respect to different combined driving cycles can be calculated off-line and the city bus route is fixed, the reference SOC model can be constructed by taking the normalized distance as input and the optimal SOC as output, based on partial least squares (PLS) method [23]. Here, the normalized distance can be described as…”

Section: The Reference Soc Modelmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Energy Management for Plug-in Hybrid Electric Bus with Limited State Space

Guo

Zhao

et al. 2019

Processes

Self Cite

View full text Add to dashboard Cite

Tabular Q-learning (QL) can be easily implemented into a controller to realize self-learning energy management control of a plug-in hybrid electric bus (PHEB). However, the “curse of dimensionality” problem is difficult to avoid, as the design space is huge. This paper proposes a QL-PMP algorithm (QL and Pontryagin minimum principle (PMP)) to address the problem. The main novelty is that the difference between the feedback SOC (state of charge) and the reference SOC is exclusively designed as state, and then a limited state space with 50 rows and 25 columns is proposed. The off-line training process shows that the limited state space is reasonable and adequate for the self-learning; the Hardware-in-Loop (HIL) simulation results show that the QL-PMP strategy can be implemented into a controller to realize real-time control, and can on average improve the fuel economy by 20.42%, compared to the charge depleting–charge sustaining (CDCS) strategy.

show abstract

Fuel economy‐oriented trajectory tracking control strategy for plug‐in hybrid electric buses

Shangguan

Yue

Fang

et al. 2021

Asian Journal of Control

Self Cite

View full text Add to dashboard Cite

Most of the existing trajectory tracking control strategies for vehicles aim at achieving high tracking accuracy but ignore energy consumption and road geometry. This paper proposes a fuel economy-oriented trajectory tracking control strategy for plug-in hybrid electric buses to improve fuel economy while ensuring tracking accuracy under different road geometries in the real world.First, a reference trajectory is reconstructed for trajectory tracking control to simulate the road geometry in real world. Next, a tracking controller based on model predictive control and proportional-integral control is developed to track the reference trajectory. Finally, an optimal control strategy with target preview method based on Pontryagin's minimum principle is developed to achieve the optimal fuel economy while tracking the trajectory. Simulation results illustrate that the proposed control strategy can realize not only excellent trajectory tracking performance but also optimal fuel economy.

show abstract

Receding horizon control-based energy management for plug-in hybrid electric buses using a predictive model of terminal SOC constraint in consideration of stochastic vehicle mass

Cited by 26 publications

References 29 publications

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Intelligent Energy Management for Plug-in Hybrid Electric Bus with Limited State Space

Fuel economy‐oriented trajectory tracking control strategy for plug‐in hybrid electric buses

Contact Info

Product

Resources

About