Citation :

Abhishek Baer, 2025. "A Cloud-Edge Digital Twin Architecture for Adaptive Battery Health Management in Sustainable Transport Systems" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 1: 7-15.

Abstract :

This paper presents a cloud-edge digital twin frame- work designed to enhance battery lifecycle management within electric vehicles, contributing to sustainable transportation and advanced battery system engineering. The architecture integrates a static state-of-health (SOH) model trained offline with a dynamically retrained state-of-charge (SOC) model updated peri- odically via cloud-based machine learning. Using a public NASA battery dataset, the system employs random forest, light gradient boosting, and deep neural networks to achieve SOH estimation errors below 1.8% RMSE and SOC errors under 0.81% RMSE while maintaining inference times under one second—compatible with onboard BMS deployment. The retrainable SOC model adapts to aging effects, ensuring continued accuracy as battery capacity degrades. This adaptive digital twin supports predictive maintenance, real-time health monitoring, and optimized battery utilization, aligning with smart manufacturing and sustainable energy system goals by extending operational life and improving reliability in EV applications.

References :

[1] Pramesh Baral. Anticipatory autonomic management of poly-cloud environments: A machine intelligence paradigm. TechRxiv, November 21, 2025. DOI: 10.36227/techrxiv.176369699.93881867/v1.

[2] Pramesh Baral. Integrating spatially continuous environmental covariates into HMMs for animal behavior via kriging. TechRxiv, November 21, 2025. DOI: 10.36227/techrxiv.176369836.61018639/v1.

[3] Harsh Maheshwari. Efficient dynamic comparison-based dictionaries with working-set property: A new approach. In 2025 International Conference on Innovative Trends in Information Technology (ICITIIT), pages 1–4, 2025. DOI: 10.1109/ICITIIT64777.2025.11041481.

[4] Prem Kireet Chowdary Nimmalapudi. Development of RD-Gen: A random directed acyclic graph generator for multi-rate real-time systems. In 2025 Global Conference in Emerging Technology (GINOTECH), pages 1–10, 2025. DOI: 10.1109/GINOTECH63460.2025.11076900.

[5] Sibaram Prasad Panda. Leveraging generative models for efficient policy learning in offline reinforcement learning. In 2025 IEEE XXXII International Conference on Electronics, Electrical Engineering and Computing (INTERCON), pages 1–6, 2025. DOI: 10.1109/INTER- CON67304.2025.11244701.

[6] Sibaram Prasad Panda. Optimizing data stream partitioning to im- prove real-time performance in distributed messaging. In 2025 IEEE International Conference on Artificial Intelligence in Engi- neering and Technology (IICAIET), pages 185–190, 2025. DOI: 10.1109/IICAIET67254.2025.11265665.

[7] Pankaj Singh. Workload-driven perspectives on networked filesystems: Benchmarking NFS/SMB and version-level trade-offs. International Journal of Advanced Research and Interdisciplinary Scientific Endeav- ours, 3(4):975–981, 2025. DOI: 10.61359/11.2206-2553.

[8] Pankaj Singh. Reproducibility by construction: Open algorithms, public benchmarks, and cloud-native artifact pipelines. International Jour- nal of Advanced Research and Interdisciplinary Scientific Endeavours, 3(6):1091–1103, 2025. DOI: 10.61359/11.2206-2562.

[9] D. Jain. Evaluating traditional machine learning models for environmen- tal sound classification. Zenodo, 2025. DOI: 10.5281/zenodo.17378750.

[10] Sourabh Rajput. Interpretable AI for 3D structural recognition: A lightweight approach to point cloud segmentation. DOI: 10.31224/6161.

[11] Sourabh Rajput. AI-powered distance estimation for autonomous sys- tems: A monocular vision approach. DOI: 10.31224/6157.

[12] Bhargavi Ugandhar. An empirical investigation of replicability in machine learning research. Journal of Data Analysis and Artificial Intelligence, 4(3), 2025. DOI: 10.46632/jdaai/4/3/10.

[13] Nagajayant Nagamani. Scaling reasoning in AI: Challenges of long- context understanding in emerging models. Research and Reviews: Advancement in Robotics, 9(1):21–30, 2025. DOI: 10.5281/zen- odo.17231097.

[14] Himanshu Arora. Compiler-enhanced language for scalable data workflows. Preprints, December 2025. DOI: 10.20944/preprints202512.1016.v1.

[15] Vishal Paul. Bridging latent factors and tags: Enhancing recommen- dation systems. In 2024 International Conference on Communication, Computing, Smart Materials and Devices (ICCCSMD), pages 1–7, 2024. DOI: 10.1109/ICCCSMD63546.2024.11015184.

[16] Mridul Banik. Novel tensor norm optimization for neural network train- ing acceleration. In Proceedings of the 2025 International Conference on Artificial Intelligence and Its Applications (icARTi ’25), Article 11, 2025. DOI: https://doi.org/10.1145/3774791.3774805.

[17] Siddhant Sukhatankar. Visualizing optimization feedback: Latent space analysis embedding visualization. TechRxiv, November 05, 2025. DOI: https://doi.org/10.36227/techrxiv.176238029.94823245/v1.

[18] S. S. Madani, Y. Shabeer, M. Fowler, S. Panchal, H. Chaoui, S. Mekhilef, and K. See. Artificial intelligence and digital twin technologies for intel- ligent lithium-ion battery management systems: A comprehensive review of state estimation, lifecycle optimization, and cloud-edge integration. Batteries, vol. 11, no. 8, p. 298, 2025.

[19] J. N. Njoku, E. C. Nkoro, R. M. Medina, C. I. Nwakanma, J. M. Lee, andD. S. Kim. Leveraging digital twin technology for battery management: A case study review. IEEE Access, 2025.

[20] M. S. Lakshmi and V. A. Sarma. Energy storage system using digital twins with AI and IoT for efficient energy management and prolonged battery life in electric vehicles. In Proceedings of the 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICM- SCI), pp. 177–184, IEEE, Jan. 2025.

[21] R. Manimegalai, P. Vivekanandan, C. Badachi, S. Navaneethan, S. Chel- lam, and S. G. Rahul. AI-integrated digital twin for cloud-connected battery management in electric vehicles. In Proceedings of the 2025 International Conference on Smart & Sustainable Technology (INCSST),pp. 1–6, IEEE, July 2025.

[22] M. Cavus, D. Dissanayake, and M. Bell. Next generation of electric vehicles: AI-driven approaches for predictive maintenance and battery management. Energies, vol. 18, no. 5, p. 1041, 2025.

Keywords :

Digital Twin, Battery Management, State of Charge, State of Health, Electric Vehicles, Cloud-Edge Computing, Machine Learning, Sustainable Transportation.