Real-Time Embedded System Optimization Using Edge Computing and Lightweight Deep Learning Architectures for Data Efficiency

C. Madana Kumar Reddy, Rajesh Kumar K., P. Chellammal, S. Muthuselvan, Evangelin M., A. Swathi

2025

Abstract

The growing need for intelligent systems led to rapid developments in edge computing and deep learning which enabled intelligent real-time processing in embedded systems. But meeting low latency, energy efficient and scalable performance in resource constrained environment is still a main challenge. The study develops a systematic framework that combines adaptive lightweight deep learning architectures with real-time edge computing strategies to enhance embedded system performance. In contrast to static capabilities in existing works, this study recognizes the need for opportunity-driven dynamic optimization of all functionalities of the system during operations, as it must adapt model parameters and resource utilization based on changes succeeding environmental and operational alterations. In addition, the framework can be deployed in a scalable way across multi-node edge networks and includes techniques for local data processing, improving privacy and decreasing dependency on the cloud. We evaluated this approach experimentally on actual IoT and embedded hardware platforms reporting dramatic improvements in latency, energy, and data throughput. This work provides an end-to-end methodology for future-ready, intelligent embedded systems with a particular focus on providing improved data efficiency and autonomous function at the edge.

Paper Citation

in Harvard Style

Reddy C., K. R., Chellammal P., Muthuselvan S., M. E. and Swathi A. (2025). Real-Time Embedded System Optimization Using Edge Computing and Lightweight Deep Learning Architectures for Data Efficiency. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 665-671. DOI: 10.5220/0013870900004919

in Bibtex Style

@conference{icrdicct`2525,
author={C. Reddy and Rajesh K. and P. Chellammal and S. Muthuselvan and Evangelin M. and A. Swathi},
title={Real-Time Embedded System Optimization Using Edge Computing and Lightweight Deep Learning Architectures for Data Efficiency},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={665-671},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013870900004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - Real-Time Embedded System Optimization Using Edge Computing and Lightweight Deep Learning Architectures for Data Efficiency
SN - 978-989-758-777-1
AU - Reddy C.
AU - K. R.
AU - Chellammal P.
AU - Muthuselvan S.
AU - M. E.
AU - Swathi A.
PY - 2025
SP - 665
EP - 671
DO - 10.5220/0013870900004919
PB - SciTePress