Hierarchical Energy Management Recognizing Powertrain Dynamics for Electrified Vehicles With Deep Reinforcement Learning and Transfer Learning
Bibliographic record
Abstract
Deep reinforcement learning (DRL)-based energy management strategies (EMSs) have gained significant popularity in improving the performance of electrified vehicles. Typically, these EMSs are trained and validated in simulated environments. However, this article reveals that the environment’s fidelity significantly impacts DRL-based EMSs’ performance. Specifically, the EMSs optimized within low-fidelity environments (LFEs)—prevalent in literature yet lacking detailed powertrain dynamics—suffer a performance drop of 2%–3% in energy economy when tested in high-fidelity environments (HFEs) that incorporate powertrain dynamics. To address it, a DRL-based hierarchical energy management framework for multimode power-split hybrid electric vehicles (HEVs) is proposed. It recognizes powertrain dynamics and facilitates transfer learning techniques to bridge the performance gap between LFEs and HFEs. In the upper level of this framework, a DRL agent determines the optimal timing to activate the hybrid mode and the optimal engine operation. The lower level optimizes the torque distribution between two electric motors for all-electric modes. Simulation results demonstrate that the proposed DRL-based EMS, enhanced by transfer learning, reduces training time by approximately 40% compared with the trained-from-scratch EMS within an HFE. Moreover, the proposed EMS achieves 98% energy economy of the optimal benchmark, addressing the noted performance degradation and exhibiting consistent performance in adaptability tests.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".