🤖 AI Summary
In O-RAN multi-service network slicing scenarios, jointly optimizing weighted throughput and PRB allocation for eMBB and URLLC services remains challenging due to stringent latency constraints and dynamic traffic demands.
Method: We propose a dual-xAPP collaborative architecture integrating power control and PRB allocation, underpinned by a novel semi-supervised two-stage training paradigm: Stage I employs a Variational Autoencoder (VAE) for supervised regression modeling; Stage II incorporates contrastive learning to enhance generalization and robustness—overcoming limitations of purely supervised and reinforcement learning approaches.
Contribution/Results: Evaluated within the O-RAN near-real-time RIC framework, our method reduces PRB allocation error by 37% and improves weighted throughput by 22% relative to exhaustive search and DQN baselines, while achieving inference latency below 15 ms—satisfying URLLC’s ultra-low-latency requirements.
📝 Abstract
This paper introduces an innovative approach to the resource allocation problem, aiming to coordinate multiple independent x-applications (xAPPs) for network slicing and resource allocation in the Open Radio Access Network (O-RAN). Our approach maximizes the weighted throughput among user equipment (UE) and allocates physical resource blocks (PRBs). We prioritize two service types: enhanced Mobile Broadband and Ultra-Reliable Low-Latency Communication. Two xAPPs have been designed to achieve this: a power control xAPP for each UE and a PRB allocation xAPP. The method consists of a two-part training phase. The first part uses supervised learning with a Variational Autoencoder trained to regress the power transmission, UE association, and PRB allocation decisions, and the second part uses unsupervised learning with a contrastive loss approach to improve the generalization and robustness of the model. We evaluate the performance by comparing its results to those obtained from an exhaustive search and deep Q-network algorithms and reporting performance metrics for the regression task. The results demonstrate the superior efficiency of this approach in different scenarios among the service types, reaffirming its status as a more efficient and effective solution for network slicing problems compared to state-of-the-art methods. This innovative approach not only sets our research apart but also paves the way for exciting future advancements in resource allocation in O-RAN.