Treffer: Hierarchical energy management strategy of hybrid electric vehicles under multiple uncertainties.

This study introduces a multi-level Energy Management Strategy (EMS) designed for Hybrid Electric Vehicles (HEV) that considers multiple uncertainties. In the upper-level strategy, an extended Long Short-Term Memory (xLSTM) neural network algorithm is utilized for short-term vehicle speed prediction. Simultaneously, within the prediction horizon, the optimal control sequence for the engine is then determined using the Dynamic Programming (DP) algorithm, which also generates a State of Charge (SOC) trajectory. In the lower-level strategy, the SOC trajectory from the upper-level strategy serves as a reference, and a tube-based Model Predictive Control (tube-MPC) approach is utilized to address the reference trajectory tracking problem under multiple uncertainties. Simulation results demonstrate that the xLSTM-based speed prediction model improves accuracy and reduces compute time compared to the Long Short-Term Memory (LSTM) and transformer speed prediction model; the proposed strategy improves fuel economy by 11.65% over the rule-based strategy and improves fuel economy by 5.25% over the latest Model Predictive Control (MPC) strategy, with a fuel consumption of 4.641 L/100 km, achieving 92.67% fuel economy of the DP strategy. Furthermore, it maintains over 90% of the DP strategy's fuel efficiency across various driving conditions, confirming its robustness and adaptability. [ABSTRACT FROM AUTHOR]

Copyright of Energy Sources Part A: Recovery, Utilization & Environmental Effects is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)