%% You should probably cite draft-ihsan-nmrg-rl-vne-ps-02 instead of this revision.
@techreport{ihsan-nmrg-rl-vne-ps-00,
    number =    {draft-ihsan-nmrg-rl-vne-ps-00},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-ihsan-nmrg-rl-vne-ps/00/},
    author =    {Ihsan Ullah and Youn-Hee Han and TaeYeon Kim},
    title =     {{Reinforcement Learning-Based Virtual Network Embedding: Problem Statement}},
    pagetotal = 17,
    year =      2021,
    month =     jun,
    day =       14,
    abstract =  {In Network virtualization (NV) technology, Virtual Network Embedding (VNE) is a problem to map a virtual network to the substrate network. It has a great impact on the performance of virtual network and resource utilization of the substrate network. An efficient embedding strategy 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, reinforcement learning (RL) can play a vital role to make the VNE problem 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 method, however, it is too difficult to apply RL techniques directly to VNE problems and need more research study. In this document, we are presenting a problem statement to motivate the research community to solve the VNE problem using reinforcement learning.},
}