The APAN AI driven Networks Working Group (AINWG) has started at the APAN 50 meeting held in 2020 by having BoF (Birds of Feather) sessions. The aim of AINWG is to share experience to design, manage, maintain, and protect the network using artificial intelligence (AI) and escalate collaboration for AI driven networks in the APAN community.
Combining human intellect and creativity with the massive computing power of AI will create situations in which new design and management techniques may be created that humans could not build on their own, but self-improving intelligent algorithms will harness over time.
All activity of AINWG is to encourage the collaboration of technical experiences and knowledge regarding AI-enabled networks. This will lead to the development of an intelligent, scalable, sustainable, and easy-to-deploy technical platform for each APAN member country to manage its respective national research and education networks.
* 1st session at 9:00 am on March 5th (Wed)
- Mariam Kiran <kiranm@ornl.gov> from ORNL (USA) - virtual
Title: Using Segment routing for a truly self-driving AI network future.
Synopsis: In this presentation, we will present the recent collaboration between Hecate and Polka to use AI to develop a segment routing intelligent network. Using P4 and AI tools, this experiment helps us see how AI can directly impact traffic and lead to performance improvements.
- Dr. Yuichi Teranishi <teranisi@nict.go.jp> from NICT (Japan)
Title: Edge computing / networking for future AI-driven CPS
Synopsis: In this presentation, NICT's testbeds for evaluating edge computing/networking are introduced, along with research on dynamic resource allocations, secure data sharing, and fault-tolerant technologies that support energy-efficient, low-latency, and secure AI-driven Cyber Physical Systems.
Slides: attached.
- Kihyun Kim <kkh1258@kisti.re.kr> from KISTI (Korea)
Title: KREONET AI research environment provision platform for AI researchers
Synopsis:This platform is developed on an open-source basis, and it is a platform that provides an environment where researchers can easily use the computing environment and freely share research results among users using this platform.
- Dr. Changhua Pei <chpei@cnic.cn> from CNIC (China) - virtual
Title: Beyond Sharing: Conflict-Aware Multivariate Time-Series Anomaly Detection
Summary: MTS data of KPIs is crucial for system reliability, but existing AD methods overlook conflicts among metrics' regression objectives. Our CAD algorithm, with an MMoE structure and innovative designs, achieves an average F1 - score of 0.943 and outperforms existing methods.
Open Zoom
