Slicing-Based Artificial Intelligence Service Provisioning on the Network Edge: Balancing AI Service Performance and Resource Consumption of Data Management
Mushu Li, Jie Gao, Conghao Zhou, Xuemin Shen, Weihua Zhuang
Abstract
Edge intelligence leverages computing resources on the network edge to provide artificial intelligence (AI) services close to network users. As it enables fast inference and distributed learning, edge intelligence is envisioned to be an important component of 6G networks. In this article, we investigate AI service provisioning for supporting edge intelligence. First, we present the features and requirements of AI services. Then we introduce AI service data management and customize network slicing for AI services. Specifically, we propose a novel resource-pooling method to regularize service data exchange within the network edge while allocating network resources for AI services. Using this method, network resources can be properly allocated to network slices to fulfill AI service requirements. A trace-driven case study demonstrates that the proposed method can allow network slicing to satisfy diverse AI service performance requirements via the flexible selection of resource-pooling policies. In this study, we illustrate the necessity, challenge, and potential of AI service provisioning on the network edge and provide insights into resource management for AI services.