Optimal flexible power allocation energy management strategy for hybrid energy storage system with genetic algorithm based model predictive control

This paper proposes an optimal flexible power allocation-based energy management system (EMS) for hybrid energy storage systems (HESS) in electric vehicles (EVs). The main advantage of the proposed EMS is its use of a genetic algorithm-based model predictive control (GA-MPC) with optimal tuning of w...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) Vol. 324; p. 135958
Main Authors: Ma, Bin, Li, Peng-Hui
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.06.2025
Subjects:
algorithms
ARIMA-LSTM
batteries
electrochemical capacitors
energy
Energy management
HESS
management systems
MPC
prediction
topology
Weight and constraint regulation
MPC
GA
Weight and constraint regulation
HESS
Energy management
ARIMA-LSTM
ISSN:0360-5442
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an optimal flexible power allocation-based energy management system (EMS) for hybrid energy storage systems (HESS) in electric vehicles (EVs). The main advantage of the proposed EMS is its use of a genetic algorithm-based model predictive control (GA-MPC) with optimal tuning of weights and constraints, which fully extends and balances ultracapacitors (UC) utilization over the actual driving cycle. Additionally, the GA-MPC gently isolates the battery from direct recharging, further extending the battery's lifetime. For the prediction aspect, a hybrid ARIMA-LSTM predictor is developed for real time prediction of more accurate power demand for the EMS optimization. Meanwhile, a MPC with a quadratic programming algorithm is designed to optimize the power allocation problem. Innovatively, a rule-based strategy and the GA are developed for constraint and weight regulation, gently preventing direct battery recharging and ensuring the UC has the highest priority in the dynamic power allocation process. The proposed approach is validated using a downscaled HESS experimental platform. Simulation results indicate that the UC utilization ratio is improved by 25.3 %, and the battery lifetime is prolonged by 13 % compared to conventional MPC, without altering the existing HESS topology. •A novel GA-MPC strategy is introduced to optimize power allocation and UC utilization, achieving an flexible power allocation.•A hybrid ARIMA-LSTM model is proposed to improve the accuracy of power demand prediction.•A rule-based method is employed for model selection, constraint regulation, and triggering the GA for weight optimization.•A scaled-down hardware-in-the-loop verification platform is established to validate the effectiveness of the proposed strategy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0360-5442
DOI:10.1016/j.energy.2025.135958