Bayesian optimization based machine learning approaches for prediction of plug-in electric vehicle state-of-charge
-
Subhasish Deb
,
Arup Kumar Goswami
,
Rahul Lamichane Chetri
Abstract
The growing popularity of plug-in electric vehicle (PEV) around the world makes complexity in power sector. The distribution system is subjected to overload due to the random penetration of PEVs in charging depending on their level of state-of-charge (SOC). The accurate calculation and prediction of SOC considering their travel distance makes significant impact on the level of SOC. Therefore, the accurate SOC prediction of PEVs is need of the hour in transportation sector. However, the prediction of SOC allows the PEVs owners to decide the charging/discharging mode or priority based charging. Recently, machine learning techniques are gaining popularity in prediction analysis of different parameters. This article proposes machine learning approaches in combination with Bayesian optimization (BO) for prediction analysis of PEVs SOC. The gradient boosting method (GBM) and random forest method (RFM) are used as machine learning approaches in this work. The energy consumption pattern, different battery capacities and total trip distance of PEVs are included in calculation for the estimation of accurate SOC. A satisfactory result of SOC prediction has been observed using both GBM-BO and RFM-BO. The comparative study of results reveals the performance and efficacy of GBM-BO against RFM-BO in the PEVs SOC prediction analysis. Moreover, the hybrid machine learning techniques with BO performs better than individual machine learning techniques in the prediction analysis of PEVs SOC.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Afshar, S, Morris, K, Khajepour, A. State-of-charge estimation using an EKF-based adaptive observer. IEEE Trans Contr Syst Technol 2019;27:1907–23. https://doi.org/10.1109/tcst.2018.2842038.Suche in Google Scholar
2. Zhao, F, Li, Y, Wang, X, Bai, L, Liu, T. Lithium-ion batteries state of charge prediction of electric vehicles using RNNs–CNNs neural networks. IEEE Access 2020;8:98168–80. https://doi.org/10.1109/access.2020.2996225.Suche in Google Scholar
3. Xuan, L, Qian, L, Chen, J, Bai, X, Wu, B. State-of-charge prediction of battery management system based on principal component analysis and improved support vector machine for regression. IEEE Access 2020;8:164693–704. https://doi.org/10.1109/access.2020.3021745.Suche in Google Scholar
4. Caliwag, AC, Lim, W. Hybrid VARMA and LSTM method for lithium-ion battery state-of-charge and output voltage forecasting in electric motorcycle applications. IEEE Access 2019;7:59680–9. https://doi.org/10.1109/access.2019.2914188.Suche in Google Scholar
5. Zhang, Z, Jiang, L, Zhang, L, Huang, C. State-of-charge estimation of lithium-ion battery pack by using an adaptive extended Kalman filter for electric vehicles. J Energy Storage 2021;37:102457–1–15. https://doi.org/10.1016/j.est.2021.102457.Suche in Google Scholar
6. Bhangu, BS, Bentley, P, Stone, DA, Bingham, CM. Nonlinear observers for predicting state-of-charge and state-of-health of lead-acid batteries for hybrid-electric vehicles. IEEE Trans Veh Technol 2005;54:783–94. https://doi.org/10.1109/tvt.2004.842461.Suche in Google Scholar
7. Zahid, T, Xu, K, Li, W, Li, C, Li, H. State of charge estimation for electric vehicle power battery using advanced machine learning algorithm under diversified drive cycles. Energy 2018;162:871–82. https://doi.org/10.1016/j.energy.2018.08.071.Suche in Google Scholar
8. Ali, A, Bibeau, E, Shahidinejad, S, Molinski, T. PEV charging profile prediction and analysis based on vehicle usage data. IEEE Trans Smart Grid 2012;3:341–50.10.1109/TSG.2011.2162009Suche in Google Scholar
9. Xia, Y, Hu, B, Xie, K, Tang, J, Tai, H-M. An EV charging demand model for the distribution system using traffic property. IEEE Access 2019;7:28089–99. https://doi.org/10.1109/access.2019.2901857.Suche in Google Scholar
10. Wang, D, Gao, J, Li, P, Wang, B, Zhang, C, Saxena, S. Modeling of plug-in electric vehicle travel patterns and charging load based on trip chain generation. J Power Sources 2017;359:468–79. https://doi.org/10.1016/j.jpowsour.2017.05.036.Suche in Google Scholar
11. Brady, J, O’Mahony, M. Modelling charging profiles of electric vehicles based on real-world electric vehicle charging data. Sustain Cities Soc 2016;26:203–16. https://doi.org/10.1016/j.scs.2016.06.014.Suche in Google Scholar
12. Zhang, J, Wang, Z, Liu, P, Zhang, Z. Energy consumption analysis and prediction of electric vehicles based on real-world driving data. Appl Energy 2020;275:115408–1–15. https://doi.org/10.1016/j.apenergy.2020.115408.Suche in Google Scholar
13. Ito, A, Kawashima, A, Suzuki, T, Inagaki, S, Yamaguchi, T, Zhou, Z. Model predictive charging control of in-vehicle batteries for home energy management based on vehicle state prediction. IEEE Trans Contr Syst Technol 2018;26:51–64. https://doi.org/10.1109/tcst.2017.2664727.Suche in Google Scholar
14. Shen, P, Zhao, Z, Zhan, X, Li, J, Guo, Q. Optimal energy management strategy for a plug-in hybrid electric commercial vehicle based on velocity prediction. Energy 2018;155:838–52. https://doi.org/10.1016/j.energy.2018.05.064.Suche in Google Scholar
15. Arias, MB, Kim, M, Bae, S. Prediction of electric vehicle charging-power demand in realistic urban traffic networks. Appl Energy 2017;195:738–53. https://doi.org/10.1016/j.apenergy.2017.02.021.Suche in Google Scholar
16. Wu, X. Role of workplace charging opportunities on adoption of plug-in electric vehicles – analysis based on GPS-based longitudinal travel data. Energy Pol 2018;114:367–79. https://doi.org/10.1016/j.enpol.2017.12.015.Suche in Google Scholar
17. Zhao, X, Cai, Y, Yang, L, Deng, Z, Qiang, J. State of charge estimation based on a new dual-polarization-resistance model for electric vehicles. Energy 2017;135:40–52. https://doi.org/10.1016/j.energy.2017.06.094.Suche in Google Scholar
18. van Bree, PJ, Veltman, A, Hendrix, WHA, van den Bosch, PPJ. Prediction of battery behavior subject to high-rate partial state of charge. IEEE Trans Veh Technol 2009;58:588–95. https://doi.org/10.1109/tvt.2008.928005.Suche in Google Scholar
19. Tang, D, Wang, P. Stocastic modeling of electric vehicle movable loads: nodal impact from transportation. In: International conference on probabilistic methods applied to power systems (PMAPS); 2014:1–6 pp.10.1109/PMAPS.2014.6960647Suche in Google Scholar
20. Jimenez-Bermejo, D, Fraile-Ardanuy, J, Castano-Solis, S, Merino, J, Alvaro-Hermana, R. Using dynamic neural networks for battery state of charge estimation in electric vehicles. Proc Comput Sci 2018;130:533–40. https://doi.org/10.1016/j.procs.2018.04.077.Suche in Google Scholar
21. Zhang, Y, Ali, H. A gradient boosting method to improve travel time prediction. Transp Res Part C 2015;58:308–24. https://doi.org/10.1016/j.trc.2015.02.019.Suche in Google Scholar
22. Deb, S, Goswami, AK, Harsh, P, Sahoo, JP, Chetri, RL, Roy, R, et al.. Charging coordination of plug-in-electric vehicle for congestion management in distribution system integrated with renewable energy sources. IEEE Trans Ind Appl 2020;56:5452–62. https://doi.org/10.1109/tia.2020.3010897.Suche in Google Scholar
23. Deb, S, Goswami, AK, Chetri, RL, Roy, R. Prediction of plug-in electric vehicle’s state-of-charge using gradient boosting method and random forest method. In: 2020 IEEE international conference on power electronics, drives and energy systems (PEDES); 2020:1–6 pp.10.1109/PEDES49360.2020.9379906Suche in Google Scholar
24. Deb, S, Goswami, AK, Chetri, RL, Roy, R. Distribution system congestion management by charging coordination of plug-in electric vehicle. In: 2020 3rd International conference on energy, power and environment: towards clean energy technologies; 2021:1–6 pp.10.1109/ICEPE50861.2021.9404380Suche in Google Scholar
25. Deb, S, Goswami, AK, Chetri, RL, Roy, R. Impact of plug-in electric vehicle integration in distribution system congestion management. In: 2020 3rd International conference on energy, power and environment: towards clean energy technologies; 2021:1–6 pp.10.1109/ICEPE50861.2021.9404398Suche in Google Scholar
26. Yu, B, Lam, WHK, Tam, ML. Bus arrival time prediction at bus stop with multiple routes. Transp Res Part C 2011;19:1157–70. https://doi.org/10.1016/j.trc.2011.01.003.Suche in Google Scholar
27. Khosravi, A, Mazloumi, E, Nahavandi, S, Creighton, D, (Hans) van Lint, JWC. Prediction intervals to account for uncertainties in travel time prediction. IEEE Trans Intell Transp Syst 2011;12:537–47. https://doi.org/10.1109/tits.2011.2106209.Suche in Google Scholar
28. Hastie, T, Tibshirani, R, Friedman, J. The elements of statistical learning: data mining, inference, and prediction. New York, NY: Springer; 2009.10.1007/978-0-387-84858-7Suche in Google Scholar
29. Wang, T, Wang, X, Ma, R, Li, X, Hu, X, Chan, FTS, et al.. Random forest-Bayesisn optimization for product quality prediction with large-scale dimensions in process industrial cyber physical systems. IEEE Internet Things J 2020;7:8641–53. https://doi.org/10.1109/jiot.2020.2992811.Suche in Google Scholar
30. Wang, Z, Hutter, F, Zoghi, M, Matheson, D, de Feitas, N. Bayesian optimization in a billion dimensions via random embeddings. J Artif Intell Res 2016;55:361–87. https://doi.org/10.1613/jair.4806.Suche in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Research Articles
- Efficient power scheduling in smart homes using a novel artificial ecosystem optimization technique considering two pricing schemes
- MPPT control based on improved mayfly optimization algorithm under complex shading conditions
- A cogeneration scheme with biogas and improvement of frequency stability using inertia based control in AC microgrid
- Profit evaluation inclusive of reserve pricing for renewable-integrated GENCOs
- An ideal solution for the deployment of photovoltaic generators using agent-based Nash Differential Evolution (NashDE) algorithm
- Design and operation of smart hybrid microgrid
- Three-state switching cell boost converter using H-inf controller
- Bayesian optimization based machine learning approaches for prediction of plug-in electric vehicle state-of-charge
- Probabilistic and deterministic analysis of single diode model of a solar cell: a case study
- A novel approach to increase the share of renewable purchase obligation for planning of distribution network including grid scale energy storage
- A non-cooperative game based energy management considering distributed energy resources in price-based and incentive-based demand response program
Artikel in diesem Heft
- Frontmatter
- Research Articles
- Efficient power scheduling in smart homes using a novel artificial ecosystem optimization technique considering two pricing schemes
- MPPT control based on improved mayfly optimization algorithm under complex shading conditions
- A cogeneration scheme with biogas and improvement of frequency stability using inertia based control in AC microgrid
- Profit evaluation inclusive of reserve pricing for renewable-integrated GENCOs
- An ideal solution for the deployment of photovoltaic generators using agent-based Nash Differential Evolution (NashDE) algorithm
- Design and operation of smart hybrid microgrid
- Three-state switching cell boost converter using H-inf controller
- Bayesian optimization based machine learning approaches for prediction of plug-in electric vehicle state-of-charge
- Probabilistic and deterministic analysis of single diode model of a solar cell: a case study
- A novel approach to increase the share of renewable purchase obligation for planning of distribution network including grid scale energy storage
- A non-cooperative game based energy management considering distributed energy resources in price-based and incentive-based demand response program
