CNN-Enabled Scheduling for Probabilistic Real-Time Guarantees in Industrial URLLC

2025-06-17

AI Summary

To address the joint guarantee of packet-level reliability and timeliness for ultra-reliable low-latency communication (URLLC) in industrial multi-cell, multi-channel wireless networks, this paper proposes a CNN-driven dynamic link priority prediction framework, replacing conventional static link-dependent priority (LDP) scheduling. Our method innovatively integrates convolutional neural networks with graph coloring to enable adaptive interference coordination based on real-time network state, traffic characteristics, and channel opportunities. We further introduce a novel offline-training–online-lightweight-inference architecture, enabling millisecond-scale priority reconfiguration. Experiments across three representative industrial network configurations demonstrate SINR improvements of 113%, 94%, and 49%, respectively. The framework significantly enhances resource utilization, schedulability, and probabilistic real-time guarantees—overcoming the performance limitations of static scheduling in highly dynamic industrial environments.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a CNN-based dynamic priority prediction mechanism for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach uses a Convolutional Neural Network and graph coloring to adaptively assign link priorities based on real-time traffic, transmission opportunities, and network conditions. Assuming that first training phase is performed offline, our approach introduced minimal overhead, while enabling more efficient resource allocation, boosting network capacity, SINR, and schedulability. Simulation results show SINR gains of up to 113%, 94%, and 49% over LDP across three network configurations, highlighting its effectiveness for complex URLLC scenarios.

Problem

• Enhancing URLLC in industrial networks with dynamic scheduling
• Improving interference coordination via CNN-based priority prediction
• Boosting network capacity and SINR with adaptive resource allocation

Innovation

• CNN-based dynamic priority prediction mechanism
• Graph coloring for adaptive link priorities
• Offline training with minimal overhead