MAC-Gyver: Open, Programmable, Scheduling for AI-RAN 6G Systems
2026-07-28 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors created MAC-Gyver, a toolkit that helps develop and test AI-based schedulers used in cellular networks, specifically inside the OpenAirInterface system. Their tool works both on real hardware and in a software emulator that mimics network behavior without requiring extra radio devices. They demonstrated two examples: one scheduler predicts when data will arrive to reduce delays, and another picks frequency bands smartly to improve performance. These examples show that MAC-Gyver lets researchers build, test, and use AI schedulers realistically in the same system.
MAC schedulerradio access networkOpenAirInterfacePHY-less emulator3GPP channel modeluplink schedulingpacket arrival predictionfrequency-selective schedulingAI in wireless networksreal-time network control
Authors
Maxime Elkael, Reshma Prasad, Tamerlan Aghayev, Salvatore D'Oro, Michele Polese, Tommaso Melodia
Abstract
Cellular networks are integrating Artificial Intelli- gence (AI) into radio access network control. The MAC scheduler is a promising target because it allocates a limited resource, spectrum, at every slot, under competing latency, throughput, and reliability requirements. However, most learning-based sched- ulers are evaluated only in simulation. Production schedulers are difficult to modify, and realistic stress tests require more radio hardware than most laboratories can provide. We present MAC-Gyver, an open-source framework for developing and evaluating scheduling applications that execute directly inside the OpenAirInterface scheduler. It exposes scheduler observations and controls through typed interfaces while preserving the underlying protocol and real-time execution paths. The same applications run over the air and in mac-emu, a PHY-less emulator that executes the unmodified OpenAirInterface Layer 2 stack for up to 90 users on one host at real-time slot pace, with a 3GPP-compliant channel model. To showcase the flexibility of MAC-Gyver, we evaluate two use cases. A proactive uplink scheduler predicts packet arrivals and roughly halves median round-trip latency. A frequency-selective uplink scheduler selects contiguous sub-bands from per-PRB sounding observations and is evaluated across mobility and power-limited operating points against an offline scheduling ceiling. Together, they show how the same production stack can be an AI playground that supports implementation, controlled evaluation, and over-the-air validation through complementary scheduling use cases.