Meta-Learning for Realizing Self-x Management of Future Networks

Manzoor Ahmed Khan, Tembine Hamidou

Research output: Contribution to journalArticle

Abstract

In this paper, we propose an autonomic network management and policy execution framework. The proposed framework refactors the network functionalities by decomposing the network architecture into hierarchical layered architecture. This paper aims at enabling the transition from a rule-based control structure to a more distributed and autonomic network control by implementing the self-x or self-∗ learning vision on each layer. The problem is modeled using multi-layer dynamic games. At each layer, a self-∗ learning procedure is proposed to learn and adapt the reverse Stackelberg policies. To validate the proposed framework, we develop a full scale demonstrator comprising of flat IP core and heterogeneous wireless access networks. We have also developed various tools and software agents to implement the self-x management vision. The proposed self-x learning is implemented via mobile intelligent agents in a distributed fashion. Our experimental results show quick re-stabilization of the self-∗ learning in mobile intelligent agents and the observed performance remain well above the satisfactory values for different key performance indicator with the proposed meta-learning approach.

Original languageEnglish (US)
Article number8017381
Pages (from-to)19072-19083
Number of pages12
JournalIEEE Access
Volume5
DOIs
StatePublished - Aug 26 2017

Fingerprint

Intelligent agents
Software agents
Network management
Network architecture
Stabilization
Intellectual property core

Keywords

  • Autonomous network management
  • game theory
  • heterogeneous wireless networks
  • self-organizing networks
  • software agents

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Meta-Learning for Realizing Self-x Management of Future Networks. / Khan, Manzoor Ahmed; Hamidou, Tembine.

In: IEEE Access, Vol. 5, 8017381, 26.08.2017, p. 19072-19083.

Research output: Contribution to journalArticle

@article{853fdedb57c443e982cd1ee0471ce5ef,
title = "Meta-Learning for Realizing Self-x Management of Future Networks",
abstract = "In this paper, we propose an autonomic network management and policy execution framework. The proposed framework refactors the network functionalities by decomposing the network architecture into hierarchical layered architecture. This paper aims at enabling the transition from a rule-based control structure to a more distributed and autonomic network control by implementing the self-x or self-∗ learning vision on each layer. The problem is modeled using multi-layer dynamic games. At each layer, a self-∗ learning procedure is proposed to learn and adapt the reverse Stackelberg policies. To validate the proposed framework, we develop a full scale demonstrator comprising of flat IP core and heterogeneous wireless access networks. We have also developed various tools and software agents to implement the self-x management vision. The proposed self-x learning is implemented via mobile intelligent agents in a distributed fashion. Our experimental results show quick re-stabilization of the self-∗ learning in mobile intelligent agents and the observed performance remain well above the satisfactory values for different key performance indicator with the proposed meta-learning approach.",
keywords = "Autonomous network management, game theory, heterogeneous wireless networks, self-organizing networks, software agents",
author = "Khan, {Manzoor Ahmed} and Tembine Hamidou",
year = "2017",
month = "8",
day = "26",
doi = "10.1109/ACCESS.2017.2745999",
language = "English (US)",
volume = "5",
pages = "19072--19083",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Meta-Learning for Realizing Self-x Management of Future Networks

AU - Khan, Manzoor Ahmed

AU - Hamidou, Tembine

PY - 2017/8/26

Y1 - 2017/8/26

N2 - In this paper, we propose an autonomic network management and policy execution framework. The proposed framework refactors the network functionalities by decomposing the network architecture into hierarchical layered architecture. This paper aims at enabling the transition from a rule-based control structure to a more distributed and autonomic network control by implementing the self-x or self-∗ learning vision on each layer. The problem is modeled using multi-layer dynamic games. At each layer, a self-∗ learning procedure is proposed to learn and adapt the reverse Stackelberg policies. To validate the proposed framework, we develop a full scale demonstrator comprising of flat IP core and heterogeneous wireless access networks. We have also developed various tools and software agents to implement the self-x management vision. The proposed self-x learning is implemented via mobile intelligent agents in a distributed fashion. Our experimental results show quick re-stabilization of the self-∗ learning in mobile intelligent agents and the observed performance remain well above the satisfactory values for different key performance indicator with the proposed meta-learning approach.

AB - In this paper, we propose an autonomic network management and policy execution framework. The proposed framework refactors the network functionalities by decomposing the network architecture into hierarchical layered architecture. This paper aims at enabling the transition from a rule-based control structure to a more distributed and autonomic network control by implementing the self-x or self-∗ learning vision on each layer. The problem is modeled using multi-layer dynamic games. At each layer, a self-∗ learning procedure is proposed to learn and adapt the reverse Stackelberg policies. To validate the proposed framework, we develop a full scale demonstrator comprising of flat IP core and heterogeneous wireless access networks. We have also developed various tools and software agents to implement the self-x management vision. The proposed self-x learning is implemented via mobile intelligent agents in a distributed fashion. Our experimental results show quick re-stabilization of the self-∗ learning in mobile intelligent agents and the observed performance remain well above the satisfactory values for different key performance indicator with the proposed meta-learning approach.

KW - Autonomous network management

KW - game theory

KW - heterogeneous wireless networks

KW - self-organizing networks

KW - software agents

UR - http://www.scopus.com/inward/record.url?scp=85028733240&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028733240&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2017.2745999

DO - 10.1109/ACCESS.2017.2745999

M3 - Article

VL - 5

SP - 19072

EP - 19083

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8017381

ER -