@techreport{hong-nmrg-ai-deploy-07, number = {draft-hong-nmrg-ai-deploy-07}, type = {Internet-Draft}, institution = {Internet Engineering Task Force}, publisher = {Internet Engineering Task Force}, note = {Work in Progress}, url = {https://datatracker.ietf.org/doc/draft-hong-nmrg-ai-deploy/07/}, author = {Yong-Geun Hong and Joo-Sang Youn and Seung-Woo Hong and Ho-Sun Yoon and Pedro Martinez-Julia}, title = {{Considerations of network/system for AI services}}, pagetotal = 25, year = 2024, month = oct, day = 21, abstract = {As the development of AI technology matured and AI technology began to be applied in various fields, AI technology is changed from running only on very high-performance servers with small hardware, including microcontrollers, low-performance CPUs and AI chipsets. In this document, we consider how to configure the network and the system in terms of AI inference service to provide AI service in a distributed method. Also, we describe the points to be considered in the environment where a client connects to a cloud server and an edge device and requests an AI service. Some use cases of deploying network-based AI services, such as self-driving vehicles and network digital twins, are described.}, }