Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Prediction of University Network Traffic Behaviour using LSTM and OGRU

Domaine:

digital infrastructure

Type de record:

paper
Créateur:
OmoOye
Éditeur:
Zenodo
Hôte:avatar

Recently, the surge in Internet usage across academic institutions has created a pressing need for effective and intelligent methods of predicting network traffic. These mechanisms are vital for efficient resource management, early detection of irregularities, strengthening cybersecurity, maintaining uninterrupted connectivity for both academic and administrative activities, and improving service quality. This research explores the application of Long Short-Term Memory (LSTM) and Optimized Gated Recurrent Unit (OGRU) models to study and predict network traffic trends within university settings. Both LSTM and OGRU are advanced deep learning frameworks designed to recognize temporal patterns in sequential data, making them well-suited for modelling intricate and dynamic network behaviours. The system undergoes some stages, such as Data collection, Data Pre-processing, Training stage, Testing Stage, Prediction stage, and Evaluation.  The data were splitted by assigning 70% to training, 10% validation, and 20% to testing.  The findings reveal that the proposed LSTM-based model performs robustly across all major metrics, achieving low values for (Test Loss: 0.000595), Mean Absolute Error (MAE: 0.009475), Mean Squared Error (MSE: 0.000584), and Root Mean Squared Error (RMSE: 0.024170), along with a high R² score, signifying outstanding accuracy and generalization capabilities. This indicates that LSTM has stronger predictive power better than the other model used.

Visit

doi.org

Tags

Network TrafficPredictionLong Short-Term MemoryOptimized Gated Recurrent Unit

Licenses

info:eu-repo/semantics/openAccessCreative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Video Streaming Data Traffic Prediction by Using Long Short Term Memory (LSTM) Model: In the case of UMTS Network in AddisNeural Network Prediction of Self-Similarity Network Trafficfle1scha/Deep-Learning-Network-Traffic-PredictionPrediction of Oil Palm Production Using Recurrent Neural Network Long Short-Term Memory (RNN-LSTM)Travel Time Prediction Under Egypt Heterogeneous Traffic Conditions Using Neural Network And Data FusionNeural Network-Based Prediction of Traffic Accidents and Congestion Levels Using Real-World Urban Road Data

Video Streaming Data Traffic Prediction by Using Long Short Term Memory (LSTM) Model: In the case of UMTS Network in Addis

Predictive analysis of mobile network traffic is fundamental for the next-generation cellular networ

Neural Network Prediction of Self-Similarity Network Traffic

Several factors are found to influence either short or long-term burstiness in Transmission Cont

fle1scha/Deep-Learning-Network-Traffic-Prediction

DL4NTP is an Honours-level research project investigating LSTM neural networks as network traffic pr

Prediction of Oil Palm Production Using Recurrent Neural Network Long Short-Term Memory (RNN-LSTM)

Travel Time Prediction Under Egypt Heterogeneous Traffic Conditions Using Neural Network And Data Fusion

Cairo is experiencing traffic congestion that places it among the worst in the world. Obviously, it

Neural Network-Based Prediction of Traffic Accidents and Congestion Levels Using Real-World Urban Road Data

This study presents a machine learning framework for predicting traffic accident occurrence and cong