Abstract
Accurate forecasting of energy consumption has emerged as a critical requirement in the evolution of sustainable and intelligent transportation systems. This also helps in reduction of fuel costs thus causing lower carbon emission and optimal vehicle performance. Existing studies present various machine learning and deep learning models considering various features however lack to use state of art transformers. This study considers the features sets of operational and environmental using Feature Tokenizer Transformer (FT-Transformer). The proposed model considers feature tokenizer to learn both feature sets using self-attention mechanism. The approach interprets various machine learning methods with advanced neural architecture. The empirical analysis demonstrates that proposed model achieves the highest predictive results with lowest mean absolute error of 0.16, root means square of 0.21 and with R² value of 0.99 as compared to latest existing models in the relevant studies. In addition, we apply XAI based techniques which describes how the proposed model generate outputs helping to understand the factors influencing predictions and decisions. XAI methods of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) presents the significance of features and their role in overall prediction.
Data availability
The dataset is freely available at online repository Kaggle URL: Dataset 1 (https:/www.kaggle.com/datasets/programmer3/energy-aware-logistics-scheduling-dataset)Dataset 2 (https:/www.kaggle.com/datasets/ziya07/ev-energy-consumption-dataset).
Abbreviations
- \(\:\text{IQR}={Q}_{3}-{Q}_{1}\) :
-
Interquartile Range (IQR) technique
- X :
-
Raw value
- \(\:\text{{\rm\:M}}\) :
-
Raw value
- \(\:{\Sigma\:}\) :
-
Mean of the feature
- \(\:\left(x,y\right)\) :
-
Standard deviation
- \(\:p\left(x\right)p\left(y\right)\) :
-
Joint probability distribution function of X and Y
- \(\:{x}_{i}\) :
-
Marginal probability distributions o
- \(\:{y}_{i}\) :
-
Feature variables
- \(\:\left({x}_{i}-\stackrel{-}{x}\right)\) :
-
Individual sample
- \(\:\stackrel{-}{y}\) :
-
Predicted energy consumption for sample i
- \(\:\left({y}_{i}-\stackrel{-}{y}\right)\) :
-
Means of x and y.
- \(\:1-{R}_{i}^{2}\) :
-
Coefficient of determination matrices
- \(\:{W}^{\left(1\right)x}+{b}^{\left(1\right)}\) :
-
Weights and biases of layer l
- \(\:{f}^{\left(1\right)}\) :
-
Predicted energy consumption
- \(\:\left(d\times\:{h}_{1}+{h}_{1}\right)\) :
-
Parameters from input layer to first hidden layer (weights + biases)
- \(\:{\sum\:}_{i=1}^{L-2}\left({h}_{i}\times\:{h}_{i+1}+{h}_{i+1}\right)\) :
-
Parameters across hidden layers
- \(\:\left({h}_{L-1}\times\:o+o\right)\) :
-
Parameters from last hidden layer to output layer
- \(\:{\text{VIF}}_{i}\) :
-
Collinear features and omitted
- N :
-
Number of Samples
- LR:
-
Linear regression
- RF:
-
Random forest
- DT:
-
Decision tree
- XGB:
-
Extreme gradient boosting
- MLP:
-
Multi-layer perceptron
- FT:
-
Fourier/feature transformer
- MAE:
-
Mean absolute error
- RMSE:
-
Root mean square error
- R2 :
-
Coefficient of determination
- MAPE:
-
Mean absolute percentage error
- MSRE:
-
Mean squared relative error
- RMSRE:
-
Root mean squared relative error
- MARE:
-
Mean absolute relative error
- t-SNE:
-
t-distributed stochastic neighbor embedding
- GPU:
-
Graphics processing unit
- RMSPE:
-
Root mean squared percentage error
- ANN:
-
Artificial neural network
- MSE:
-
Mean squared error
- ML:
-
Machine Learning
- DL:
-
Deep learning
- NLP:
-
Natural language processing
- EV:
-
Electric vehicle
- RNN:
-
Recurrent neural network
- LSTM:
-
Long short-term memory
- AI:
-
Artificial Intelligence
References
Oubrahim, I. & Sefiani, N. An integrated multi-criteria decision-making approach for sustainable supply chain performance evaluation from a manufacturing perspective. Int. J. Prod. Perform. Manage. 74 (1), 304–339. https://doi.org/10.1108/IJPPM-09-2023-0464 (2024)
Gössling, S., Humpe, A. & Sun, Y. Y. Are emissions from global air transport significantly underestimated? Curr. Issues Tourism. 28, 695–708 (2025). https://doi.org/10.1080/13683500.2024.2337281
Hall, C. & van Asselt, H. Decarbonising the land transport sector: pathways towards enhanced global governance. Transp. Res. D Transp. Environ. 140, 104601 https://doi.org/10.1016/J.TRD.2025.104601 (2025).
Nazim, M. S., Rahman, M. M., Joha, M. I. & Jang, Y. M. An RNN-CNN-based parallel hybrid approach for battery state of charge (SoC) estimation under various temperatures and discharging cycle considering noisy conditions. World Electr. Veh. J. (2024)https://doi.org/10.3390/WEVJ15120562 (2024).
Song, X. et al. Sustainable operations of last Mile logistics based on machine learning processes. Processes 10 (12), 2524. https://doi.org/10.3390/PR10122524 (2022)
Zhang, S. Research on energy-saving packaging design based on artificial intelligence. Energy Rep. 8, 480–489. https://doi.org/10.1016/j.egyr.2022.05.069 (2022).
Wang, K. & Du, N. Real-time monitoring and energy consumption management strategy of cold chain logistics based on the internet of things. Energy Inf. 8, 1–20 (2025). https://doi.org/10.1186/S42162-025-00493-W
Sahin, D. O., Akleylek, S. & Kilic, E. LinRegDroid: detection of android malware using multiple linear regression Models-Based classifiers. IEEE Access. 10, 14246–14259. https://doi.org/10.1109/ACCESS.2022.3146363 (2022).
Baek, J. W. & Chung, K. Context deep neural network model for predicting depression risk using multiple regression. IEEE Access. 8, 18171–18181. https://doi.org/10.1109/ACCESS.2020.2968393 (2020).
Rezaei, O., Sahraeian, R. & Hosseini, S. M. H. A multi-objective optimization framework to design the closed-loop supply chain network using machine learning for demand prediction, process integration and optimization for sustainability, pp. 1–22, May (2025). https://doi.org/10.1007/S41660-025-00520-Z
Zalza, K., Nazim, M. S., Jang, Y. M. & Hudaya, C. Mar., UAV energy consumption prediction: A comparative study from four different deep learning models, pp. 0196–0199, (2025). https://doi.org/10.1109/ICAIIC64266.2025.10920767
Alkanhel, R. et al. Network intrusion detection based on feature selection and hybrid metaheuristic optimization. Computers Mater. Continua. 74 (2), 2677–2693 https://doi.org/10.32604/CMC.2023.033273 (2022).
Leng, J. et al. A loosely-coupled deep reinforcement learning approach for order acceptance decision of mass-individualized printed circuit board manufacturing in industry 4.0. J. Clean. Prod. 280, 124405 https://doi.org/10.1016/J.JCLEPRO.2020.124405 (2021).
Farzaneh, H. et al. Artificial intelligence evolution in smart buildings for energy efficiency. Appl. Sci. 11, 763 (2021). https://doi.org/10.3390/APP11020763
Abid, F. A survey of machine learning algorithms based forest fires prediction and detection systems. Fire Technol. 57, 559–590 (2021). https://doi.org/10.1007/S10694-020-01056-Z
Sarswatula, S. A., Pugh, T. & Prabhu, V. Modeling energy consumption using machine learning. Front. Manuf. Technol. 2, 855208 https://doi.org/10.3389/FMTEC.2022.855208 (2022).
Ribeiro, A. M. N. C., Carmo, D., Endo, P. R. X., Rosati, P. T. & Lynn, T. P. Short- and very short-term firm-level load forecasting for warehouses: A comparison of machine learning and deep learning models. Energies, 15, 750, https://doi.org/10.3390/EN15030750 (2022).
Ullah, I. et al. A comparative performance of machine learning algorithm to predict electric vehicles energy consumption: A path towards sustainability. Energy Environ. 33, 1583–1612 (2022). https://doi.org/10.1177/0958305X211044998
Mhlanga, D. Artificial intelligence and machine learning for energy consumption and production in emerging markets: A review. Energies 16, 745 (2023). https://doi.org/10.3390/EN16020745
Mansoursamaei, M., Moradi, M., González-Ramírez, R. G. & Lalla-Ruiz, E. Machine learning for promoting environmental sustainability in ports. J. Adv. Transp. 1, 2144733 (2023). https://doi.org/10.1155/2023/2144733
Gan, S., Zhang, Q. & Wang, Y. Energy consumption analysis of metropolitan logistics vehicles based on an ensemble K-means long short-term memory model. Energy Environ. https://doi.org/10.1177/0958305X241244488 (2024).
Eddaoudi, Z., Aarab, Z., Boudmen, K., Elghazi, A. & Rahmani, M. D. A brief review of energy consumption forecasting using machine learning models. Procedia Comput. Sci. 236, 33–40 https://doi.org/10.1016/J.PROCS.2024.05.001 (2024).
Zhang, X., Zhang, Z., Liu, Y., Xu, Z. & Qu, X. A review of machine learning approaches for electric vehicle energy consumption modelling in urban transportation. Renew. Energy https://doi.org/10.1016/j.renene.2024.121243 (2024).
Alshdadi, A. A. & Almazroi, A. A. Ayub, N. IoT-driven load forecasting with machine learning for logistics planning. Internet Things. 29, 101441 https://doi.org/10.1016/J.IOT.2024.101441 (2025).
Różycki, R., Solarska, D. A. & Waligóra, G. Energy-aware machine learning models—a review of recent techniques and perspectives. Energies 18, 2810 (2025). https://doi.org/10.3390/EN18112810
Hussain, I., Ching, K. B., Uttraphan, C., Tay, K. G. & Noor, A. Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study. Sci. Rep. 15, 1–20 (2025). https://doi.org/10.1038/S41598-025-94946-7
Dong, C. et al. A real-time prediction framework for energy consumption of electric buses using integrated machine learning algorithms. Transp. Res. E Logist Transp. Rev. 194, 103884 https://doi.org/10.1016/J.TRE.2024.103884 (2025).
Nazim, M. S., Jang, Y. M. & Chung, B. Machine Learning Based Battery Anomaly Detection Using Empirical Data, 6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024, pp. 847–850, (2024). https://doi.org/10.1109/ICAIIC60209.2024.10463489
Phiboonbanakit, T., Horanont, T., Huynh, V. N. & Supnithi, T. A hybrid reinforcement Learning-Based model for the vehicle routing problem in transportation logistics. IEEE Access. 9, 163325–163347. https://doi.org/10.1109/ACCESS.2021.3131799 (2021).
Slowik, M. & Urban, W. Machine learning short-term energy consumption forecasting for microgrids in a manufacturing plant. Energies 15, 3382 (2022). https://doi.org/10.3390/EN15093382
Abdelhamid, A. A. et al. Innovative feature selection method based on hybrid sine cosine and dipper throated optimization algorithms. IEEE Access. 11, 79750–79776. https://doi.org/10.1109/ACCESS.2023.3298955 (2023).
Antonopoulos, I. et al. Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review. Renew. Sustain. Energy Rev. 130, 109899 https://doi.org/10.1016/J.RSER.2020.109899 (2020).
Chen, Z., Xiao, F., Guo, F. & Yan, J. Interpretable machine learning for Building energy management: A state-of-the-art review. Adv. Appl. Energy. 9, 100123 https://doi.org/10.1016/J.ADAPEN.2023.100123 (2023).
Atteia, G. et al. Adaptive dynamic dipper throated optimization for feature selection in medical data. Computers Mater. Continua. 75 (1), 1883–1900 https://doi.org/10.32604/CMC.2023.031723 (2023).
Flores-García, E., Hoon Kwak, D., Jeong, Y. & Wiktorsson, M. Machine learning in smart production logistics: a review of technological capabilities. Int. J. Prod. Res. 63, 1898–1932 (2025). https://doi.org/10.1080/00207543.2024.2381145
Sun, P. et al. Deep reinforcement learning based low energy consumption scheduling approach design for urban electric logistics vehicle networks. Sci. Rep. 15 (1), 1–18 https://doi.org/10.1038/S41598-025-92916-7 (2025).
Shah, M. A. & Wicaksono, H. Leveraging machine learning for power consumption prediction of Multi-Step production processes in dynamic electricity price environment. Procedia CIRP. 130, 226–231 https://doi.org/10.1016/J.PROCIR.2024.10.080 (2024).
Long, X., Cai, W., Yang, L. & Huang, H. Improved particle swarm optimization with reverse learning and neighbor adjustment for space surveillance network task scheduling. Swarm Evol. Comput. https://doi.org/10.1016/J.SWEVO.2024.101482 (2024).
El-Kenawy, E. S. M. et al. Metaheuristic optimization for improving weed detection in wheat images captured by drones. Mathematics 10, 4421 (2022). https://doi.org/10.3390/MATH10234421
Wei, M., Yang, S., Wu, W. & Sun, B. A multi-objective fuzzy optimization model for multi-type aircraft flight scheduling problem. Transport 39, 313–322 (2024). https://doi.org/10.3846/TRANSPORT.2024.20536
Fulginei, F. R. & Zournatzidou, G. Advancing sustainability through machine learning: modeling and forecasting renewable energy consumption. Sustainability 17, 1304. (2025). https://doi.org/10.3390/SU17031304
Naz, A. et al. Using Transformers and Bi-LSTM with sentence embeddings for prediction of openness human personality trait. PeerJ Comput. Sci. 11, 1–42 https://doi.org/10.7717/PEERJ-CS.2781/SUPP-6 (2025).
Myriam, H. et al. Advanced Meta-Heuristic algorithm based on particle swarm and Al-Biruni Earth radius optimization methods for oral cancer detection. IEEE Access. 11, 23681–23700. https://doi.org/10.1109/ACCESS.2023.3253430 (2023).
Alghieth, M. & Sustain, A. I. A multi-modal deep learning framework for carbon footprint reduction in industrial manufacturing. Sustainability 17, 4134 (2025). https://doi.org/10.3390/SU17094134
Zhang, B., Sang, H., Meng, L., Jiang, X. & Lu, C. Knowledge- and data-driven hybrid method for lot streaming scheduling in hybrid flowshop with dynamic order arrivals. Comput. Oper. Res. 184, 107244 https://doi.org/10.1016/J.COR.2025.107244 (2025).
Li, Z., Gu, W., Shang, H., Zhang, G. & Zhou, G. Research on dynamic job shop scheduling problem with AGV based on DQN. Cluster Comput. 28, 1–18 (2025). https://doi.org/10.1007/S10586-024-04970-X
Zhang, B., Meng , Lu, L., Han, C. & Sang, H. Y. Automatic design of constructive heuristics for a reconfigurable distributed flowshop group scheduling problem. Comput. Oper. Res. https://doi.org/10.1016/j.cor.2023.106432 (2024).
Meng, Q. et al. Economic optimization operation approach of integrated energy system considering wind power consumption and flexible load regulation. J. Electr. Eng. Technol. 19 (1), 209–221 https://doi.org/10.1007/S42835-023-01572-2 (2023).
Zhou, Y. Improvement of visual servo system of industrial robot based on sliding mode control and deep reinforcement learning. Theoretical Nat. Sci. 41, 132–138 (2024). https://doi.org/10.54254/2753-8818/41/2024CH0168
Funding
Not applicable to this study.
Author information
Authors and Affiliations
Contributions
The author Lai Yan fully contributed to this study.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
Authors have no conflict of Interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yan, L. Energy consumption forecasting in logistics considering environmental and operational constraints using FT-transformer architecture. Sci Rep (2026). https://doi.org/10.1038/s41598-025-34414-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34414-4
