ML and Smartphones Assisted Real-Time Uplink Performance Prediction in 5G Cellular System

2026-04-21T07:23:51Zc625fb71a4d6da6ece19619daaeb40c375a4ff4ac339ba23791b24064ab568e2
5GAoIBBRBLERIABIntel Tofino2LEO satelliteMARLMPEG-DASHQUICautonomous vehiclescongestion-controldeadlines`,`network-slicing`,`pinwheel-scheduling`,`RMAB`,`AoI-sdistributed traininghandoverin-networkmachine learningprogrammable switchring-based collectivessafety-criticalschedulingsmartphonessrsRANthroughput predictionuplink performance

What happened

This batch of CS/Networking papers (arXiv) covers applied research on 5G/LEO-satellite networks, in-network scheduling for distributed AI, age-of-information (AoI) and deadline-aware scheduling, wireless/optical resource configuration, and decentralized trust/IDS enhancements at the IoT edge. Key contributions: (1) ML + COTS smartphones predict 5G uplink throughput/BLER in a private srsRAN testbed (useful for network monitoring and optimization, with potential information‑leakage/traffic-analysis implications); (2) end-to-end MPEG-DASH streaming over LEO-based 5G IAB showing QUIC+BBR tradeoffs

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
arxiv_cs_ni
Record identifier
c625fb71a4d6da6ece19619daaeb40c375a4ff4ac339ba23791b24064ab568e2
Enrichment time
2026-04-21T07:23:51Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.