On Modeling Network Slicing Communication Resources with SARSA Optimization

EasyChair Preprint 14194

Abstract

Network slicing is a crucial enabler to support the composition and deployment of virtual network infrastructures required by the dynamic behavior of networks like 5G/6G mobile networks, IoT-aware networks, e-health systems, and industry verticals like the internet of vehicles (IoV) and industry 4.0. The communication slices and their allocated communication resources are essential in slicing architectures for resource orchestration and allocation, virtual network function (VNF) deployment, and slice operation functionalities. The communication slices provide the communications capabilities required to support slice operation, SLA guarantees, and QoS/ QoE application requirements. Therefore, this contribution proposes a networking slicing conceptual model to formulate the optimization problem related to the sharing of communication resources among communication slices. First, we present a conceptual model of network slicing, we then formulate analytically some aspects of the model and the optimization problem to address. Next, we propose to use a SARSA agent to solve the optimization problem and implement a proof of concept prototype highlighting its results.

Keyphrases: Communication Slice, Conceptual and Analytical Model, Network Slicing, Network and Service Management, Proof of Concept, SARSA, allocation of communication resources, analytical model, communication resources, composition and deployment of virtual network, conceptual and analytical modeling, conceptual model of network slicing, deployment and slice operation, deployment of virtual network infrastructures, dynamic behavior of networks, infrastructure and service resources, machine learning, multi domain sliced virtual, network slicing process, network slicing reference architecture, optimization problem, resource allocation, sarsa agent, slice communication model, slice operation, view of communication resources

@booklet{EasyChair:14194,
  author    = {Eduardo S. Xavier and Nazim Agoulmine and Joberto S. B. Martins},
  title     = {On Modeling Network Slicing Communication Resources with SARSA Optimization},
  howpublished = {EasyChair Preprint 14194},
  year      = {EasyChair, 2024}}