Daejeon University DONG-EUI University ETRI National Institute of Information and Communications Technology Huawei As the development of AI technology has matured and AI technology has begun to be applied in various fields, the execution environment has evolved from dedicated high-performance servers to commodity servers and affordable, small-scale hardware, including microcontrollers, low-performance CPUs, and AI chipsets. This document outlines how to configure the network and system for an AI inference service, providing AI services in a distributed manner. It also outlines the factors to consider when a client connects to a cloud server and an edge device to request an AI service. It describes some use cases for deploying network-based AI services, such as self-driving vehicles and network digital twins.