Towards Green AI: A Novel Hybrid Filter Based AI Approach for Energy Efficient State of Charge and Energy Estimation in Li-Ion Batteries Under Various Drive Cycles
The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Artificial intelligence models usually need a hefty dataset, which indeed requires more computational time, energy consumption, and laborious work to train the models to achieve accurate results. These models consume more energy to deliver output. Therefore, in this work proposes a novel filter technique (FT) based on an average reduction method. This approach improves the quality of the dataset, i.e., reduces volume and averages similar data to find the precision. This novel FT was incorporated with the convolutional neural network with bidirectional long short-term memory network (FT-CNN-Bi-LSTM) model and tested on four dynamic drive cycle circumstances. The key objective of this modelling technique is to enhance the performance and computational efficiency of the state of charge (SOC) and state of energy (SOE) of rechargeable battery systems such as lithium-ion batteries. A comparison examination was performed by proposed models configured with FT and traditional models, including FT-CNN, FT-LSTM, FT-BiLSTM, and FT-CNN-LSTM. The comparison examines SOC and SOE estimation efficacy and the model's capabilities and limitations. The FT-CNN-BiLSTM model was significantly tested on multiple dynamic drive cycles, including HWFET, LA92, UDDS, and US06. These drive cycle datasets were collected from our laboratory, where experiments were conducted at ambient temperature. The FT-CNN-Bi-LSTM approach achieved percentage improvements, 99.98% of RMSE, 99.97% of MSE, and 99.96% of MAE. The significant percentage improvement in computational time and energy consumption ranges from 59 to 66% and 61 to 68%. These results demonstrate superior efficiency for rapid SOC and SOE estimation in all dynamic drive cycles.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Using Green AI principles, which emphasize improving AI models' sustainability and energy efciency, is one strategy [183].”
Citations
Cites
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00815-1 · Cited by 2,678 · cited 1×
“Thelargevolumeof Thelargevolumeof repeated data is a time-consuming and computationally difficult requirement during modeling [7], [8].”
Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020) · Communications of the ACM · doi:10.1145/3381831 · Cited by 1,647
Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey
Nguyen, G., Dlugolinsky, S., Bobák, M., Tran, V., López García, Á., Heredia, I., Malík, P., & Hluchý, L. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-018-09679-z · Cited by 864 · cited 1×
“Thelargevolumeof Thelargevolumeof repeated data is a time-consuming and computationally difficult requirement during modeling [7], [8].”
A review of green artificial intelligence: Towards a more sustainable future
Bolón-Canedo, V., Morán-Fernández, L., Cancela, B., & Alonso-Betanzos, A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128096 · Cited by 486
State-of-Charge Estimation of Li-Ion Battery in Electric Vehicles: A Deep Neural Network Approach
How, D. N. T., Hannan, M. A., Lipu, M. S. H., Sahari, K. S. M., Ker, P. J., & Muttaqi, K. M. (2020) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2020.3004294 · Cited by 337
Ma, L., Hu, C., & Cheng, F. (2021) · Journal of Energy Storage · doi:10.1016/j.est.2021.102440 · Cited by 308 · cited 1×
“The Ma. L. et al. [24] incorporated DNN-based LSTM models to estimate SOC and SOE jointly without establishing extra calculations between SOC and SOE.”
Sarker, I. H., Kayes, A. S. M., & Watters, P. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0219-y · Cited by 287 · cited 1×
“In contrast, theaccuraciesandcomputationaltimeofdata-drivenapproaches dependonthenatureofthedatasets[5],[6].”
Shrivastava, P., Kok Soon, T., Bin Idris, M. Y. I., Mekhilef, S., & Adnan, S. B. R. S. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3051655 · Cited by 280 · cited 2×
“Recently, [19], [21], [22], [23] proposed joint investigation approaches for SOC and SOE.”
InfluentialZhang, Y., Xiong, R., He, H., & Shen, W. (2017) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2016.2603229 · Cited by 235 · cited 1×
“The SOE is related to energy consumption and is similarly important to the BMS as well as to the SOC [18].”
Cai, L., Meng, J., Stroe, D.-I., Peng, J., Luo, G., & Teodorescu, R. (2020) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2020.2987383 · Cited by 194 · cited 1×
“Theyalsoneedregularretrainingtoupdatetheir hyperparameters [17].”
Bhattacharjee, A., Verma, A., Mishra, S., & Saha, T. K. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3064287 · Cited by 181
Li, K., Wei, F., Tseng, K. J., & Soong, B.-H. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2779411 · Cited by 160
State-of-Charge Estimation for Li-Ion Batteries: A More Accurate Hybrid Approach
Misyris, G. S., Doukas, D. I., Papadopoulos, T. A., Labridis, D. P., & Agelidis, V. G. (2019) · IEEE Transactions on Energy Conversion · doi:10.1109/tec.2018.2861994 · Cited by 134 · cited 1×
“Inaddition,AImodelsoutperformthantraditional modelsbutrequirehoursoftrainingonlargeamountsofbattery datasets[16].”
Chen, L., Wang, Z., Lu, Z., Li, J., Ji, B., Wei, H., & Pan, H. (2018) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2017.2782721 · Cited by 102 · cited 1×
“However,optimization methodslikeparticleswarmoptimization[11]andgeneticalgo-rithms[12]canbecombinedwithAImodelstooptimizehyper-parameters.”
Pan, D., Li, H., & Wang, S. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3142757 · Cited by 99 · cited 1×
“Thepre-existingreports[13],[14],[15] usedlargedatasetstotraininitialestimators.”
Zhang, S., & Zhang, X. (2021) · Electrochimica Acta · doi:10.1016/j.electacta.2021.139637 · Cited by 86 · cited 1×
“Recently, [19], [21], [22], [23] proposed joint investigation approaches for SOC and SOE.”
Chen, L., Song, Y., Lopes, A. M., Bao, X., Zhang, Z., & Lin, Y. (2024) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2023.3291501 · Cited by 85 · cited 2×
“The SOC and SOE can be represented by (1) and (2), [20].”
InfluentialHannan, M. A., How, D. N. T., Mansor, M. B., Hossain Lipu, M. S., Ker, P., & Muttaqi, K. (2021) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2021.3065194 · Cited by 70 · cited 1×
“The AI models include gated recurrent units [9] and long short-termmemory[10]toachievegoodestimationresultsunder variousloadanddrivecyclecircumstancesbutrequirealot ofcomputationalburdenanddatasets.”
Zhao, Y., Li, Y., Cao, Y., Jiang, L. Z., Wan, J., & Rehtanz, C. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3267500 · Cited by 67 · cited 2×
“The AI models include gated recurrent units [9] and long short-termmemory[10]toachievegoodestimationresultsunder variousloadanddrivecyclecircumstancesbutrequirealot ofcomputationalburdenanddatasets.”
Chen, L., Ding, Y., Wang, H., Wang, Y., Liu, B., Wu, S., Li, H., & Pan, H. (2022) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2021.3107727 · Cited by 66
An, F., Jiang, J., Zhang, W., Zhang, C., & Fan, X. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3125194 · Cited by 60 · cited 1×
“Recently, [19], [21], [22], [23] proposed joint investigation approaches for SOC and SOE.”
Upadhyaya, A., & Mahanta, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3316191 · Cited by 57 · cited 1×
“The SOC and SOE estimation has some limitations, i.e., unsuitable battery state estimation frameworks, complex mathematical designs, inadequate adaptability and instability [2].”
Antón, J. C. Á., Nieto, P. J. G., García–Gonzalo, E., Viera, J. C., Vega, M. G., & Viejo, C. B. (2015) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2015.2504933 · Cited by 36 · cited 1×
“However,optimization methodslikeparticleswarmoptimization[11]andgeneticalgo-rithms[12]canbecombinedwithAImodelstooptimizehyper-parameters.”
Ruan, G., Liu, Z., Cheng, J., Hu, X., Chen, S., Liu, S., Guo, Y., & Yang, K. (2024) · Energy · doi:10.1016/j.energy.2024.132161 · Cited by 32
Xiao, R., Yang, Y., Jia, X., & Nan, P. (2023) · Energy · doi:10.1016/j.energy.2023.127305 · Cited by 23
Ma, C., Sun, Y., Zhang, P., Song, F., Feng, Y., He, Y., & Zhang, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3342856 · Cited by 23 · cited 1×
“Thepre-existingreports[13],[14],[15] usedlargedatasetstotraininitialestimators.”
Kumar, D., Rizwan, M., & Panwar, A. K. (2023) · 2023 IEEE International Conference on Power Electronics, Smart Grid, and Renewable Energy (PESGRE) · doi:10.1109/pesgre58662.2023.10404810 · Cited by 9 · cited 4×
“In this section, the proposed AI models, experimental setup and evaluation matrices were used from our previous work [1].”
InfluentialSelf-citation
Cited by
Optimizing lithium-ion battery manufacturing with digitalization and AI-driven frameworks
Manoharan, A., Chong, J. J., Choong, Z. J., Lambert, S., Gupta, R. K., Chandra, D., Jain, A., Rao, A., & Sharma, A. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-17129-8 · Cited by 17
“Therefore, Technology and Inno-vation Partners developing these models need to carefully assess data diversity, balance, and relevance when designing AI frameworks [173].”
Vigneswar, N., Manivannan, R., & Abdissa, C. M. (2026) · IEEE Access · doi:10.1109/access.2026.3681620 · Cited by 11
“Kumar et al. [28] introduced an FT-CNN-BiLSTM framework that integrates a filter technique with CNN and BiLSTM architectures, reporting over 99.9% improvement in RMSE and MAE, along with more than 60% reductions in computation time and energy consumption compared to conventional methods.”
InfluentialKumar, D., Nasimov, R., Singh, A., Jha, A., Jha, A., & Rizwan, M. (2025) · Applied Computational Intelligence and Soft Computing · doi:10.1155/acis/5516151 · Cited by 8
“Using Green AI principles, which emphasize improving AI models’ sustainability and energy efciency, is one strategy [183].”
Self-citationState estimation for electric vehicles with deep learning- a survey
Leyla, E. F. E., & Tabak, A. (2026) · Electric Power Systems Research · doi:10.1016/j.epsr.2026.112800 · Cited by 4
Kumar, D., Ahmed, M., Jamil, M., Rizwan, M., & Panwar, A. K. (2026) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2025.3604739 · Cited by 3
“Therefore, this research article carefully addresses the environmental impact of AI algorithms, which have been ignored in previous works [1], [12], [13].”
Self-citation
Metadata
- Authors
- Kumar, D., Rizwan, M., & Panwar, A. K.
- Affiliations
- Delhi Technological University (IN)
- Venue
- IEEE Transactions on Industry Applications
- Published
- 2025-09
- Volume
- 61
- Issue
- 5
- Pages
- 7633-7645
- ISSN
- 0093-9994 (ISSN-L)
- 1939-9367
- OpenAlex
- W4408324306
- Cited by
- 11
- References
- 27
- Citations by year
- 2026: 5 · 2025: 6
- FWCI
- 2.68
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industry Applications (publishedVersion)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Battery Modeling and Management
- Physical Sciences › Engineering › Automotive Engineering › Electric and Hybrid Vehicle Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advancements in Battery Materials
- Keywords
- lithium-ion batteries, state of charge estimation, state of energy estimation, hybrid filter, data reduction, convolutional neural networks, bidirectional LSTM, driving cycles, energy consumption reduction, computational efficiency, green AI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.