DeepViNE: Virtual Network Embedding with Deep Reinforcement Learning

Dolati, Mahdi; Hassanpour, Seyedeh Bahereh; Ghaderi, Majid; Khonsari, Ahmad

doi:10.1109/infcomw.2019.8845171

Cited by 60 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Reinforcement Learning: Reinforcement learning typically finds use in problems associated with resource management [97], [98]. For example, the popular virtual network embedding problem wherein the network orchestrator performs optimal placement of virtual network functions onto the underlying physical substrate, is highly amenable to reinforcement learning [99]. Other applications include elastic scaling of network infrastructure [100], failure prevention, and configuration rollback [101].…”

Section: Ai In Network Management and Orchestrationmentioning

confidence: 99%

6G and Beyond: The Future of Wireless Communications Systems

2020

View full text Add to dashboard Cite

The next generation of wireless communication networks, or 6G, will fulfill the requirements of a fully connected world and provide ubiquitous wireless connectivity for all. Transformative solutions are expected to drive the surge for accommodating a rapidly growing number of intelligent devices and services. Major technological breakthroughs to achieve connectivity goals within 6G include: (i) a network operating at the THz band with much wider spectrum resources, (ii) intelligent communication environments that enable a wireless propagation environment with active signal transmission and reception, (iii) pervasive artificial intelligence, (iv) large-scale network automation, (v) an all-spectrum reconfigurable front-end for dynamic spectrum access, (vi) ambient backscatter communications for energy savings, (vii) the Internet of Space Things enabled by CubeSats and UAVs, and (viii) cell-free massive MIMO communication networks. In this roadmap paper, use cases for these enabling techniques as well as recent advancements on related topics are highlighted, and open problems with possible solutions are discussed, followed by a development timeline outlining the worldwide efforts in the realization of 6G. Going beyond 6G, promising early-stage technologies such as the Internet of NanoThings, the Internet of BioNanoThings, and quantum communications, which are expected to have a far-reaching impact on wireless communications, have also been discussed at length in this paper.

show abstract

Section: Ai In Network Management and Orchestrationmentioning

confidence: 99%

6G and Beyond: The Future of Wireless Communications Systems

2020

View full text Add to dashboard Cite

show abstract

“…In recent years, learning-based approaches have been well-received as a common enabling technology to handle various VNM problems. In DeepVine [11], online VNE decisions were formulated as reinforcement learning (RL) problems where an RL agent continuously determines the mapping for arriving virtual networks. DeepVine leverages the automatic feature extraction capability of convolutional neural networks by representing the resource properties of substrate and virtual networks in the form of images.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, several research works have introduced learning-based VNM solutions. In [11], DeepVine leveraged convolutional neural networks to extract important embedding features from virtual networks represented in images. In [12], VNM problems were formalized as an Markov decision process (MDP) where continual decisions about selecting target substrate nodes for given virtual nodes are made, and then those problems were addressed through reinforcement learning (RL) such as the Q-learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Gemma: Reinforcement Learning-Based Graph Embedding and Mapping for Virtual Network Applications

et al. 2021

View full text Add to dashboard Cite

Virtual network mapping (VNM) is a challenge in the field of network virtualization. As VNM variants have been formalized depending on substrate network structures, virtual network specifications, mapping optimization objectives, and other factors, a number of VNM heuristic methods have been introduced. On the other hand, reinforcement learning (RL) algorithms have been incorporated into deep learning frameworks and recognized as a promising solution for solving complex resource allocation problems. In this paper, we present an RL-based graph embedding and mapping framework, Gemma, for tackling various VNM problems in a unified end-to-end manner. In the framework, we employ an encoder-decoder deep learning architecture and propose several optimization schemes such as two-stage mapping and model-based selective embedding. Aiming to deal with large-scale VNM problems in both online and offline scheduling systems, the proposed schemes explore the trade-off between inference accuracy and mapping function runtimes, enhancing scalability and timeliness. Gemma shows robust performance under various problem conditions, outperforming other heuristic and learning-based methods.

show abstract

“…The Hopfield network is a form of recurrent neural network, which can extract whole valuable subgraphs and compute a probability for each node. The authors of [107] have developed a DRL-based VNE solution called DeepViNE. The key idea is to encode substrate and virtual networks as two-dimensional images.…”

Section: Machine Learning Based Vne Algorithmsmentioning

confidence: 99%

“…VNE has obtained more concerns due to its importance for 5G network slicing. Some existing works [106,107] have addressed the issues by considering ML technique to learn how to allocate resource and manage the service request itself automatically. However, more ML-based algorithms for VNE need to be proposed in the future to obtain better performance metrics (e.g., profit, latency, energy efficiency, and survivability) for network management dynamically [126].…”

Section: Machine Learning Based Management Algorithmmentioning

confidence: 99%

Virtual Network Embedding for Multi-Domain Heterogeneous Converged Optical Networks: Issues and Challenges

Zong

Feng

Guan

et al. 2020

Sensors

View full text Add to dashboard Cite

The emerging 5G applications and the connectivity of billions of devices have driven the investigation of multi-domain heterogeneous converged optical networks. To support emerging applications with their diverse quality of service requirements, network slicing has been proposed as a promising technology. Network virtualization is an enabler for network slicing, where the physical network can be partitioned into different configurable slices in the multi-domain heterogeneous converged optical networks. An efficient resource allocation mechanism for multiple virtual networks in network virtualization is one of the main challenges referred as virtual network embedding (VNE). This paper is a survey on the state-of-the-art works for the VNE problem towards multi-domain heterogeneous converged optical networks, providing the discussion on future research issues and challenges. In this paper, we describe VNE in multi-domain heterogeneous converged optical networks with enabling network orchestration technologies and analyze the literature about VNE algorithms with various network considerations for each network domain. The basic VNE problem with various motivations and performance metrics for general scenarios is discussed. A VNE algorithm taxonomy is presented and discussed by classifying the major VNE algorithms into three categories according to existing literature. We analyze and compare the attributes of algorithms such as node and link embedding methods, objectives, and network architecture, which can give a selection or baseline for future work of VNE. Finally, we explore some broader perspectives in future research issues and challenges on 5G scenario, field trail deployment, and machine learning-based algorithms.

show abstract

DeepViNE: Virtual Network Embedding with Deep Reinforcement Learning

Cited by 60 publications

References 18 publications

6G and Beyond: The Future of Wireless Communications Systems

6G and Beyond: The Future of Wireless Communications Systems

Gemma: Reinforcement Learning-Based Graph Embedding and Mapping for Virtual Network Applications

Virtual Network Embedding for Multi-Domain Heterogeneous Converged Optical Networks: Issues and Challenges

Contact Info

Product

Resources

About