A Min-Max Fair Resource Allocation Framework for Optical x-haul and DU/CU in Multi-tenant O-RANs

TL;DR

This paper introduces a fair resource allocation framework for multi-tenant O-RAN networks, optimizing x-haul and DU/CU resources to improve efficiency, latency, and cost-effectiveness in cloud-based radio access architectures.

Contribution

It proposes a novel min-max fairness resource allocation framework for multi-tenant O-RANs, integrating TWDM-PON virtualization for enhanced low-latency connectivity.

Findings

Improved resource utilization and fairness among MNOs.

Reduced operational expenditure compared to baseline methods.

Enhanced system performance with virtual mesh interconnections.

Abstract

The recently proposed open-radio access network (O-RAN) architecture embraces cloudification and network function virtualization techniques to perform the base-band function processing by dis-aggregated radio units (RUs), distributed units (DUs), and centralized units (CUs). This enables the cloud-RAN vision in full, where mobile network operators (MNOs) could install their own RUs, but then lease on-demand computational resources for the processing of DU and CU functions from commonly available open-cloud (O-Cloud) servers via open x-haul interfaces due to variation of load over the day. This creates a multi-tenant scenario where multiple MNOs share networking as well as computational resources. In this paper, we propose a framework that dynamically allocates x-haul and DU/CU resources in a multi-tenant O-RAN ecosystem with min-max fairness guarantees. This framework ensures that a maximum number of RUs get sufficient resources while minimizing the OPEX for their MNOs. Moreover, in order to provide an access network architecture capable of sustaining low-latency and high capacity between RUs and edge-computing devices, we consider time-wavelength division multiplexed (TWDM) passive optical network (PON)-based x-haul interfaces where the PON virtualization technique is used to provide a direct optical connection between end-points. This creates a virtual mesh interconnection among all the nodes such that the RUs can be connected to the Edge-Clouds at macro-cell RU locations as well as to the O-Cloud servers at the central office locations. Furthermore, we analyze the system performance with our proposed framework and show that MNOs can operate with a better cost-efficiency than baseline greedy resource allocation with uniform cost-sharing.