Network Slicing Resource Allocation ML-Enhanced (NSRALLOC-ML)Â
research PROJECT
January 2022 - July 2023
Embedded Files
The NSRAlloc-ML project proposes the modeling and deployment of network slicing strategies to allocate communication resources capable of supporting the dynamism and elasticity of end-to-end communication users.
NSRAlloc-ML uses new resource allocation models with bandwidth allocation models (BAM) aided by Q-Learning, SARSA, Deep Learning and CBR algorithms for resource slicing and bandwidth allocation in networks.
A dynamic, intelligent, and self-regulating network slicing resource allocation for 5G, telecommunication networks, and Edge/Fog/Cloud computing in various application scenarios is the target of the NSRAlloc-ML.
Objectives:
Objectives:
Network Slicing (Slice-as-a-Service)
Intelligent Slicing Resource Allocation
Self-driving Resource Allocation across Slices
NSRAlloc-ML Research Topics:
NSRAlloc-ML Research Topics:
Network Slicing
Resource Orchestration and Allocation
Machine Learning (ML)
ML-based Resource Allocation
Multi-Domain Network Slicing
Slice-as-a-Service (SLaaS)
Self-driven Networks
Research Activities:
Research Activities:
ATV1 - Network Slicing Strategies, Requirements, and Functional Architecture
ATV2 - Machine Learning for Intelligent Allocation of Communication Resources in Slicing
ATV3 - Dyra Framework Cognitive Module Embedding
ATV4 - Use Cases
ATV5 - Dissemination and Data Management
FUNDING and SUPPORT :
FUNDING and SUPPORT :
Instituto ANIMA supports NSRAlloc-ML project
UNIFACS supports NSRAlloc-ML project
FIBRE Testbed Project supports NSRAlloc-ML project
Page updated
Google Sites
Report abuse