Predictive energy management (PEM) strategy has shown great advantages in improving fuel economy for plug-in hybrid electric vehicles (PHEVs). A key technology in PEM is velocity prediction and its accuracy greatly affects the effectiveness of a PEM strategy. This paper proposes a novel dynamic competitive velocity prediction method based on Markov state space (SS) reconstruction. The basic Markov model is introduced and its performance is fully evaluated. The Markov SS is designed by the K-Means++ clustering method to support online reconstruction. The transition probability matrix (TPM) is updated to adapt to the actual driving scenario. The dynamic competitive prediction method combines the basic and the reconstructed Markov models to achieve better performance. The velocity prediction performance is validated through repetitive complex driving conditions. Simulation result shows that the proposed method has superior performance in both prediction accuracy and computing time. For the complex driving condition scenario, the proposed method can reduce prediction error by 5.7%–9.1% comparing to the basic Markov model and its computing time is about 1% of that of LSTM when the prediction horizon is 5 s.
ZhangFHuXLangariR, et al. Energy management strategies of connected HEVs and PHEVs: recent progress and outlook. Prog Energy Combust Sci2019; 73: 235–256.
2.
SunCHuXMouraSJ, et al. Velocity predictors for predictive energy management in hybrid electric vehicles. IEEE Trans Control Syst Technol2015; 23(3): 1197–1204.
3.
GuoJHeHSunC. ARIMA-based road gradient and vehicle velocity prediction for hybrid electric vehicle energy management. IEEE Trans Veh Technol2019; 68(6): 5309–5320.
4.
SunCMouraSJHuX, et al. Dynamic traffic feedback data enabled energy management in plug-in hybrid electric vehicles. IEEE Trans Control Syst Technol2015; 23(3): 1075–1086.
5.
FengTYangLGuQ, et al. A supervisory control strategy for plug-in hybrid electric vehicles based on energy demand prediction and route preview. IEEE Trans Veh Technol2015; 64(5): 1691–1700.
6.
WuGBoriboonsomsinKBarthMJ. Development and evaluation of an intelligent energy-management strategy for plug-in hybrid electric vehicles. IEEE Trans Intell Transp Syst2014; 15(3): 1091–1100.
7.
SunCSunFHeH. Investigating adaptive-ECMS with velocity forecast ability for hybrid electric vehicles. Appl Energy2017; 185(2): 1644–1653.
8.
LiLYouSYangC, et al. Driving-behavior-aware stochastic model predictive control for plug-in hybrid electric buses. Appl Energy2016; 162: 868–879.
9.
ShinJYeonKKimS, et al. Comparative study of Markov chain with recurrent neural network for short term velocity prediction implemented on an embedded system. IEEE Access2021; 9: 24755–24767.
10.
GuoJJiangYLiuC, et al. Integrated multistep Markov-based velocity predictor of energy consumption prediction model for battery electric vehicles. Transportmetr B Transp Dyn2021; 9(1): 399–414.
11.
XieSHeHPengJ. An energy management strategy based on stochastic model predictive control for plug-in hybrid electric buses. Appl Energy2017; 196: 279–288.
12.
ShenPZhaoZZhanX, et al. Optimal energy management strategy for a plug-in hybrid electric commercial vehicle based on velocity prediction. Energy2018; 155: 838–852.
13.
LinXWangZWuJ. Energy management strategy based on velocity prediction using back propagation neural network for a plug-in fuel cell electric vehicle. Int J Energy Res2021; 45(2): 2629–2643.
14.
LiJZhouQHeY, et al. Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles. Appl Energy2019; 253: 113617.
15.
ZhangYChuLDingY, et al. A hierarchical energy management strategy based on model predictive control for plug-in hybrid electric vehicles. IEEE Access2019; 7: 81612–81629.
16.
Di CairanoSBernardiniDBemporadA, et al. Stochastic MPC with learning for driver-predictive vehicle control and its application to HEV energy management. IEEE Trans Control Syst Technol2014; 22(3): 1018–1031.
17.
ZouYKongZLiuT, et al. A real-time Markov chain driver model for tracked vehicles and its validation: its adaptability via stochastic dynamic programming. IEEE Trans Veh Technol2017; 66(5): 3571–3582.
18.
LiuTZouYLiuD, et al. Reinforcement learning-based energy management strategy for a hybrid electric tracked vehicle. Energies2015; 8(7): 7243–7260.
19.
ZhouYRaveyAPéraMC. Multi-objective energy management for fuel cell electric vehicles using online-learning enhanced Markov speed predictor. Energy Convers Manag2020; 213: 112821.
20.
ZhouYRaveyAPéraM. Multi-mode predictive energy management for fuel cell hybrid electric vehicles using Markov driving pattern recognizer. Appl Energy2020; 258: 114057.
21.
KongZZouYLiuT. Velocity predictions research and prediction horizon determination. Energy Procedia2017; 105: 3616–3622.
22.
LiGZhangJHeH. Battery SOC constraint comparison for predictive energy management of plug-in hybrid electric bus. Appl Energy2017; 194: 578–587.
23.
LiuSZhengKZhaoL, et al. A driving intention prediction method based on hidden Markov model for autonomous driving. Comput Commun2020; 157: 143–149.
24.
YangWWanBQuX. A forward collision warning system using driving intention recognition of the front vehicle and V2V communication. IEEE Access2020; 8: 11268–11278.
25.
WangRHeYSongT. Markov velocity predictor based on state space optimization and its applications in PHEV energy management. Proc IMechE, Part D: J Automobile Engineering. Epub ahead of print 5February2023. DOI: 10.1177/09544070231152000.
26.
GuoSWuKZhangG. Application of PCA-K-means++ combination model to construction of light vehicle driving conditions in intelligent traffic. J Meas Eng2020; 8(3): 107–121.
27.
YangCLiLYouS, et al. Cloud computing-based energy optimization control framework for plug-in hybrid electric bus. Energy2017; 125: 11–26.
28.
LinXWuJWeiY. An ensemble learning velocity prediction-based energy management strategy for a plug-in hybrid electric vehicle considering driving pattern adaptive reference SOC. Energy2021; 234(4): 121308.
29.
LiuHLiXWangW, et al. Markov velocity predictor and radial basis function neural network-based real-time energy management strategy for plug-in hybrid electric vehicles. Energy2018; 152: 427–444.
30.
LiuLWangZQiuS. Driving behavior tracking and recognition based on multisensors data fusion. IEEE Sens J2020; 20(18): 10811–10823.
31.
ZhangYHuangYChenZ, et al. A novel learning-based model predictive control strategy for plug-in hybrid electric vehicle. IEEE Trans Transp Electrification2022; 8(1): 23–35.
