In a multi-domain edge intelligence cloud (MDEIC) managed by multiple network operators, AI services are delivered by chains of virtual network functions (VNFs) executed in sequence, called AI service chains (AISCs). Therefore, achieving an efficient and economical AISC provisioning approach is essential. However, the interaction between the environmental characteristics (heterogeneity, resource constraints and limited information visibility) of MDEIC and the time-dependence of AISCs, introduces various challenges to AISC provisioning in MDEIC. In this paper, we first formulate the AISC provisioning problem as a partially observable stochastic game (POSG). Then, we propose a graph-and-time-based multi-agent AISC provisioning (GT-MAAISCP) approach to achieve the collaborative optimization of AISC provisioning cost, delay and availability. Specifically, each agent uses the graph-time dueling network (GTDN) architecture to extract network topology information and temporal relationships. Finally, the experimental results demonstrate that the proposed approach outperforms benchmark approaches in MDEIC and also illustrate its performance under varying network topologies and different numbers of local EICs (LEICs).

翻译：在多运营商管理的多域边缘智能云（MDEIC）中，AI服务通过链式执行的虚拟网络功能（VNF）序列——即AI服务链（AISC）——进行交付。因此，实现高效经济的AISC部署方法至关重要。然而，MDEIC的环境特征（异构性、资源约束及有限信息可见性）与AISC的时间依赖性之间的交互，为MDEIC中的AISC部署带来了多重挑战。本文首先将AISC部署问题建模为部分可观测随机博弈（POSG），继而提出一种基于图与时间维度的多智能体AISC部署方法（GT-MAAISCP），以实现部署成本、时延与可用性的协同优化。具体而言，每个智能体采用图-时间竞争网络（GTDN）架构提取网络拓扑信息与时序关系。实验结果表明，所提方法在MDEIC中优于基准方法，并进一步验证了其在异构网络拓扑及不同本地边缘智能云（LEIC）数量下的性能表现。