Windex: Realtime Neural Whittle Indexing for Scalable Service Guarantees in NextG Cellular Networks

TL;DR

Windex is a real-time neural network-based method that efficiently computes Whittle indices for resource allocation in NextG networks, significantly improving service guarantees and decision speed.

Contribution

The paper introduces Windex, a novel neural approach for fast, scalable resource allocation using Whittle indices in NextG cellular networks.

Findings

Achieves resource allocation decision times under 20μs per user.

Improves service guarantees over existing schedulers.

Validated on 3GPP service classes with real-world channel traces.

Abstract

We address the resource allocation challenges in NextG cellular radio access networks (RAN), where heterogeneous user applications demand guarantees on throughput and service regularity. We leverage the Whittle indexability property to decompose the resource allocation problem, enabling the independent computation of relative priorities for each user. By simply allocating resources in decreasing order of these indices, we transform the combinatorial complexity of resource allocation into a linear one. We propose Windex, a lightweight approach for training neural networks to compute Whittle indices, considering constraint violation, channel quality, and system load. Implemented on a real-time RAN intelligent controller (RIC), our approach enables resource allocation decision times of less than 20$\mu$s per user and efficiently allocates resources in each 1ms scheduling time slot. Evaluation across standardized 3GPP service classes demonstrates significant improvements in service guarantees compared to existing schedulers, validated through simulations and emulations with over-the-air channel traces on a 5G testbed.