IEEE ComSoc Seminar 1- Enhancing Network Resilience via Detecting, Recovering, and Preventing Configuration-Induced Failures
#communications
#6G
Date and Time
- Date: Monday, 7 September 2026
- Time: 15:00 - 16:00 AWST
Location
- Venue: Room 434A, Building 105, Curtin University, Bentley Campus (room details to be confirmed)
- Online attendance:
- Microsoft Teams
Link: https://teams.microsoft.com/meet/47305401149961?p=1c0mVVDbT4wRqcsWuZ
Meeting ID: 473 054 011 499 61
Passcode: dG9D2JU7
- Microsoft Teams
Hosts
- IEEE Communications Society Western Australia Chapter (IEEE ComSoc WA Chapter)
- School of Electrical Engineering, Computing and Mathematical Sciences (EECMS), Curtin University
Registration
- No registration required.
Fee
- Free and open to IEEE members and non-members.
Contact
Dr Peng Chen
Chair, IEEE Communications Society WA Chapter
Email: peng.chen@curtin.edu.au
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Curtin University
- Perth, Western Australia
- Australia 6107
- Building: 105
- Room Number: 434A
- Click here for Map
- Contact Event Host
- Co-sponsored by Curtin University
Speakers
Wei of Edith Cowan University
Topic:
Enhancing Network Resilience via Detecting, Recovering, and Preventing Configuration-Induced Failures
Abstract: Modern networks are evolving into unified terrestrial, aerial, and satellite infrastructures under 6G, making sovereign network functions increasingly prone to configuration-induced failures that can cascade into network-wide outages. This talk presents a closed-loop Detect-Recover-Prevent framework for network resilience against such failures, addressing partial observability, inadequate automatability, and limited generalizability. By jointly modelling physical network entities and logical protocol states as a bipartite graph, a graph structural inconsistency detector localizes root causes through adaptive configuration encoding and inconsistency-aware attention, exposing subtle anomalies overlooked by rule-based methods. Building on this detection capability, interpretable agentic decision-making enables automated, risk-aware recovery, while ongoing work targets anticipation of unseen failure modes. Validated on emulated testbeds, the results demonstrate the potential of graph-based resilience as a key enabler of dependable network operation in 6G.
Biography:
Wei Ni (Fellow, IEEE) is the Associate Dean (Research) with the School of Engineering, Edith Cowan University, Perth. He was the Deputy Project Manager with Alcatel/Alcatel-Lucent Bell Labs from 2005 to 2008; a Senior Research Engineer with Nokia from 2008 to 2009; and a Senior Principal Research Scientist and Group Leader with the Commonwealth Scientific and Industrial Research Organization from 2009 to 2025. His research interests include distributed and trusted learning with constrained resources. He was a co-recipient of the ACM Conference on Computer and Communications Security (CCS) 2025 Distinguished Paper Award and four best paper awards. He was the Chair of the IEEE VTS NSW Chapter (2020–2022), the Workshop Co-Chair for ICC 2027, the PC Co-Chair for MSN 2026, the Track Chair for VTC-Spring 2017, the Track Co-Chair for IEEE VTC-Spring 2016, the Publication Chair for BodyNet 2015, and the Student Travel Grant Chair for WPMC 2014. He has been an Editor or a Senior Area Editor of IEEE Transactions on Wireless Communications since 2018, IEEE Transactions on Vehicular Technology since 2022, IEEE Transactions on Information Forensics and Security since 2024, IEEE Communication Surveys and Tutorials since 2024, IEEE Transactions on Network Science and Engineering since 2025, and IEEE Transactions on Cloud Computing since 2025.