Dynamic Service Function Chain Orchestration for NFV/MEC-Enabled IoT Networks: A Deep Reinforcement Learning Approach

Network function virtualization (NFV) and mobile-edge computing (MEC) have been introduced by Internet service providers (ISPs) to deal with various challenges, which hinder them from satisfying ambitious quality of experience demands of the Internet-of-Things (IoT) applications. In NFV/MEC-enabled...

Full description

Saved in:
Bibliographic Details
Published in:IEEE internet of things journal 2021-05, Vol.8 (9), p.7450-7465
Main Authors: Liu, Yicen, Lu, Hao, Li, Xi, Zhang, Yang, Xi, Leiping, Zhao, Donghao
Format: Article
Language:English
Subjects:
Algorithms
Chains
Cloud computing
Deep learning
Deep reinforcement learning (DRL)
dynamic orchestration
Edge computing
Heuristic algorithms
Internet of Things
Internet of Things (IoT)
Internet service providers
Machine learning
Mobile computing
mobile-edge computing (MEC)
network function virtualization (NFV)
Resource management
Routing
service function chain (SFC)
Terminals
Virtual networks
Virtualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Network function virtualization (NFV) and mobile-edge computing (MEC) have been introduced by Internet service providers (ISPs) to deal with various challenges, which hinder them from satisfying ambitious quality of experience demands of the Internet-of-Things (IoT) applications. In NFV/MEC-enabled IoT networks, any IoT service can be expressed as a service function chain (SFC) consisting of several strictly ordered virtual network functions (VNFs), which can be geographically placed onto edge clouds close to IoT terminals. However, regarding the large number of IoT terminals and constant dynamics of IoT networks, determining the placement of VNFs and routing service paths that optimize the end-to-end delays in the hybrid edge clouds is a challenging problem. This problem is also called SFC dynamic orchestration problem (SFC-DOP). To address the SFC-DOP, we are motivated to creatively present an SFC dynamic orchestration framework for IoT deep reinforcement learning (DRL). Also, a DRL-based algorithm for SFC-DOP with the actor-critic and the deterministic policy gradient scheme is provided, which can efficiently deal with the SFC-DOP in IoT networks. The obtained experimental results show the outstanding performance of our proposal compared with the current benchmarks.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2020.3038793