Agentic DDQN-Based Scheduling for Licensed and Unlicensed Band Allocation in Sidelink Networks

2025-09-08

AI Summary

To address QoS degradation in NR sidelink networks—caused by licensed-spectrum sharing with cellular communications and unlicensed-spectrum coexistence with Wi-Fi—this paper proposes a DDQN-based autonomous agent scheduling framework. The framework jointly incorporates queue state, channel quality, and cross-technology interference awareness to enable online learning and adaptive evolution of dynamic resource allocation policies. Unlike conventional threshold-based methods constrained by static rules, it supports real-time decision-making under complex, time-varying network conditions. Experimental results demonstrate that, under licensed bandwidth scarcity, the proposed approach reduces communication blocking probability by up to 87.5%, while significantly improving spectral efficiency, system stability, and service reliability.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Multiagent Systems: Agent Communication
• Machine Learning: Online Learning & Bandits

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

This paper presents an agentic artificial intelligence (AI)-driven double deep Q-network (DDQN) scheduling framework for licensed and unlicensed band allocation in New Radio (NR) sidelink (SL) networks. SL must share licensed spectrum with cellular communications (CC) and unlicensed bands with Wi-Fi, posing significant challenges for coexistence. Unlike prior rule-based or threshold-based methods, the proposed agentic scheduler autonomously perceives queueing dynamics, channel conditions, and coexistence states, and adapts its policy to maintain quality-of-service (QoS). Simulation results show that our framework reduces the blocking rate by up to 87.5% compared to threshold-based scheduling under limited licensed bandwidth. These findings demonstrate the potential of Agentic AI to enable stable, QoS-aware, and adaptive scheduling for future NR SL systems.

Problem

• Allocating licensed and unlicensed bands in sidelink networks
• Managing spectrum sharing with cellular and Wi-Fi systems
• Ensuring quality-of-service in dynamic coexistence environments

Innovation

• Agentic AI-driven DDQN scheduling framework
• Autonomously perceives network dynamics and states
• Adapts policy to maintain quality-of-service QoS