Traffic Engineering Based on Reinforcement Learning for Service Function Chaining With Delay Guarantee

Abstract

Network Function Virtualization (NFV) is an approach that provides a network service provider with agility and cost-efficiency in managing 6G network services. Standard traffic engineering rules are known limited in assuring a very stringent delay requirement in NFV when a traffic flow is required to follow a sequence of network functions scattered in data center networks. This paper proposes an innovative model and algorithm of traffic engineering for service function chaining (SFC) to maximize cost-efficiency under a delay-guarantee constraint. We first formulate the problem as a mixed-integer linear programming model for obtaining the optimal solution. We then propose an algorithm based on the reinforcement learning principles for finding an approximation solution in a large-scale problem with the dynamics of service demands. Numerical results under both real-world datasets and synthetic network topologies demonstrate that our proposed model and algorithm allow an NFV service provider (NSP) to place a virtual network function and steer a traffic flow efficiently in terms of energy cost for a delay-guarantee SFC. Importantly, the results provide an insight into the optimal and approximation solutions for an NSP to select a suitable traffic engineering approach with regard to network dynamics.

Fast Resource Allocation for Resilient Service Coordination in an NFV-Enabled Internet-of-Things System

“…Our future work will address the dynamics of service demand parameters and various performance metrics as in [6,23]. We also can consider a more general coordination model or the federation of IoT providers for enhancing service quality.…”

“…After RSS obtains a new feasible solution, RSS replaces the current solution with the neighborhood solution if the neighborhood solution is better than the current solution (i.e., lines [19][20][21][22][23][24]. Otherwise, to overcome local optimization, RSS probabilistically switches the current solution to the neighborhood solution (i.e., lines 25-30).…”

Intelligent Traffic Engineering for 6G Heterogeneous Transport Networks

“…In the traffic engineering framework, the study of [27] demonstrated the capability to locate the optimal placement of VNF to determine highly efficient service function chaining (SFC) in a network function virtualization (NFV) environment using MILP and approximation solution. The findings from [27] indicate the optimum method to address strict SFC routing policy, the efficient management of VNF usability, and the identification of an algorithm that works efficiently in specific scenarios. The study in [28] demonstrated deep reinforcement learning (DRL), a subsection in machine learning frameworks.…”

In the Direction of Service Guarantees for Virtualized Network Functions

“…Gatekeeper [30] is an example of a rate-limit approach, where Linux hierarchical token buckets are used to enforce rate limits. SENIC [31] uses hardware-assisted rate limits at traffic sources to improve performance of latency-sensitive applications. Along the same lines, Silo [32] dynamically enforces rate limits on virtual machines in order to achieve performance guarantees.…”