Revolutionizing QoE-Driven Network Management with Digital Agent Technology in 6G

2024-12-03

arXiv.org

AI Summary

To address the QoE enhancement challenge in 6G networks—where conventional QoS-centric, single-dimensional optimization fails to capture user-centric performance—this paper proposes a Digital Agent (DA)-driven network management framework. To jointly model dynamic user behavior and complex environmental factors, we introduce a novel Behavior–Environment Coupled QoE metric. We further design a hierarchical, cooperative DA architecture enabling joint optimization of network orchestration and network slicing. The framework integrates three core mechanisms: DA-aware perception, adaptive scheduling algorithm selection, and elastic DA deployment. Experimental evaluation demonstrates that our approach achieves a 27.3% average QoE improvement over baseline schemes and increases user satisfaction for latency-sensitive services by 31.5%, validating its effectiveness and superiority in heterogeneous, dynamic 6G scenarios.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Algorithm Configuration
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

In this article, we propose a digital agent (DA)-assisted network management framework for future sixth generation (6G) networks considering users' quality of experience (QoE). Particularly, a novel QoE metric is defined by incorporating the impact of user behavior dynamics and environment complexity on quality of service (QoS). A two-level DA architecture is developed to assist the QoE-driven network orchestration and slicing, respectively. To further improve the performance of proposed framework, three potential solutions are presented from the perspectives of DA data collection, network scheduling algorithm selection, and DA deployment. A case study demonstrates that the proposed framework can effectively improve users' QoE compared with benchmark schemes.

Problem

• Enhance 6G network management
• Introduce QoE metric
• Propose two-level DA architecture

Innovation

• Digital agent-assisted network management
• Two-level DA architecture
• QoE-driven network slicing