Leveraging Deep Reinforcement Learning With Attention Mechanism for Virtual Network Function Placement and Routing
Top Cited Papers
- 30 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 34 (4) , 1186-1201
Abstract
The efficacy of Network Function Virtualization (NFV) depends critically on (1) where the virtual network functions (VNFs) are placed and (2) how the traffic is routed. Unfortunately, these aspects are not easily optimized, especially under time-varying network states with different QoS requirements. Given the importance of NFV, many approaches have been proposed to solve the VNF placement and Service Function Chaining (SFC) routing problem. However, those prior approaches mainly assume that the network state is static and known, disregarding dynamic network variations. To bridge that gap, we leverage Markov Decision Process (MDP) to model the dynamic network state transitions. To jointly minimize the delay and cost of NFV providers and maximize the revenue, we first devise a customized Deep Reinforcement Learning (DRL) algorithm for the VNF placement problem. The algorithm uses the attention mechanism to ascertain smooth network behavior within the general framework of network utility maximization (NUM). We then propose attention mechanism-based DRL algorithm for the SFC routing problem, which is to find the path to deliver traffic for the VNFs placed on different nodes. The simulation results show that our proposed algorithms outperform the state-of-the-art algorithms in terms of network utility, delay, cost, and acceptance ratio.Keywords
Funding Information
- National Natural Science Foundation of China (62172038)
- National Natural Science Foundation of China (62072040)
- National Natural Science Foundation of China (62232002)
- EU H2020 COSAFE project (824019)
- EU Horizon CODECO project (101092696)
This publication has 39 references indexed in Scilit:
- Joint Optimization of Chain Placement and Request Scheduling for Network Function Virtualization2017
- On Efficient Offloading Control in Cloud Radio Access Network with Mobile Edge Computing2017
- Traffic aware placement of interdependent NFV middleboxes2017
- Impact of processing costs on service chain placement in network functions virtualization2015
- Optimal scheduling for jobs with progressive deadlines2015
- Multi-cloud Distribution of Virtual Functions and Dynamic Service Deployment: Open ADN Perspective2015
- Providing public intradomain traffic matrices to the research communityACM SIGCOMM Computer Communication Review, 2006
- Methodology and input availability parameters for calculating OpEx and CapEx costs for realistic network scenariosJournal of Optical Networking, 2006
- A mathematical theory of communicationACM SIGMOBILE Mobile Computing and Communications Review, 2001
- Algorithms for the Weight Constrained Shortest Path ProblemInternational Transactions in Operational Research, 2001