Quality of Service (QoS) is a critical factor in 5G networks, ensuring reliable and efficient communication across diverse applications. In this paper, we introduce Machine Learning (ML) algorithms to predict QoS parameters in 5G network slices, enabling early detection and optimization of service degradation. Our system leverages advanced ML models to analyse key features like Slice Type, User Mobility, Slice Priority, Throughput, Jitter, and other network metrics without relying on manual monitoring. This application predicts QoS parameters and provides insights to improve network performance, ensuring better resource allocation and user experience. The system is trained to distinguish patterns from real-world and synthetic datasets, including parameters such as CPU utilization, memory usage, and environmental conditions (e.g., weather and time of day). Early detection of QoS degradation can prevent major service disruptions, including reduced network reliability, increased latency, and poor user experience in critical applications like autonomous vehicles and telemedicine. Traditional methods for monitoring and optimizing QoS often require manual intervention and substantial computational resources. These approaches may lack the responsiveness and scalability required for modern 5G networks. Our proposed system uses an efficient, automated, and adaptive method to predict QoS by analysing multiple factors simultaneously. The application provides network operators with real-time insights and actionable recommendations to maintain optimal service quality. The process is implemented using advanced ML models, including Random Forest, Linear Regression model and Decision Tree Model, with Random Forest providing the best performance through hyperparameter tuning. We utilize an enhanced QoS dataset collected from Kaggle and enriched with synthetic data to simulate real-world 5G conditions. After dataset preprocessing— such as feature extraction, scaling, and encoding—model training is conducted, and the final optimized model is deployed using Django for real-time predictions and analysis.
Introduction
With the rapid advancement of 5G technology and its diverse, complex service requirements, ensuring Quality of Service (QoS) has become critical for delivering reliable and efficient network performance. Traditional QoS prediction methods struggle with the dynamic and large-scale nature of 5G networks, especially with features like network slicing which demand tailored resource allocation.
This project proposes a machine learning (ML)-based system to predict key QoS metrics—such as latency, jitter, and throughput—across 5G network slices. It employs algorithms including Random Forest, Decision Tree, and Linear Regression, combined with data preprocessing techniques like scaling and encoding, to improve prediction accuracy. The ML model is integrated into a Django web interface to provide real-time, user-friendly QoS predictions, facilitating proactive network management.
The system aims to address limitations of traditional models that often lack adaptability to nonlinear network behaviors and real-time data fluctuations. By automating QoS prediction, the project helps service providers optimize network resources, reduce operational costs, and maintain consistent service quality in applications ranging from autonomous vehicles to smart cities.
Comparative analysis of ML models shows Random Forest offers robust and accurate predictions by aggregating multiple decision trees, handling noise and complex patterns better than linear regression or single decision trees. The Django-based platform supports scalable deployment and real-time user interaction, enhancing network decision-making and planning.
Conclusion
The QoS Prediction in 5G Network Slices project successfully applies machine learning and web technologies to predict key Quality of Service (QoS) metrics like latency, jitter, and throughput, enabling efficient network resource allocation and improved performance. Using algorithm such as Random Forest, the project achieved reliable predictions from diverse input features, while a Django-based web application provided a user-friendly interface for seamless interaction. Despite challenges like data acquisition and integration, the project delivers a scalable, practical solution with potential applications in fields like telemedicine and autonomous vehicles, paving the way for smarter and more adaptive 5G networks.
References
[1] Rommer, S., et al. – 5G Core Networks: Powering Digitalization
[2] Huawei Technologies – QoS and QoE Management in 5G Networks
[3] Mitchell,T.M. – Machine Learning
[4] Haijun Zhang et al. – Network Slicing Based 5G and Future Mobile Networks
[5] Qi Wang et al. – Enable Advanced QoS-Aware Network Slicing in 5G Network
[6] Diana Hayder Hussein et al. – Quality of Service (QoS) Optimization in 5G Using Machine Learning
[7] Shivani Saini et al. – Enhancing QoS of Network Traffic Based on 5G Wireless Networking Using ML Approaches.