Predicting Network Performance Rhythms Based on Academic Cycles for Dynamic Bandwidth Management in Higher Education

DOI

10.2991/978-94-6239-781-1_6How to use a DOI?

Keywords

Predictive Network Monitoring; Academic Cycles; Bandwidth Management; Quality of Service; Campus Networks

Abstract

The digital transformation in higher education increasingly relies on robust network infrastructure, particularly with the rise of hybrid and remote learning models. However, conventional bandwidth management approaches often fail to capture the nuanced network usage dynamics tied to network performance rhythm patterns influenced by academic activities. This research addresses this critical gap by developing a novel machine learning-based predictive model utilizing Long Short-Term Memory (LSTM) for dynamic bandwidth allocation, designed to identify network performance patterns grounded in academic rhythms. By integrating granular Quality of Service (QoS) data, including throughput, latency, jitter, and packet loss, this model accurately predicts bandwidth demands during critical peak periods, such as assignment submission deadlines or simultaneous online classes. Our findings demonstrate that this model substantially optimizes dynamic bandwidth allocation, effectively mitigates network disruptions, and, crucially, ensures equitable service quality for both on-campus and remote students. The proposed approach enhances overall network stability and guarantees persistent educational access despite existing digital infrastructure disparities. Ultimately, this model offers an adaptive, sustainable, and data-driven solution for network management in higher education, paving the way for more resilient academic environments amid evolving technological demands. Future research could further validate the network performance rhythm model under constrained bandwidth scenarios.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, 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 license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Murhaban Murhaban
AU  - Suryadi Suryadi
AU  - Nica Astrianda
AU  - Mirna Ria Andini
PY  - 2026
DA  - 2026/09/30
TI  - Predicting Network Performance Rhythms Based on Academic Cycles for Dynamic Bandwidth Management in Higher Education
BT  - Proceedings of the 3rd International Conference on Applied Engineering, Sciences, Technology and Innovation (AESTI 2025)
PB  - Atlantis Press
SP  - 32
EP  - 42
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-781-1_6
DO  - 10.2991/978-94-6239-781-1_6
ID  - Murhaban2026
ER  -