Yinqiu Liu, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Yonggang Wen, Dong In Kim
{"title":"数据中心网络中的生成式人工智能:基础、视角和案例研究","authors":"Yinqiu Liu, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Yonggang Wen, Dong In Kim","doi":"arxiv-2409.09343","DOIUrl":null,"url":null,"abstract":"Generative AI (GenAI), exemplified by Large Language Models (LLMs) such as\nOpenAI's ChatGPT, is revolutionizing various fields. Central to this\ntransformation is Data Center Networking (DCN), which not only provides the\ncomputational power necessary for GenAI training and inference but also\ndelivers GenAI-driven services to users. This article examines an interplay\nbetween GenAI and DCNs, highlighting their symbiotic relationship and mutual\nadvancements. We begin by reviewing current challenges within DCNs and discuss\nhow GenAI contributes to enhancing DCN capabilities through innovations, such\nas data augmentation, process automation, and domain transfer. We then focus on\nanalyzing the distinctive characteristics of GenAI workloads on DCNs, gaining\ninsights that catalyze the evolution of DCNs to more effectively support GenAI\nand LLMs. Moreover, to illustrate the seamless integration of GenAI with DCNs,\nwe present a case study on full-lifecycle DCN digital twins. In this study, we\nemploy LLMs equipped with Retrieval Augmented Generation (RAG) to formulate\noptimization problems for DCNs and adopt Diffusion-Deep Reinforcement Learning\n(DRL) for optimizing the RAG knowledge placement strategy. This approach not\nonly demonstrates the application of advanced GenAI methods within DCNs but\nalso positions the digital twin as a pivotal GenAI service operating on DCNs.\nWe anticipate that this article can promote further research into enhancing the\nvirtuous interaction between GenAI and DCNs.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"215 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generative AI in Data Center Networking: Fundamentals, Perspectives, and Case Study\",\"authors\":\"Yinqiu Liu, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Yonggang Wen, Dong In Kim\",\"doi\":\"arxiv-2409.09343\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generative AI (GenAI), exemplified by Large Language Models (LLMs) such as\\nOpenAI's ChatGPT, is revolutionizing various fields. Central to this\\ntransformation is Data Center Networking (DCN), which not only provides the\\ncomputational power necessary for GenAI training and inference but also\\ndelivers GenAI-driven services to users. This article examines an interplay\\nbetween GenAI and DCNs, highlighting their symbiotic relationship and mutual\\nadvancements. We begin by reviewing current challenges within DCNs and discuss\\nhow GenAI contributes to enhancing DCN capabilities through innovations, such\\nas data augmentation, process automation, and domain transfer. We then focus on\\nanalyzing the distinctive characteristics of GenAI workloads on DCNs, gaining\\ninsights that catalyze the evolution of DCNs to more effectively support GenAI\\nand LLMs. Moreover, to illustrate the seamless integration of GenAI with DCNs,\\nwe present a case study on full-lifecycle DCN digital twins. In this study, we\\nemploy LLMs equipped with Retrieval Augmented Generation (RAG) to formulate\\noptimization problems for DCNs and adopt Diffusion-Deep Reinforcement Learning\\n(DRL) for optimizing the RAG knowledge placement strategy. This approach not\\nonly demonstrates the application of advanced GenAI methods within DCNs but\\nalso positions the digital twin as a pivotal GenAI service operating on DCNs.\\nWe anticipate that this article can promote further research into enhancing the\\nvirtuous interaction between GenAI and DCNs.\",\"PeriodicalId\":501280,\"journal\":{\"name\":\"arXiv - CS - Networking and Internet Architecture\",\"volume\":\"215 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Networking and Internet Architecture\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.09343\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Networking and Internet Architecture","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09343","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Generative AI in Data Center Networking: Fundamentals, Perspectives, and Case Study
Generative AI (GenAI), exemplified by Large Language Models (LLMs) such as
OpenAI's ChatGPT, is revolutionizing various fields. Central to this
transformation is Data Center Networking (DCN), which not only provides the
computational power necessary for GenAI training and inference but also
delivers GenAI-driven services to users. This article examines an interplay
between GenAI and DCNs, highlighting their symbiotic relationship and mutual
advancements. We begin by reviewing current challenges within DCNs and discuss
how GenAI contributes to enhancing DCN capabilities through innovations, such
as data augmentation, process automation, and domain transfer. We then focus on
analyzing the distinctive characteristics of GenAI workloads on DCNs, gaining
insights that catalyze the evolution of DCNs to more effectively support GenAI
and LLMs. Moreover, to illustrate the seamless integration of GenAI with DCNs,
we present a case study on full-lifecycle DCN digital twins. In this study, we
employ LLMs equipped with Retrieval Augmented Generation (RAG) to formulate
optimization problems for DCNs and adopt Diffusion-Deep Reinforcement Learning
(DRL) for optimizing the RAG knowledge placement strategy. This approach not
only demonstrates the application of advanced GenAI methods within DCNs but
also positions the digital twin as a pivotal GenAI service operating on DCNs.
We anticipate that this article can promote further research into enhancing the
virtuous interaction between GenAI and DCNs.