Intent-based Radio Scheduler for RAN Slicing: Learning to deal with different network scenarios

2025-01-01

AI Summary

To address the challenges of limited radio resources, heterogeneous multi-application QoS requirements, and frequent SLA violations in RAN slicing scenarios, this paper proposes an intent-driven multi-agent deep reinforcement learning (MADRL) scheduling framework. The framework formalizes network intents as optimization objectives and enables distributed agents to collaboratively perform fine-grained resource allocation under dynamic channel conditions and UE-specific feature modeling. A novel transfer learning mechanism is introduced to facilitate rapid cross-scenario policy adaptation—reducing training steps by 8× without performance degradation. Experimental results demonstrate that the framework improves SLA compliance for high-priority slices by 40% and increases the average SLA satisfaction rate across all slices by 20%, significantly outperforming baseline approaches.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Multiagent Systems: Multiagent Learning
• Machine Learning: Reinforcement Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The future mobile network has the complex mission of distributing available radio resources among various applications with different requirements. The radio access network slicing enables the creation of different logical networks by isolating and using dedicated resources for each group of applications. In this scenario, the radio resource scheduling (RRS) is responsible for distributing the radio resources available among the slices to fulfill their service-level agreement (SLA) requirements, prioritizing critical slices while minimizing the number of intent violations. Moreover, ensuring that the RRS can deal with a high diversity of network scenarios is essential. Several recent papers present advances in machine learning-based RRS. However, the scenarios and slice variety are restricted, which inhibits solid conclusions about the generalization capabilities of the models after deployment in real networks. This paper proposes an intent-based RRS using multi-agent reinforcement learning in a radio access network (RAN) slicing context. The proposed method protects high-priority slices when the available radio resources cannot fulfill all the slices. It uses transfer learning to reduce the number of training steps required. The proposed method and baselines are evaluated in different network scenarios that comprehend combinations of different slice types, channel trajectories, number of active slices and users' equipment (UEs), and UE characteristics. The proposed method outperformed the baselines in protecting slices with higher priority, obtaining an improvement of 40% and, when considering all the slices, obtaining an improvement of 20% in relation to the baselines. The results show that by using transfer learning, the required number of training steps could be reduced by a factor of eight without hurting performance.

Problem

• Intelligent Wireless Scheduler
• Resource Allocation
• Service Level Agreement (SLA) Violation Reduction

Innovation

• Multi-agent Reinforcement Learning
• Wireless Resource Scheduling
• Transfer Learning