用AI代理实现5G网络自适应，响应速度低于10毫秒
Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
- 采用混合知识表示的协同式主动-被动运行时架构
- 5G RAN链路适配中实现<10毫秒实时控制，吞吐量提升4%
- 动态调制编码优化使误块率降低85%，适合高可靠场景
向第4级（L4）自治网络（AN）的演进标志着电信领域的战略转折点，要求网络超越被动自动化，具备真正的认知能力——实现TM论坛提出的自配置、自修复、自优化系统，提供零等待、零接触、零故障服务。本文通过在功能型认知系统中实现Joseph Sifakis的AN Agent参考架构，将理论与实践相结合，部署由混合知识表征驱动的协同主动-被动运行时。以无线接入网（RAN）链路适配（LA）代理的实证案例研究验证了该框架的变革潜力：在5G NR sub-6 GHz环境下实现小于10毫秒的实时控制，下行吞吐量比外环链路适配（OLLA）算法高出4%，并通过动态调制与编码方案（MCS）优化，将超可靠服务的块错误率（BLER）降低85%。这些成果证实该架构能有效突破传统自治瓶颈，推动关键的L4能力发展，迈向下一代目标。
原文摘要 · Abstract (English)
The evolution toward Level 4 (L4) Autonomous Networks (AN) represents a strategic inflection point in telecommunications, where networks must transcend reactive automation to achieve genuine cognitive capabilities--fulfilling TM Forum's vision of self-configuring, self-healing, and self-optimizing systems that deliver zero-wait, zero-touch, and zero-fault services. This work bridges the gap between architectural theory and operational reality by implementing Joseph Sifakis's AN Agent reference architecture in a functional cognitive system, deploying coordinated proactive-reactive runtimes driven by hybrid knowledge representation. Through an empirical case study of a Radio Access Network (RAN) Link Adaptation (LA) Agent, we validate this framework's transformative potential: demonstrating sub-10 ms real-time control in 5G NR sub-6 GHz while achieving 4% higher downlink throughput than Outer Loop Link Adaptation (OLLA) algorithms and 85% Block Error Rate (BLER) reduction for ultra-reliable services through dynamic Modulation and Coding Scheme (MCS) optimization. These improvements confirm the architecture's viability in overcoming traditional autonomy barriers and advancing critical L4-enabling capabilities toward next-generation objectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。