Generative AI for O-RAN Slicing: A Semi-Supervised Approach with VAE and Contrastive Learning

TL;DR

This paper proposes a semi-supervised generative AI framework combining VAE and contrastive learning to optimize resource allocation and network slicing in O-RAN, improving throughput and service quality.

Contribution

It introduces a novel unified semi-supervised learning architecture that enhances resource management in O-RAN using VAE and contrastive learning.

Findings

Outperforms exhaustive search and deep Q-Network algorithms in efficiency.

Improves resource allocation accuracy and network slicing effectiveness.

Demonstrates robustness and generalization in dynamic mobile network scenarios.

Abstract

This paper introduces a novel generative AI (GAI)-driven, unified semi-supervised learning architecture for optimizing resource allocation and network slicing in O-RAN. Termed Generative Semi-Supervised VAE-Contrastive Learning, our approach maximizes the weighted user equipment (UE) throughput and allocates physical resource blocks (PRBs) to enhance the quality of service for eMBB and URLLC services. The GAI framework utilizes a dedicated xApp for intelligent power control and PRB allocation. This integrated GAI model synergistically combines the generative power of a VAE with contrastive learning to achieve robustness in an end-to-end trainable system. It is a semi-supervised training approach that concurrently optimizes supervised regression of resource allocation decisions (i.e., power, UE association, PRB) and unsupervised contrastive objectives. This intrinsic fusion improves the precision of resource management and model generalization in dynamic mobile networks. We evaluated our GAI methodology against exhaustive search and deep Q-Network algorithms using key performance metrics. Results show our integrated GAI approach offers superior efficiency and effectiveness in various scenarios, presenting a compelling GAI-based solution for critical network slicing and resource management challenges in next-generation O-RAN systems.