Skip to main content

Reinforcement Learning-Based Virtual Network Embedding: Problem Statement

Document Type Expired Internet-Draft (individual)
Expired & archived
Authors Ihsan Ullah , Youn-Hee Han , TaeYeon Kim
Last updated 2022-10-23 (Latest revision 2022-04-21)
RFC stream (None)
Intended RFC status (None)
Stream Stream state (No stream defined)
Consensus boilerplate Unknown
RFC Editor Note (None)
IESG IESG state Expired
Telechat date (None)
Responsible AD (None)
Send notices to (None)

This Internet-Draft is no longer active. A copy of the expired Internet-Draft is available in these formats:


In Network virtualization (NV) technology, Virtual Network Embedding (VNE) is an algorithm used to map a virtual network to the substrate network. VNE is the core orientation of NV which has a great impact on the performance of virtual network and resource utilization of the substrate network. An efficient embedding algorithm can maximize the acceptance ratio of virtual networks to increase the revenue for Internet service provider. Several works have been appeared on the design of VNE solutions, however, it has becomes a challenging issues for researchers. To solved the VNE problem, we believe that reinforcement learning (RL) can play a vital role to make the VNE algorithm more intelligent and efficient. Moreover, RL has been merged with deep learning techniques to develop adaptive models with effective strategies for various complex problems. In RL, agents can learn desired behaviors (e.g, optimal VNE strategies), and after learning and completing training, it can embed the virtual network to the subtract network very quickly and efficiently. RL can reduce the complexity of the VNE algorithm, however, it is too difficult to apply RL techniques directly to VNE problems and need more research study. In this document, we presenting a problem statement to motivate the researchers toward the VNE problem using deep reinforcement learning.


Ihsan Ullah
Youn-Hee Han
TaeYeon Kim

(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)