Quality of Experience (QoE) and Network Performance Modelling for Multimedia Traffic

Table 6.

Directions for Future Research on QoEModelling


Future Research Area	Description	Expected Outcome / Benefit	Relevance to Study

AI-Driven QoE Prediction	Integrate deep learning and reinforcement learning algorithms to enhance QoE estimation accuracy under dynamic network conditions.	Real-time, adaptive prediction of user experience with minimal latency.	Extends the proposed hybrid model into intelligent automation.
Cross-Layer Optimization	Develop integrated frameworks combining network, transport, and application layers for holistic QoE management.	Improved end-to-end performance through coordinated resource allocation.	Strengthens the theoretical link between QoS and QoE.
Immersive Media (AR/VR, Cloud Gaming)	Apply QoE modeling to new media types requiring ultra-low latency and high bandwidth.	Improved user satisfaction in next-generation multimedia services.	Expands applicability of the model to future technologies.
Real-World Validation	Conduct empirical tests using user feedback and live network environments.	Verification of model accuracy and adaptability in real deployment scenarios.	Confirms the model’s reliability beyond simulation.
Energy- and Cost-Aware QoE Optimization	Combine QoE improvement with energy efficiency and cost-effectiveness goals.	Sustainable and optimized multimedia service delivery.	Aligns with global trends toward green communication systems.