Strengthening network slicing for Industrial Internet with deep reinforcement learning

Abstract

Industrial Internet combines the industrial system with Internet connectivity to build a new manufacturing and service system covering the entire industry chain and value chain. Its highly heterogeneous network structure and diversified application requirements call for the applying of network slicing technology. Guaranteeing robust network slicing is essential for Industrial Internet, but it faces the challenge of complex slice topologies caused by the intricate interaction relationships among Network Functions (NFs) composing the slice. Existing works have not concerned the strengthening problem of industrial network slicing regarding its complex network properties. Towards this end, we aim to study this issue by intelligently selecting a subset of most valuable NFs with the minimum cost to satisfy the strengthening requirements. State-of-the-art AlphaGo series of algorithms and the advanced graph neural network technology are combined to build the solution. Simulation results demonstrate the superior performance of our scheme compared to the benchmark schemes.

Keywords

• Industrial Internet
• Network slicing
• Deep reinforcement learning
• Graph neural network