A Multi-Agent System for 5G Throughput Prediction in Multi-Operator Urban Environments
Networking and Internet ArchitectureArtificial Intelligence
Summary
The authors address the challenge of predicting data speeds in complex urban 6G networks, where traditional AI models fail to adapt well across different conditions. They introduce a Tiered Multi-Agent System (TMAS) that uses specialized micro-agents tailored to specific contexts like mobility type and traffic profile. Tested on real-world data from multiple cities and network operators, their system significantly improves prediction accuracy and operates very quickly, making it suitable for future wireless network needs. This approach helps bridge the gap between raw signal information and actual internet speeds users experience.
Authors
Muhammad Kabeer, Rosdiadee Nordin, Nadiva Nuriftitah, Sian Lun Lau
Abstract
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.