Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Review and Analysis of Recent Advances in Intelligent Network Softwarization for the Internet of Things

Mohamed Ali Zormati, Hicham Lakhlef, Sofiane Ouni

TL;DR

The paper tackles the challenge of building scalable, heterogeneous IoT networks by surveying the convergence of ML with network softwarization (SDN and NFV). It offers a taxonomy of ML approaches (SL, UL, RL, FL) and maps them to IoT contexts such as routing, VNF placement, and security, highlighting the state-of-the-art and practical gaps. Key findings include notable potential for QoS, energy efficiency, and security enhancements, but pervasive issues with reproducibility, IoT-specific benchmarks, and limited adoption of Federated Learning. The authors outline future directions that combine edge/fog computing, network slicing, distributed intelligence, and blockchain-based security, emphasizing standardization to enable real-world deployments. Overall, intelligent network softwarization stands as a promising pathway to realize self-configured, self-managed IoT ecosystems at scale.

Abstract

The Internet of Things (IoT) is an emerging technology that aims to connect heterogeneous and constrained objects to each other and to the Internet. It has grown significantly in a wide variety of applications such as smart homes, smart cities, smart vehicles, etc. The huge number of connected devices increases the challenges, as IoT provides diverse and complex network services with different requirements on a common infrastructure. Network Softwarization is the latest network paradigm that transforms traditional network processes to the separation of hardware and software by using some enabling network technologies such as Software Defined Networking (SDN) and Network Function Virtualization (NFV). Machine Learning (ML) plays an essential role in creating smarter IoT networks, as it has shown remarkable results in various domains. Given that the network softwarization allows it to be easily integrated, ML can play a crucial role in efficient and self-adaptive IoT networks. In this paper, we provide a detailed overview of the concepts of IoT, network softwarization, and ML, and we study and discuss the state of the art of intelligent ML-enabled network softwarization for IoT. We also identify the most prominent future research directions to be considered.

Review and Analysis of Recent Advances in Intelligent Network Softwarization for the Internet of Things

TL;DR

The paper tackles the challenge of building scalable, heterogeneous IoT networks by surveying the convergence of ML with network softwarization (SDN and NFV). It offers a taxonomy of ML approaches (SL, UL, RL, FL) and maps them to IoT contexts such as routing, VNF placement, and security, highlighting the state-of-the-art and practical gaps. Key findings include notable potential for QoS, energy efficiency, and security enhancements, but pervasive issues with reproducibility, IoT-specific benchmarks, and limited adoption of Federated Learning. The authors outline future directions that combine edge/fog computing, network slicing, distributed intelligence, and blockchain-based security, emphasizing standardization to enable real-world deployments. Overall, intelligent network softwarization stands as a promising pathway to realize self-configured, self-managed IoT ecosystems at scale.

Abstract

The Internet of Things (IoT) is an emerging technology that aims to connect heterogeneous and constrained objects to each other and to the Internet. It has grown significantly in a wide variety of applications such as smart homes, smart cities, smart vehicles, etc. The huge number of connected devices increases the challenges, as IoT provides diverse and complex network services with different requirements on a common infrastructure. Network Softwarization is the latest network paradigm that transforms traditional network processes to the separation of hardware and software by using some enabling network technologies such as Software Defined Networking (SDN) and Network Function Virtualization (NFV). Machine Learning (ML) plays an essential role in creating smarter IoT networks, as it has shown remarkable results in various domains. Given that the network softwarization allows it to be easily integrated, ML can play a crucial role in efficient and self-adaptive IoT networks. In this paper, we provide a detailed overview of the concepts of IoT, network softwarization, and ML, and we study and discuss the state of the art of intelligent ML-enabled network softwarization for IoT. We also identify the most prominent future research directions to be considered.
Paper Structure (25 sections, 7 figures)

This paper contains 25 sections, 7 figures.

Table of Contents

  1. Introduction
  2. Contributions
  3. Survey organization
  4. Related Surveys
  5. Background
  6. Internet of Things (IoT)
  7. Network softwarization
  8. Software Defined Networking (SDN)
  9. Network Function Virtualization (NFV)
  10. Machine Learning (ML)
  11. Supervised Learning (SL)
  12. Unsupervised Learning (UL)
  13. Reinforcement Learning (RL)
  14. Federated Learning (FL)
  15. Intelligent Network Softwarization for IoT
  16. ...and 10 more sections

Figures (7)

  • Figure 1: IoT Architecture
  • Figure 2: SDN Controller Design
  • Figure 3: SDN Architecture
  • Figure 4: NFV Architecture
  • Figure 5: Main Phases of an ML Approach
  • ...and 2 more figures