AI-Enabled Autonomous Network Slicing Optimization for 6G Communication Systems

Abstract

The advent of sixth-generation (6G) wireless communication networks introduces unprecedented demands for ultra-high data rates, near-zero latency, massive device connectivity, and hyper-reliability. To satisfy these heterogeneous service requirements simultaneously, network slicing has emerged as a foundational architectural paradigm. However, the static and reactive resource allocation strategies utilized in legacy generations are insufficient to cope with the highly dynamic, multi-dimensional, and time-varying nature of 6G traffic demands. This paper presents a comprehensive framework for artificial intelligence (AI)-enabled autonomous network slicing optimization in 6G systems. We investigate the application of advanced machine learning paradigms specifically deep reinforcement learning (DRL), federated learning (FL), and generative AI to orchestrate dynamic resource provisioning, cross-slice isolation, and proactive SLA (Service Level Agreement) enforcement. Through a robustly designed methodology combining centralized global coordination with decentralized edge execution, this study provides an optimized, self-healing, and intent-driven network orchestration architecture. The experimental evaluation illustrates that the proposed AI-driven framework outperforms conventional heuristics and static optimization models across critical performance metrics, including spectrum efficiency, SLA satisfaction rate, and computational overhead. The paper concludes by defining prominent research gaps and future directions toward standardizing fully autonomous, zero-touch 6G network management.