Skip to main content

Artificial Intelligence Framework for Network Management
draft-pedro-nmrg-ai-framework-01

The information below is for an old version of the document.
Document Type
This is an older version of an Internet-Draft whose latest revision state is "Active".
Expired & archived
Authors Pedro Martinez-Julia , Shunsuke Homma , Diego Lopez
Last updated 2023-01-07 (Latest revision 2022-07-06)
Replaces draft-pedro-nmrg-intelligent-reasoning
RFC stream (None)
Formats
Stream Stream state (No stream defined)
Consensus boilerplate Unknown
RFC Editor Note (None)
IESG IESG state Expired
Telechat date (None)
Responsible AD (None)
Send notices to (None)

This Internet-Draft is no longer active. A copy of the expired Internet-Draft is available in these formats:

Abstract

The adoption of artificial intelligence (AI) in network management (NM) solutions is becoming a reality. It is mainly supported by the need to resolve complex problems arisen from the acceptance of SDN/ NFV technologies as well as network slicing. Thus, the AINEMA framework, as discussed in this document, is required to keep focus and organize the efforts on applying AI to NM. This is enlarged by the inclusion of external events in NM operations as well as the consideration of a full intelligence process instead of simple AI- based guesses. Such process will be highly based in reasoning and formal and target-based intelligence analysis and decision. This will allow computer and network system infrastructures to grow in complexity. The same applies to user demands. The construction and maintenance of AINEMA requires a comprehensive inclusion of several mechanisms. For instance, although there has been a lot of effort to make Machine Learning (ML) solutions reliable and acceptable, other mechanisms have been forgotten. It is the particular case of reasoning, which is the key within AINEMA. It will provide enormous benefits to NM solutions by, for example, inferring new knowledge and applying different kind of rules (e.g. logical) to choose from several actions. While ML solutions work with data, so their only requirement from the network infrastructure is data retrieval, AINEMA will work in collaboration to the network it is managing. This makes the challenges arisen from intelligent reasoning essential for the evolution of NM. They will be addressed within the context of AINEMA.

Authors

Pedro Martinez-Julia
Shunsuke Homma
Diego Lopez

(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)