An optimal control for power management in super capacitors/battery of electric vehicles using Deep Neural Network

Pisal, Pravin Subhash; Vidyarthi, Abhay

doi:10.1016/j.jpowsour.2022.231696

Cited by 7 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks deal with highly nonlinear systems by simulating the calculation and thinking processes of the human brain. Reference [24] adopted the deep neural network to predict HESS control parameters, which results show that the algorithm can effectively improve the EMS performance. However, the control stability of neural network algorithm extremely relies on the quantity and quality of training data.…”

Section: Introductionmentioning

confidence: 99%

Wavelet transform‐based real‐time energy management strategy of hybrid energy storage system for electric vehicle

Jiang,

Wang,

Zhang

et al. 2023

Circuit Theory & Apps

View full text Add to dashboard Cite

SummaryThe peak and transient components of demand power caused by the complex and variable traffic environment could induce the accelerated degradation of the battery lifespan for electric vehicle (EV). This paper proposes a wavelet transform‐based real‐time energy management strategy (EMS) to fully exploit the advantages of the hybrid energy storage system (HESS). First, to adapt the characteristics of battery and ultracapacitor, wavelet transform is employed to decompose driving cycle into high frequency power and low frequency power. Second, since the wavelet transform is difficult to be directly implemented in real‐time control, a power prediction model including four neural network predictors is established, which are trained by the data obtained from wavelet transform to online predict the power of different frequencies. Third, the high frequency power and the low frequency power are distributed to the battery and ultracapacitor by fuzzy logic control (FLC) algorithm, which can significantly reduce the damage caused by current rapid changes into the battery. Accordingly, the battery lifespan is effectively extended because it significantly avoids the impact of rapidly changing and peak current. Finally, simulation results verify the effectiveness of wavelet transform‐based real‐time EMS, and the proposed EMS robustness against temperature is verified at different temperatures. Compared with the wavelet transform strategy (WTS), the peak currents of wavelet transform‐fuzzy logic control strategy (WTFLCS) are decreased by 26.07%, 25.66%, and 25.85% at 10°C, 25°C, and 40°C, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Wavelet transform‐based real‐time energy management strategy of hybrid energy storage system for electric vehicle

Jiang,

Wang,

Zhang

et al. 2023

Circuit Theory & Apps

View full text Add to dashboard Cite

show abstract

“…It can effectively map the input-output relationship in complex situations, and has stronger feature extraction and generalisation ability. Besides, it is very suitable for rapid and intelligent estimation of the minimum inertia demand and frequency security, and can be applied to system scheduling and planning [16][17][18][19]. In literature [16], the implementation scheme of frequency response pattern prediction and analysis after large disturbance based on DNN were proposed, but the system inertia was not analysed.…”

Section: Introductionmentioning

confidence: 99%

Minimum inertia demand estimation of new power system considering diverse inertial resources based on deep neural network

Liu

Zhou

Chen

et al. 2022

IET Energy Syst Integration

View full text Add to dashboard Cite

With the high-proportion integration of renewable energy and power electronic equipment, the inertia supporting ability of new power system continues to decline, which seriously threatens the frequency stability of power grids. In order to clarify the operation boundary, and realise the rapid analysis and prediction of the minimum inertia demand of new power systems, this study proposes a minimum inertia demand estimation method based on deep neural network (DNN). Firstly, this study establishes the system frequency response model of new power systems containing diverse inertia resources including renewable energy, induction machine and so on. Considering the constraints of rate of change of frequency and maximum frequency deviation, the minimum inertia demand estimation model is established to ensure the system frequency stability. DNN is introduced to effectively map non-linear relations in complex situations, which can quickly estimate and predict the minimum inertia of new power systems. Adam algorithm is utilised to optimise the input weight matrix and hidden layer feature vector of the network to improve accuracy. Finally, the simulations and analysis are conducted in IEEE-39 system to verify the accuracy and generalisation ability of the proposed method in this paper.

show abstract

A comprehensive review on energy management strategies of hybrid energy storage systems for electric vehicles

Kumaresan,

Rammohan

2024

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

An optimal control for power management in super capacitors/battery of electric vehicles using Deep Neural Network

Cited by 7 publications

References 22 publications

Wavelet transform‐based real‐time energy management strategy of hybrid energy storage system for electric vehicle

Wavelet transform‐based real‐time energy management strategy of hybrid energy storage system for electric vehicle

Minimum inertia demand estimation of new power system considering diverse inertial resources based on deep neural network

A comprehensive review on energy management strategies of hybrid energy storage systems for electric vehicles

Contact Info

Product

Resources

About