Regression-based investigation of latency in automated networks
Latency defines a sizable performance parameter in measuring the system performance. In 5G networks, the latency required for real-world connectivity lies in the threshold of 5 ms. Current systems utilizing Cloud-Fog architecture are still struggling to achieve this target. Many proposed algorithm...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mehran University of Engineering and Technology
2025-07-01
|
| Series: | Mehran University Research Journal of Engineering and Technology |
| Subjects: | |
| Online Access: | https://murjet.muet.edu.pk/index.php/home/article/view/339 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Latency defines a sizable performance parameter in measuring the system performance. In 5G networks, the latency required for real-world connectivity lies in the threshold of 5 ms. Current systems utilizing Cloud-Fog architecture are still struggling to achieve this target. Many proposed algorithms are deployed to reduce the system latency to an acceptable level. Federated learning provides one such area where system latency can be reduced since the model, rather than the data, is transferred from the device to the Cloud. It results in reduced system processing time and enhanced performance. Regression analysis of such a system has predicted that the performance gap will persist with varying network nodes and increasing time limits. Hence, the federated learning-based architecture provides a reliable solution for reducing system latency. |
|---|---|
| ISSN: | 0254-7821 2413-7219 |