Curated Collaborative AI Edge with Network Data Analytics for B5G/6G Radio Access Networks

2025-06-30

AI Summary

In 5G RANs, energy consumption exceeds 50% of total network energy, and conventional functional split schemes fail to fully exploit data potential, leading to high operational expenditures (OPEX). Method: This paper proposes an edge–end collaborative intelligent RAN energy-efficiency optimization framework for B5G/6G scenarios. It introduces Curated Collaborative Learning (CCL) to dynamically select cooperative nodes and learning content, and integrates Distributed Unit Pooling (DUPS) to close the prediction–scheduling loop—overcoming limitations of traditional federated learning and static resource allocation. The framework unifies personalized federated learning, incremental learning, deep reinforcement learning, and network data analytics into a lightweight, efficient model. Contribution/Results: Experiments demonstrate 31.35–43.9% improvement in traffic prediction accuracy and an 89% gain in energy efficiency, significantly reducing OPEX. The framework establishes a novel paradigm for green, intelligent wireless access networks.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Despite advancements, Radio Access Networks (RAN) still account for over 50% of the total power consumption in 5G networks. Existing RAN split options do not fully harness data potential, presenting an opportunity to reduce operational expenditures. This paper addresses this opportunity through a twofold approach. First, highly accurate network traffic and user predictions are achieved using the proposed Curated Collaborative Learning (CCL) framework, which selectively collaborates with relevant correlated data for traffic forecasting. CCL optimally determines whom, when, and what to collaborate with, significantly outperforming state-of-the-art approaches, including global, federated, personalized federated, and cyclic institutional incremental learnings by 43.9%, 39.1%, 40.8%, and 31.35%, respectively. Second, the Distributed Unit Pooling Scheme (DUPS) is proposed, leveraging deep reinforcement learning and prediction inferences from CCL to reduce the number of active DU servers efficiently. DUPS dynamically redirects traffic from underutilized DU servers to optimize resource use, improving energy efficiency by up to 89% over conventional strategies, translating into substantial monetary benefits for operators. By integrating CCL-driven predictions with DUPS, this paper demonstrates a transformative approach for minimizing energy consumption and operational costs in 5G RANs, significantly enhancing efficiency and cost-effectiveness.

Problem

• Reducing power consumption in 5G Radio Access Networks (RAN).
• Optimizing data collaboration for accurate network traffic predictions.
• Improving energy efficiency via dynamic DU server resource allocation.

Innovation

• Curated Collaborative Learning for traffic forecasting
• Deep reinforcement learning for DU server optimization
• Dynamic traffic redirection to improve energy efficiency