用于多运营商城市环境中5G吞吐量预测的多智能体系统

中文摘要 AI 辅助

吞吐量预测是人工智能驱动的6G资源编排的基础。传统的整体机器学习模型难以在不同运营商、移动模式和流量类型之间进行泛化，在信号条件和可实现的吞吐量之间留下了关键的随机性差距。为了克服异构城市环境中的这些限制，我们提出了一种分层多智能体系统（TMAS），它将边缘遥测数据动态路由到上下文感知的域微智能体，并在马来西亚双威市收集的48618个样本数据集上进行了验证。该数据集使用Nemo Handy路测软件，涵盖三个一级移动网络运营商、三种移动模式和三种流量配置文件。我们的评估表明，TMAS克服了可预测性瓶颈，决定系数（R2）高达0.931，平均绝对误差（MAE）低至0.53Mbps。该系统具有较高的运行效率，微智能体训练时间短，推理延迟低，智能体路由开销为0.004至0.126ms。这些延迟特性表明该架构是下一代无线网络所需响应时间的一个有前途的候选方案。

英文摘要

Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration. Conventional monolithic machine learning models struggle to generalize across diverse operators, mobility modes, and traffic types, leaving a critical stochasticity gap between signal conditions and achievable throughput. To overcome these constraints in heterogeneous urban environments, we propose a Tiered Multi-Agent System (TMAS) that dynamically routes edge telemetry to context-aware Domain Micro-Agents, validated on a dataset of 48,618 samples collected in Sunway City, Malaysia, with Nemo Handy drive test software, spanning three Tier-1 mobile network operators, three mobility modes, namely (i) elevated pedestrian walkway, (ii) ground-level shuttle bus, and (iii) elevated bus rapid transit; and three traffic profiles, namely (i) persistent download, (ii) persistent upload, and (iii) adaptive video streaming. Our evaluations reveal that TMAS overcomes predictability bottlenecks, achieving a coefficient of determination (R2) of up to 0.931 and a Mean Absolute Error (MAE) as low as 0.53 Mbps. The system demonstrates high operational efficiency, with rapid micro-agent training times, low inference latencies, and agentic routing overhead of 0.004 to 0.126 ms. These latency characteristics indicate the architecture is a promising candidate for the response times required by next-generation wireless networks.

发表机构

• Faculty of Engineering and Technology, Sunway University（Sunway大学工程与技术学院）
• Department of Computer Science, Federal University Dutsinma（联邦大学杜辛马大学计算机科学系）
• Future Cities Research Institute (FCRI), Faculty of Engineering and Technology, Sunway University（Sunway大学工程与技术学院未来城市研究所）
• Future Cities Research Institute (FCRI), Lancaster University（兰卡斯特大学未来城市研究所）

机构由 AI 辅助整理，请以论文原文为准。