DT-Assisted VNF Migration in SDN/NVF-Enabled IoT Networks via Multiagent Deep Reinforcement Learning
- 29 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (14) , 25294-25315
Abstract
Network Function Virtualization (NFV) and Software-Defined Networking (SDN) provide high-quality services to users of the Internet of Things (IoT). However, dynamic changes in network traffic and service function chain (SFC) resource requirements may result in virtual network function (VNF) migration issue and real-time triggering of VNF migration can cause service delay issues in SDN/NVF-enabled IoT networks. In this paper, we propose a DT-assisted VNF migration strategy to effectively address this issue. The digital twin of VNF (DT-VNF) is integrated with a multi-task digital twin migration model based on bidirectional-gated recurrent units (DTMBi-GRU) to achieve accurate resource demands prediction. Based on this, the VNF migration strategy is formulated in advance to avoid network performance degradation. We focus on the post-migration effects on services, networks, and DTs, so migration plans for DT-VNF and a re-association scheme are formulated to enable real-time monitoring of post-migration VNF by DT-VNF. Then, an optimization problem is formulated to minimize average network energy consumption, network resource differences, and SDN synchronization delay in order to obtain optimal strategies. In addition, considering the problem’s complexity, it is decoupled into the VNF migration problem and the DT association and migration problem. The collaborative solution involves employing the multi-agent proximal policy optimization (MAPPO) and asynchronous advantage actor-critic (A3C). Simulation results confirm the superiority of the proposed algorithms over baseline algorithms.Keywords
Funding Information
- National Natural Science Foundation of China (62071078)
- Sichuan Science and Technology Program (2021YFQ0053)
This publication has 42 references indexed in Scilit:
- SDN and NFV for QoE-driven multimedia services delivery: The road towards 6G and beyond networksComputer Networks, 2022
- Priority-awareness VNF migration method based on deep reinforcement learningComputer Networks, 2022
- Digital Twins From Smart Manufacturing to Smart Cities: A SurveyIEEE Access, 2021
- Design and Implementation of Network-Aware VNF Migration MechanismIEEE Access, 2020
- Make It Directly: Event Extraction Based on Tree-LSTM and Bi-GRUIEEE Access, 2020
- An Approach for Service Function Chain Reconfiguration in Network Function Virtualization ArchitecturesIEEE Access, 2019
- Virtual Network Function Migration Based on Dynamic Resource Requirements PredictionIEEE Access, 2019
- IoT survey: An SDN and fog computing perspectiveComputer Networks, 2018
- The industrial internet of things (IIoT): An analysis frameworkComputers in Industry, 2018
- Migration Energy Aware Reconfigurations of Virtual Network Function Instances in NFV ArchitecturesIEEE Access, 2017