Adaptive Network Function Chain Orchestration Strategy for 6G Inclusive Intelligent Services

In the upcoming 6G era, inclusive intelligent services (IISs) that rely on integrated communications and AI arithmetic will become the new norm. The IISs stem from numerous intelligent devices working collaboratively. However, with the proliferation of complex applications, providing differentiated and customized services through effective network function chain (NFC) orchestration has become a significant challenge. This paper proposes an adaptive NFC orchestration strategy (ANFCOS) for 6G IISs. ANFCOS prioritizes the tailored placement of virtual network functions (VNFs) and NFC embedding, catering to diverse quality of service requirements while minimizing orchestration costs. It models this process as a Markov decision process to simulate the dynamic process of network orchestration. And develops the multi-actor-attention-critic (MAAC) reinforcement learning. The strategy enables the deployment and operational cost optimization of multiple parallel NFCs, relying on a dynamic attention-shifting mechanism. Numerical results demonstrate that ANFCOS significantly enhances network performance and reduces NFC orchestration cost in 6G IISs. Compared with Multi-Agent Deep Deterministic Policy Gradient (MADDPG), Deep Deterministic Policy Gradient (DDPG) and Monte Carlo Tree Search (MCTS), the cost of orchestration was reduced by 8.2%, 22.1% and 28.6%.