Forecasting of energy consumption rate and battery stress under real-world traffic conditions using ANN model with different learning algorithms

Anbazhagan Geetha; S. Usha; J. Santhakumar; Surender Reddy Salkuti; Anbazhagan Geetha; S. Usha; J. Santhakumar; Surender Reddy Salkuti

doi:10.3934/energy.2025005

AIMS Energy

2025, Volume 13, Issue 1: 125-146. doi: 10.3934/energy.2025005

Previous Article Next Article

Research article Special Issues

Forecasting of energy consumption rate and battery stress under real-world traffic conditions using ANN model with different learning algorithms

1.
Department of Electrical and Electronics Engineering, College of Engineering and Technology, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, Tamil Nadu 603203, India
2.
Department of Mechanical Engineering, College of Engineering and Technology, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chengalpattu, Tamil Nadu 603203, India
3.
Department of Railroad and Electrical Engineering, Woosong University, Daejeon 34606, Republic of Korea

Received: 29 October 2024 Revised: 22 January 2025 Accepted: 11 February 2025 Published: 18 February 2025

Estimating energy consumption rates is a necessary step when building infrastructure for charging and schedule optimization of battery-powered vehicles utilized in public urban driving patterns. This study examined several input factors for the prediction of vehicle performance. Input conditions were energy management controls, State of Charge (SOC) power train batteries, and ultra-capacitor vehicle models; output metrics included consumption rates, battery loads, and trip distances. To examine the experimental design, an L9 design was used with four control factors at three different levels each. Artificial neural network (ANN) models were developed employing four learning algorithms: quick propagation (QuP), batch backpropagation (BBaP), Levenberg-Marquardt backpropagation (LMBaP), and incremental backpropagation (IBaP). Post-simulation results were summarized and validated using the root mean square error (RMSE), which indicated that the values collected experimentally were close to those predicted by the models. This paper built an ANN-based prediction model and accurately predicted vehicle performance and potential energy shortfalls in public transportation networks. These insights can be applied to interventions like charging stations or reshaping bus timings to avoid power loss.
- Hybrid electric vehicle,
- energy management control strategies,
- artificial neural network,
- learning algorithm,
- LM backpropagation algorithm
Citation: Anbazhagan Geetha, S. Usha, J. Santhakumar, Surender Reddy Salkuti. Forecasting of energy consumption rate and battery stress under real-world traffic conditions using ANN model with different learning algorithms[J]. AIMS Energy, 2025, 13(1): 125-146. doi: 10.3934/energy.2025005

Related Papers:

Abstract

Estimating energy consumption rates is a necessary step when building infrastructure for charging and schedule optimization of battery-powered vehicles utilized in public urban driving patterns. This study examined several input factors for the prediction of vehicle performance. Input conditions were energy management controls, State of Charge (SOC) power train batteries, and ultra-capacitor vehicle models; output metrics included consumption rates, battery loads, and trip distances. To examine the experimental design, an L9 design was used with four control factors at three different levels each. Artificial neural network (ANN) models were developed employing four learning algorithms: quick propagation (QuP), batch backpropagation (BBaP), Levenberg-Marquardt backpropagation (LMBaP), and incremental backpropagation (IBaP). Post-simulation results were summarized and validated using the root mean square error (RMSE), which indicated that the values collected experimentally were close to those predicted by the models. This paper built an ANN-based prediction model and accurately predicted vehicle performance and potential energy shortfalls in public transportation networks. These insights can be applied to interventions like charging stations or reshaping bus timings to avoid power loss.

References

[1]	Moreno J, Ortuzar ME, Dixon JW (2006) Energy-management system for a hybrid electric vehicle, using ultracapacitors and neural networks. IEEE Trans Ind Electron 53: 614–623. https://doi.org/10.1109/TIE.2006.870880 doi: 10.1109/TIE.2006.870880
[2]	Hideki K, Ryosuke A, Yoshinori K, et al. (2016) The eco-driving effect of electric vehicles compared to conventional gasoline vehicles. AIMS Energy 4: 804–816. https://doi.org/10.3934/energy.2016.6.804 doi: 10.3934/energy.2016.6.804
[3]	Sun S, Li T (2024) An analysis of the global EV market: Sustainable pathways to net zero emissions. J Appl Econ Policy Stud 11: 67–80. https://doi.org/10.54254/2977-5701/11/2024104 doi: 10.54254/2977-5701/11/2024104
[4]	Dalong G, Chi Z (2016) Potential performance analysis and future trend prediction of electric vehicle with V2G/V2H/V2B capability. AIMS Energy 4: 331–346. https://doi.org/10.3934/energy.2016.2.331 doi: 10.3934/energy.2016.2.331
[5]	Zhang S, Xiong R (2015) Adaptive energy management of a plug-in hybrid electric vehicle based on driving pattern recognition and dynamic programming. Appl Energy 155: 68–78. https://doi.org/10.1016/j.apenergy.2015.06.003 doi: 10.1016/j.apenergy.2015.06.003
[6]	Samson OS, Atanda KR (2022) State-of-the-art review of fuel cell hybrid electric vehicle energy management systems. AIMS Energy 10: 458–485. https://doi.org/10.3934/energy.2022023 doi: 10.3934/energy.2022023
[7]	Kraa O, Ghodbane H, Saadi R, et al. (2015) Energy management of fuel cell/supercapacitor hybrid source based on linear and sliding mode control. Energy Proc 74: 1258–1264. https://doi.org/10.1016/j.egypro.2015.07.770 doi: 10.1016/j.egypro.2015.07.770
[8]	Eduardo EMJ, António MNQ, Santos DMF (2023) Economic analysis of lithium-ion battery recycling. AIMS Energy 11: 960–973. https://doi.org/10.3934/energy.2023045 doi: 10.3934/energy.2023045
[9]	Attanayaka AMSMHS, Karunadasa JP, Hemapala KTMU (2019) Estimation of state of charge for lithium-ion batteries—A review. AIMS Energy 7: 186–210. https://doi.org/10.3934/energy.2019.2.186. doi: 10.3934/energy.2019.2.186
[10]	Steven BS, Zachary PC, Michael F, et al. (2018) Range-extending zinc-air battery for electric vehicle. AIMS Energy 6: 121–145. https://doi.org/10.3934/energy.2018.1.121 doi: 10.3934/energy.2018.1.121
[11]	Kritanjali D, Santanu S (2022) Coulombic efficiency estimation technique for eco-routing in electric vehicles. AIMS Energy 10: 356–374. https://doi.org/10.3934/energy.2022019 doi: 10.3934/energy.2022019
[12]	Caroline B, Stéphane R, Melika H, et al. (2021) Direct fuel cell—Supercapacitor hybrid power source for personal suburban transport. AIMS Energy 9: 1274–1298. https://doi.org/10.3934/energy.2021059. doi: 10.3934/energy.2021059
[13]	Geetha A, Subramani C (2017) A comprehensive review on energy management strategies of hybrid energy storage system for electric vehicles. Int J Energy Res 41: 1817–1835. https://doi.org/10.1002/er.3730 doi: 10.1002/er.3730
[14]	Ruchen H, Hongwen H, Xuyang Z, et. al. (2022) Battery health-aware and naturalistic data-driven energy management for hybrid electric bus based on TD3 deep reinforcement learning algorithm. Appl Energy 321: 119353. https://doi.org/10.1016/j.apenergy.2022.119353 doi: 10.1016/j.apenergy.2022.119353
[15]	Huang R, He H, Su Q (2024) Towards a fossil-free urban transport system: An intelligent cross-type transferable energy management framework based on deep transfer reinforcement learning. Appl Energy 363: 123080. https://doi.org/10.1016/j.apenergy.2024.123080 doi: 10.1016/j.apenergy.2024.123080
[16]	Berjoza D, Jurgena I (2017) Effects of change in the weight of electric vehicles on their performance characteristics. Agron Res 15: 952–963. Available from: https://agronomy.emu.ee/wp-content/uploads/2017/04/Vol15SP1_Berjoza.pdf.
[17]	Wang R, Shi X, Su Y, et. al. (2024) 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 1: 1–10. https://doi.org/10.1177/09544070241239996 doi: 10.1177/09544070241239996
[18]	Abdelrahman K, Samir K, Taher E (2023) Prediction of the equivalent circulation density using machine learning algorithms based on real-time data. AIMS Energy 11: 425–453. https://doi.org/10.3934/energy.2023023 doi: 10.3934/energy.2023023
[19]	Xiaoyu Z, Dewang C, Yusheng W, et al. (2023) Remaining useful life indirect prediction of lithium-ion batteries using CNN-BiGRU fusion model and TPE optimization. AIMS Energy 11: 896–917. https://doi.org/10.3934/energy.2023043 doi: 10.3934/energy.2023043
[20]	Linda G, Roy C (2002) Operation of an aluminum-intensive vehicle: Report on a six-year project. Cent Transp Res Argonne Natl Lab 1: 1–9. https://doi.org/10.4271/2002-01-2066 doi: 10.4271/2002-01-2066
[21]	Martin M, Igor GLK, Dalibor B (2016) Analysis of parameters influencing electric vehicle range. Proc Eng 134: 165–174. https://doi.org/10.1109/TII.2015.2404800 doi: 10.1109/TII.2015.2404800
[22]	Yang C, Du X, Wang W, et al. (2024) Variable optimization domain-based cooperative energy management strategy for connected plug-in hybrid electric vehicles. Energy 15: 1–17. https://doi.org/10.3390/wevj15080350 doi: 10.3390/wevj15080350
[23]	Rauh N, Franke T, Krems JF (2015) User experience with electric vehicles while driving in a critical range situation—A qualitative approach. IET Intell Transp Syst 9: 734–739. https://doi.org/10.1049/iet-its.2014.0214 doi: 10.1049/iet-its.2014.0214
[24]	Huang R, He H, Zhao X, et al. (2023) Longevity-aware energy management for fuel cell hybrid electric bus based on a novel proximal policy optimization deep reinforcement learning framework. J Power Sources 561: 232717. https://doi.org/10.1016/j.jpowsour.2023.232717 doi: 10.1016/j.jpowsour.2023.232717
[25]	Shuo Z, Rui X, Xuan Z (2015) Comparison of the topologies for a hybrid energy-storage system of electric vehicles via a novel optimization method. Sci China Technol Sci 58: 1173–1185. http://doi.org/10.1007/s11431-015-5843-y doi: 10.1007/s11431-015-5843-y
[26]	Qusay H, Sameer A, Aws ZS, Hayder MS, et al. (2023) A review of hybrid renewable energy systems: Solar and wind-powered solutions: Challenges, opportunities, and policy implications. Results Eng 20: 101621. https://doi.org/10.1016/j.rineng.2023.101621 doi: 10.1016/j.rineng.2023.101621
[27]	Staackmann M, Liaw BY, Yun DYY (1997) Dynamic driving cycle analyses using electric vehicle time-series data. IEEE Int Electr Veh Conf Proc 1: 2014–2018. http://doi.org/10.1109/IECEC.1997.656736. doi: 10.1109/IECEC.1997.656736
[28]	Momenimovahed A (2014) Real-time driving cycle measurements of ultrafine particle emissions from two wheelers and comparison with passenger cars. Int J Automot Technol 15: 1053−1061. http://doi.org/10.1007/s12239-014-0109-4 doi: 10.1007/s12239-014-0109-4
[29]	Zhihan L, Wenlong S (2023) Impacts of intelligent transportation systems on energy conservation and emission reduction of transport systems: A comprehensive review. Green Technol Sustainability 1: 100002. https://doi.org/10.1016/j.grets.2022.100002 doi: 10.1016/j.grets.2022.100002
[30]	Vishal P, Varshaben S (2015) Measurement and analysis of Indian road drive cycles for efficient and economic design of HEV component. World Electr Veh J 7: 1–12. https://doi.org/10.3390/wevj7010121 doi: 10.3390/wevj7010121

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)