Abstract
The autonomous placement of Virtual Network Functions (VNFs) is a key aspect of Zero-touch network and Service Management (ZSM) in Fifth Generation (5G) networking. Therefore, current orchestration frameworks need to be enhanced, accordingly. To address this need, this work presents an Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement, namely AREL3P. Our solution design bears a dual novelty. First, it leverages end-to-end service-level performance predictions for placing VNFs. Second, whereas the majority of other Machine Learning efforts in the literature use Supervised Learning (SL) techniques, AREL3P is based on a particular form of Reinforcement Learning adapted to predictions. This makes placement decisions more resilient to dynamic conditions, as well as portable to other network nodes, and able to generalize in heterogeneous network environments. Backed by a meticulous performance evaluation over a real 5G end-to-end testbed, we verify the above properties after integrating AREL3P to Open Source Management and Orchestration (OSM MANO) decisions. Among other highlights, we show increased VNF performance predictions accuracy by 40-45%, and an overall improved VNF placement efficiency against other SL benchmarks reflected by near-optimal decision scores in 23 out of a total of 27 investigated scenarios.
Highlights
C ONTEMPORARY networks are becoming increasingly programmable based on two key concepts: (i) SoftwareDefined Networking (SDN) and (ii) Network Function Virtualization (NFV)
2) Scenario 2 (VNF Placement Efficiency): The results presented below denote that AREL3P leads to good placement decisions, nearly as good as the ones made by the best benchmark predictions out of all Supervised Learning (SL) model options
Taking a different approach from other solutions in the literature based on Supervised Learning (SL), AREL3P adapts a particular type of RL, namely Q-learning
Summary
C ONTEMPORARY networks are becoming increasingly programmable based on two key concepts: (i) SoftwareDefined Networking (SDN) and (ii) Network Function Virtualization (NFV). BUNYAKITANON et al.: END-TO-END PERFORMANCE-BASED AUTONOMOUS VNF PLACEMENT WITH ADOPTED REINFORCEMENT LEARNING maintaining the models), and (iii) sufficiently accurate for the purposes of ZSM in 5G?” Motivated by this question, the current work proposes an Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement (AREL3P). The purpose of this module is to enhance network orchestrator systems based on online learning. AREL3P covers this gap by serving as an extension module to orchestrators, being embedded with its own e2e service-level monitoring and corresponding intelligent VNF performance prediction mechanism at candidate VNF hosting nodes
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Transactions on Cognitive Communications and Networking
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.