Enhancing 5G O-RAN Communication Efficiency Through AI-Based Latency Forecasting

2025-02-25

AI Summary

To address the challenges of low-latency assurance in dynamic 5G Open Radio Access Network (O-RAN) environments and the limited scalability and hardware validation of existing AI-based approaches, this paper proposes and implements the first end-to-end AI-driven real-time latency prediction system integrated into a fully functional O-RAN prototype. The system employs a Bidirectional Long Short-Term Memory (Bi-LSTM) network and is built upon the open-source FlexRIC platform, interfacing with the O-RAN Near-Real-Time RAN Intelligent Controller (RIC). It enables real-time data stream processing and hardware-in-the-loop validation. Crucially, it achieves the first deployment and live testing of a Bi-LSTM latency prediction model within a production-grade O-RAN architecture, overcoming prior limitations in deployment scalability and physical-layer verification. Experimental evaluation demonstrates a root-mean-square error below 0.04 and confirms substantial improvements in resource scheduling responsiveness and end-to-end latency stability under dynamic 5G channel conditions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

The increasing complexity and dynamic nature of 5G open radio access networks (O-RAN) pose significant challenges to maintaining low latency, high throughput, and resource efficiency. While existing methods leverage machine learning for latency prediction and resource management, they often lack real-world scalability and hardware validation. This paper addresses these limitations by presenting an artificial intelligence-driven latency forecasting system integrated into a functional O-RAN prototype. The system uses a bidirectional long short-term memory model to predict latency in real time within a scalable, open-source framework built with FlexRIC. Experimental results demonstrate the model's efficacy, achieving a loss metric below 0.04, thus validating its applicability in dynamic 5G environments.

Problem

• AI-based latency forecasting
• Enhancing 5G O-RAN efficiency
• Real-time scalable framework with FlexRIC

Innovation

• AI-driven latency forecasting system
• Bidirectional long short-term memory model
• Scalable open-source FlexRIC framework