The power demand of heavy-duty commercial vehicles varies significantly with dynamic mass and upper-part load, which should be considered in energy management strategy (EMS) development. This paper thus proposes a two-level energy optimization framework that incorporates these factors. The cloud level generates EMSs from multiple vehicles’ operational data, while the vehicle level conducts energy management and power distribution. The periodic transfer, strategy verification, and updating between them enhance EMS effectiveness and reduce communication dependence. By designing a mass identifier and analyzing the upper-part load power demand, the two factors are incorporated into the EMS based on a twin delayed deep deterministic policy gradient algorithm. Simulations show the proposed EMS attains an average 98.26% fuel optimality of dynamic programming, and an average 19.59% fuel economy improvement against the rule-based EMS. Bench test indicates the power-following capability of the auxiliary power unit, thereby grounding the practicality of the proposed EMS.
GadnerSPifkoABrehmerU, et al. Electric truck mixer for the future urban construction site. ATZheavy Duty Worldw2019; 12: 14–21.
2.
LinYZhangTHongJ, et al. Multi-agent-based energy management strategy for a novel electric-flywheel hybrid electric vehicle. Sustain Energy Technol Assess2025; 82: 104538.
3.
ShiDXuHWangS, et al. Deep reinforcement learning based adaptive energy management for plug-in hybrid electric vehicle with double deep Q-network. Energy2024; 305: 132402.
4.
WangRShiXSuY, et al. A predictive energy management strategy for plug-in hybrid electric vehicles using real-time traffic based reference SOC planning. Proc Inst Mech Eng Part D: J Automobile Eng2025; 239(6): 1872–1889.
5.
LiuYWuYWangX, et al. Energy management for hybrid electric vehicles based on imitation reinforcement learning. Energy2023; 263: 125890.
6.
UroojANasirA. Review of intelligent energy management techniques for hybrid electric vehicles. J Energy Storage2024; 92: 112132.
7.
GuoHLiangBGuoH, et al. A robust co-state predictive model for energy management of plug-in hybrid electric bus. J Clean Prod2020; 250: 119478.
8.
YuXLinCXieP, et al. A novel real-time energy management strategy based on Monte Carlo tree search for coupled powertrain platform via vehicle-to-cloud connectivity. Energy2022; 256: 124619.
9.
SongDWuQYangD, et al. Research on operation cost minimization online energy management strategy for fuel cell hybrid passenger vehicles. Proc Inst Mech Eng Part D: J Automobile Eng2024; 238(2–3): 420–432.
10.
PengJHeHXiongR. Rule based energy management strategy for a series–parallel plug-in hybrid electric bus optimized by dynamic programming. Appl Energy2017; 185(2): 1633–1643.
11.
ChenXLiMChenZ. Meta rule-based energy management strategy for battery/supercapacitor hybrid electric vehicles. Energy2023; 285: 129365.
12.
YangCDuSLiL, et al. Adaptive real-time optimal energy management strategy based on equivalent factors optimization for plug-in hybrid electric vehicle. Appl Energy2017; 203: 883–896.
13.
HuangRHeHSuQ, et al. Towards sustainable and intelligent urban transportation: a novel deep transfer reinforcement learning framework for eco-driving of fuel cell buses. Energy2025; 330: 136730.
14.
ChenZXiongRLiuB, et al. Pontryagin’s minimum principle-based power management of plug-in hybrid electric vehicles to enhance the battery durability and thermal safety. IEEE Trans Transp Electrification2023; 9(4): 5039–5048.
15.
JiaHLiHYinB, et al. Study on energy management strategy of fuel cell patrol vehicle hybrid power system. Proc Inst Mech Eng Part D: J Automobile Eng2025; 239(6): 2141–2152.
16.
ShiDRongXWangS, et al. Adaptive energy management strategy for hybrid electric vehicle based on power prediction. Proc Inst Mech Eng Part D: J Automobile Eng2023; 237(6): 1365–1377.
17.
YanSFangJYangC, et al. Eco-driving for connected automated hybrid electric vehicles in learning-enabled layered transportation systems. Transp Res D Transp Environ2025; 142: 104677.
18.
GuoNZhangWChenW, et al. Universal bounds estimation and efficient tuning for equivalent factor in real-time cost-optimal predictive ECMS of PHEVs. IEEE Trans Transp Electrification2025; 11(1): 2796–2813.
19.
GuoNZhangWLiJ, et al. Predictive energy management of fuel cell plug-in hybrid electric vehicles: a co-state boundaries-oriented PMP optimization approach. Appl Energy2024; 362: 122882.
20.
TangWHeJWangZ, et al. Energy management optimization control with the consideration of the driving style for connected hybrid electric vehicles in mixed driving scenarios. In: 2023 7th CAA international conference on vehicular control and intelligence (CVCI), Changsha, China, 2023, pp.1–6.
21.
ZhouJGuoAWangJ, et al. Energy management strategy of fuel cell vehicles with hybrid energy sources: a novel framework via deep reinforcement learning and transfer learning. Proc Inst Mech Eng D J Automobile Eng2024; 238(14): 4659–4675.
22.
YangWLuoDZhangW, et al. Investigation of energy management strategy based on deep reinforcement learning algorithm for multi-speed pure electric vehicles. Proc Inst Mech Eng Part D: J Automobile Eng2025; 239(10–11): 4774–4784.
23.
LillicrapTPHuntJJPritzelA, et al. Continuous control with deep reinforcement learning. In 4th International Conference on Learning Representations (ICLR), 2016.
24.
HeHMengXWangY, et al. Deep reinforcement learning based energy management strategies for electrified vehicles: recent advances and perspectives. Renew Sustain Energ Rev2024; 192: 114248.
25.
ZhangYZhangCFanR, et al. Twin delayed deep deterministic policy gradient-based deep reinforcement learning for energy management of fuel cell vehicle integrating durability information of powertrain. Energy Convers Manag2022; 274: 116454.
26.
GaneshAHXuB. A review of reinforcement learning based energy management systems for electrified powertrains: progress, challenge, and potential solution. Renew Sustain Energ Rev2022; 154: 111833.
27.
ZhouYHuangYMaoX, et al. Research on energy management strategy of fuel cell hybrid power via an improved TD3 deep reinforcement learning. Energy2024; 293: 130564.
28.
HuoWLiuTLuB. A reinforcement learning-based energy management strategy for fuel cell electric vehicle considering coupled-energy sources degradations. Sustain Energy Grid Netw2024; 40: 101548.
29.
LiuRWangCTangA, et al. A twin delayed deep deterministic policy gradient-based energy management strategy for a battery-ultracapacitor electric vehicle considering driving condition recognition with learning vector quantization neural network. J Energy Storage2023; 71: 108147.
30.
CuiNCuiWShiY. Deep reinforcement learning based PHEV energy management with co-recognition for traffic condition and driving style. IEEE Trans Intell Vehicles2023; 8: 3026–3039.
31.
WangYTangHPanB, et al. A cloud energy management strategy for intelligent connected HEVs based on end-edge-cloud collaboration. Proc Inst Mech Eng Part D: J Automobile Eng2025; 239: 4756–4773.
32.
WangYLiWWangT, et al. A cloud-supported plug-in hybrid electric buses energy-saving control integrating spatial–temporal traffic condition. Transp Res D Transp Environ2025; 147: 104927.
33.
ShiJXuBZhouX, et al. A cloud-based energy management strategy for hybrid electric city bus considering real-time passenger load prediction. J Energy Storage2022; 45: 103749.
34.
TanHZhangHPengJ, et al. Energy management of hybrid electric bus based on deep reinforcement learning in continuous state and action space. Energy Convers Manag2019; 195: 548–560.
35.
TangQHuMBianY, et al. Optimal energy efficiency control framework for distributed drive mining truck power system with hybrid energy storage: a vehicle-cloud integration approach. Appl Energy2024; 374: 123989.
36.
HouJSongZ. A hierarchical energy management strategy for hybrid energy storage via vehicle-to-cloud connectivity. Appl Energy2020; 257: 113900.
37.
LiuGShenSLiuY, et al. Energy-saving control of intelligent connected plug-in hybrid electric vehicle via fusing driving intention of front vehicle. Green Energy Intell Transp2026; 5(2): 100330.
38.
ChenWPengJMaY, et al. Eco-driving framework for hybrid electric vehicles in multi-lane scenarios by using deep reinforcement learning methods. Green Energy Intell Transp2026; 5(2): 100309.
39.
FathyHKKangDSteinJL. Online vehicle mass estimation using recursive least squares and supervisory data extraction. In: American control conference, 2008, pp.1842–1848.
40.
FanPSongGZhaiZ, et al. Fuel consumption estimation in heavy-duty trucks: integrating vehicle weight into deep-learning frameworks. Transp Res D Transp Environ2024; 130: 104157.
41.
JiangSWangCZhangC, et al. Adaptive estimation of road slope and vehicle mass of fuel cell vehicle. eTransportation2019; 2: 100023.
42.
HuangYWangHKhajepourA, et al. Model predictive control power management strategies for HEVs: a review. J Power Sources2017; 341: 91–106.
43.
HuangYWangSLiK, et al. Multi-parameter adaptive online energy management strategy for concrete truck mixers with a novel hybrid powertrain considering vehicle mass. Energy2023; 277: 127700.
44.
FardSMKhajepourA. An optimal power management system for a regenerative auxiliary power system for delivery refrigerator trucks. Appl Energy2016; 169: 748–756.
45.
BagheriFFayazbakhshMACheppudira ThimmaiahP, et al. Theoretical and experimental investigation into anti-idling A/C system for trucks. Energy Convers Manag2015; 98: 173–183.
46.
ZhouJXueSXueY, et al. A novel energy management strategy of hybrid electric vehicle via an improved TD3 deep reinforcement learning. Energy2021; 224: 120118.
47.
MaZLuanYZhangF, et al. A data-driven energy management strategy for plug-in hybrid electric buses considering vehicle mass uncertainty. J Energy Storage2024; 77: 109963.
48.
JiaCLiuWHeH, et al. Deep reinforcement learning-based energy management strategy for fuel cell buses integrating future road information and cabin comfort control. Energy Convers Manag2024; 321: 119032.
49.
LüXWuYLianJ, et al. Energy management of hybrid electric vehicles: a review of energy optimization of fuel cell hybrid power system based on genetic algorithm. Energy Convers Manag2020; 205: 112474.
50.
BoLHanLXiangC, et al. A real-time energy management strategy for off-road hybrid electric vehicles based on the expected SARSA. Proc Inst Mech Eng Part D: J Automobile Eng2023; 237(2–3): 362–380.
51.
HuangYJiangFXieH. Adaptive hierarchical energy management design for a novel hybrid powertrain of concrete truck mixers. J Power Sources2021; 509: 230325.
52.
HuangYJiangFXieH. Machine-learning-based optimization of energy management in a novel hybrid powertrain of concrete truck mixers. World Electr Veh J2021; 12: 175.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
