AI-Powered Network Slicing for Joint Sensing and Communication in 6G Systems

Abstract

The rapid evolution of sixth generation (6G) wireless networks envisions a unified framework that integrates communication and sensing functionalities within a single infrastructure. This convergence, often referred to as Joint Sensing and Communication (JSC), demands highly flexible and intelligent resource management strategies. Traditional static or heuristic approaches to network slicing are insufficient to address the dynamic and heterogeneous requirements of JSC services, where stringent latency, reliability, and accuracy must coexist with massive connectivity and throughput.  The proposed approach leverages machine learning models to predict service demands, deceptively orchestrate slices, and ensure isolation across diverse use cases such as extended reality, vehicular communication, and environment-aware services.  The findings highlight the pivotal role of artificial intelligence in enabling reliable, low-latency, and resource-efficient JSC services within 6G infrastructures. This study provides a foundation for intelligent orchestration strategies that can accelerate the deployment of future 6G systems where communication and sensing coexist seamlessly.