A new IETF non-working group email list has been created. List address: [email protected] Archive: https://mailarchive.ietf.org/arch/search/?email_list=idnet To subscribe: https://www.ietf.org/mailman/listinfo/idnet
Purpose: The IDNet (Intelligence-Defined Network) is aiming to applying Artificial Intelligence technologies, including Machine Learning mechanisms, to networks. It can intelligently learn the network environment and react to dynamic situations. It can learn and complete complicated tasks, such as traffic load balancing associated with link utilities, autonomic network operation & maintenance dynamic flow&path controlling in large-scale network, etc. It can even predict the future network situation for proactive controlling. There will be new requirements for networks towards IDN, and new work on standards. This mail list is for discussion of IDN architecture, which focuses on applying machine learning into network, gap analysis, potential standard opportunities, etc. Its topics are including, but not limited: - use cases that AI could better manage&control network over traditional technologies - architecture or reference model for the Intelligence-Defined Network - integrate IDN with various network infrastructure architectures and IETF standards - gap analysis from the current and emerging IETF standards towards IDN - data requirements for AI network controlling, including new measurement technologies - network data selection, data structure & protocol for data transmission - distribution, and modifications and extensions if needed, for AI controlling result to network elements - integrate network expert knowledge and AI controlling mechanisms The scope of this mail list discussion is limited to machine learning. Identified standard work on IETF protocols will be provided to the appropriate Working Group, e.g. for network control-protocol functions, TEAS (e.g. ACTN) and PCE. For additional information, please contact the list administrators.
