Optimizing network resource allocation with graph pointer neural network in large-scale AI systems

Abstract

For increasingly complex communication demands of large-scale AI systems, the Space-Air-Ground Integrated Network (SAGIN) better caters to demands but also raises concerns about resource scarcity and diversity. This paper innovatively combines Graph Pointer Neural Networks (GPNN) and Reinforcement Learning (RL) to enhance resource allocation efficiency. The method leverages the advantages of GPNN in handling graph data and RL in optimizing decisions in dynamic environments. It also targets the optimization goal of maximizing resource allocation while minimizing deployment latency. This work begins by modeling its and elucidating the SAGIN logical architecture based on Software-defined Networking (SDN). Subsequently, it introduces an SFC deployment algorithm aimed at joint optimization of resource allocation and latency. The algorithm leverages GPNN and RL to deploy virtual nodes and links, with the goal of optimizing resource allocation and deployment latency. Experimental findings conclusively demonstrate the efficacy proposed algorithm in effectively weighing limited heterogeneous resources and minimum mapping delay. Notably, when compared to three other SFC mapping algorithms MLRL, NFVdeep, and RL, the proposed algorithm consistently outperforms them, with an average improvement of 10.17% in long-term average reward/cost, 11.21% in link resource utilization ratio, 15.34% in node resource utilization ratio, and 16.38% in acceptance ratio.