{"title":"NWDAF UDI (Use-case Development Interface) for End-to-end AI Enabled 5G and Beyond Networks","authors":"Hale Donertasli, Madhukiran Medithe","doi":"10.1109/ICAIoT57170.2022.10121746","DOIUrl":null,"url":null,"abstract":"The Network Data Analyses Function (NWDAF) is a 3GPP standard that enables the use of Machine Learning (ML) models to automate the heavy data analytics in 5G. NWDAF generates and analyzes 5G network data, and network entities behave accordingly depending on the gleaned knowledge. There is a potential for a 5G network to be managed via closed loop end-to-end NWDAF use-cases. Despite this, there hasn’t been much research done in the subject recently. This paper explains NWDAF Use-case Development Interface (UDI) which defines the protocols between producers and consumers for them to interact for data exchange and then later on to track the actions being decided to be taken and their evaluation feedback based on the results of the 5G network. Furthermore, we describe unresolved issues and thoroughly review relevant work, and then define NWDAF UDI which provides SBA based HTTP APIs for NWDAF use-case developers to create closed loop 5G network management involving NFs, AFs, OAM, slice manager and RAN, TN, CN domain controllers.","PeriodicalId":297735,"journal":{"name":"2022 International Conference on Artificial Intelligence of Things (ICAIoT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Artificial Intelligence of Things (ICAIoT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAIoT57170.2022.10121746","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The Network Data Analyses Function (NWDAF) is a 3GPP standard that enables the use of Machine Learning (ML) models to automate the heavy data analytics in 5G. NWDAF generates and analyzes 5G network data, and network entities behave accordingly depending on the gleaned knowledge. There is a potential for a 5G network to be managed via closed loop end-to-end NWDAF use-cases. Despite this, there hasn’t been much research done in the subject recently. This paper explains NWDAF Use-case Development Interface (UDI) which defines the protocols between producers and consumers for them to interact for data exchange and then later on to track the actions being decided to be taken and their evaluation feedback based on the results of the 5G network. Furthermore, we describe unresolved issues and thoroughly review relevant work, and then define NWDAF UDI which provides SBA based HTTP APIs for NWDAF use-case developers to create closed loop 5G network management involving NFs, AFs, OAM, slice manager and RAN, TN, CN domain controllers.