Adaptive Slicing for Intelligent Network Automation

The forthcoming 5G networks will be much more complex than their predecessors. They are on the verge of a generational transformation driven by the coverage, connectivity, availability, speed and latency demands of 5G. 5G networks will use network slicing to open up the network “as a service” to various third parties and their diversified applications, e.g., from autonomous vehicle control to massive machine-type communication for IoT devices. As a result, traditional monitoring tools designed only for the network layer will be no longer be fit for purpose in this new 5G environment.
In such a environment, humans will simply be incapable of managing the interplay and orchestration of the Quality of Service (Gos) on which applications depend. Artificial intelligence (AI) will therefore play an important role in orchestration by self-learning from network parameters KPIs to proactively manage actual QoS in real time.
The current project is consequently about the design of artificial intelligence models and algorithms to address the required QoS for 5G networks.

Faculty Supervisor:

Brigitte Jaumard

Student:

Shivam Patel;Trong Tuan Tran

Partner:

Ciena Canada

Discipline:

Engineering - computer / electrical

Sector:

Information and cultural industries

University:

Concordia University