Generative QoE Modeling: A Lightweight Approach for Telecom Networks

2025-04-30

AI Summary

To address the challenge of real-time Quality of Experience (QoE) prediction under resource-constrained and ultra-low-latency conditions in telecommunications networks, this paper proposes a lightweight generative modeling framework. The method innovatively integrates Vector Quantization (VQ) with a Hidden Markov Model (HMM) into a unified VQ-HMM paradigm: VQ discretizes continuous network features into compact symbolic representations, while HMM captures the temporal dynamics among these discrete states, enabling probabilistic inference for unseen samples. The framework achieves high prediction accuracy, strong interpretability, and minimal computational overhead. Evaluations on public time-series datasets demonstrate that its predictive performance matches that of deep learning models, while inference latency is substantially reduced—enabling practical deployment at the network edge. This capability supports real-time network resource orchestration and QoE assurance in operational 5G/6G environments.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Natural Language Processing: Generation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Quality of Experience (QoE) prediction plays a crucial role in optimizing resource management and enhancing user satisfaction across both telecommunication and OTT services. While recent advances predominantly rely on deep learning models, this study introduces a lightweight generative modeling framework that balances computational efficiency, interpretability, and predictive accuracy. By validating the use of Vector Quantization (VQ) as a preprocessing technique, continuous network features are effectively transformed into discrete categorical symbols, enabling integration with a Hidden Markov Model (HMM) for temporal sequence modeling. This VQ-HMM pipeline enhances the model's capacity to capture dynamic QoE patterns while supporting probabilistic inference on new and unseen data. Experimental results on publicly available time-series datasets incorporating both objective indicators and subjective QoE scores demonstrate the viability of this approach in real-time and resource-constrained environments, where inference latency is also critical. The framework offers a scalable alternative to complex deep learning methods, particularly in scenarios with limited computational resources or where latency constraints are critical.

Problem

• Lightweight QoE modeling for telecom and OTT services
• Balancing efficiency, interpretability, and predictive accuracy
• Enabling real-time QoE prediction in resource-constrained environments

Innovation

• Lightweight generative modeling for QoE prediction
• Vector Quantization with Hidden Markov Model
• Scalable alternative to deep learning methods