IEICE TRANSACTIONS on Communications
iMon: Network Function Virtualisation Monitoring Based on a Unique Agent
Summary :
As a key technology of 5G, NFV has attracted much attention. In addition, monitoring plays an important role, and can be widely used for virtual network function placement and resource optimisation. The existing monitoring methods focus on the monitoring load without considering they own resources needed. This raises a unique challenge: jointly optimising the NFV monitoring systems and minimising their monitoring load at runtime. The objective is to enhance the gain in real-time monitoring metrics at minimum monitoring costs. In this context, we propose a novel NFV monitoring solution, namely, iMon (Monitoring by inferring), that jointly optimises the monitoring process and reduces resource consumption. We formalise the monitoring process into a multitarget regression problem and propose three regression models. These models are implemented by a deep neural network, and an experimental platform is built to prove their availability and effectiveness. Finally, experiments also show that monitoring resource requirements are reduced, and the monitoring load is just 0.6% of that of the monitoring tool cAdvisor on our dataset.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E106-B No.3 pp.230-240
- Publication Date
- 2023/03/01
- Publicized
- 2022/09/21
- Online ISSN
- 1745-1345
- DOI
- 10.1587/transcom.2022EBP3103
- Type of Manuscript
- PAPER
- Category
- Network
Authors
Cong ZHOU
National University of Defense Technology
Jing TAO
National University of Defense Technology
Baosheng WANG
National University of Defense Technology
Na ZHAO
National University of Defense Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Cong ZHOU, Jing TAO, Baosheng WANG, Na ZHAO, "iMon: Network Function Virtualisation Monitoring Based on a Unique Agent" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 3, pp. 230-240, March 2023, doi: 10.1587/transcom.2022EBP3103.
Abstract: As a key technology of 5G, NFV has attracted much attention. In addition, monitoring plays an important role, and can be widely used for virtual network function placement and resource optimisation. The existing monitoring methods focus on the monitoring load without considering they own resources needed. This raises a unique challenge: jointly optimising the NFV monitoring systems and minimising their monitoring load at runtime. The objective is to enhance the gain in real-time monitoring metrics at minimum monitoring costs. In this context, we propose a novel NFV monitoring solution, namely, iMon (Monitoring by inferring), that jointly optimises the monitoring process and reduces resource consumption. We formalise the monitoring process into a multitarget regression problem and propose three regression models. These models are implemented by a deep neural network, and an experimental platform is built to prove their availability and effectiveness. Finally, experiments also show that monitoring resource requirements are reduced, and the monitoring load is just 0.6% of that of the monitoring tool cAdvisor on our dataset.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3103/_p
Copy
@ARTICLE{e106-b_3_230,
author={Cong ZHOU, Jing TAO, Baosheng WANG, Na ZHAO, },
journal={IEICE TRANSACTIONS on Communications},
title={iMon: Network Function Virtualisation Monitoring Based on a Unique Agent},
year={2023},
volume={E106-B},
number={3},
pages={230-240},
abstract={As a key technology of 5G, NFV has attracted much attention. In addition, monitoring plays an important role, and can be widely used for virtual network function placement and resource optimisation. The existing monitoring methods focus on the monitoring load without considering they own resources needed. This raises a unique challenge: jointly optimising the NFV monitoring systems and minimising their monitoring load at runtime. The objective is to enhance the gain in real-time monitoring metrics at minimum monitoring costs. In this context, we propose a novel NFV monitoring solution, namely, iMon (Monitoring by inferring), that jointly optimises the monitoring process and reduces resource consumption. We formalise the monitoring process into a multitarget regression problem and propose three regression models. These models are implemented by a deep neural network, and an experimental platform is built to prove their availability and effectiveness. Finally, experiments also show that monitoring resource requirements are reduced, and the monitoring load is just 0.6% of that of the monitoring tool cAdvisor on our dataset.},
keywords={},
doi={10.1587/transcom.2022EBP3103},
ISSN={1745-1345},
month={March},}
Copy
TY - JOUR
TI - iMon: Network Function Virtualisation Monitoring Based on a Unique Agent
T2 - IEICE TRANSACTIONS on Communications
SP - 230
EP - 240
AU - Cong ZHOU
AU - Jing TAO
AU - Baosheng WANG
AU - Na ZHAO
PY - 2023
DO - 10.1587/transcom.2022EBP3103
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 3
JA - IEICE TRANSACTIONS on Communications
Y1 - March 2023
AB - As a key technology of 5G, NFV has attracted much attention. In addition, monitoring plays an important role, and can be widely used for virtual network function placement and resource optimisation. The existing monitoring methods focus on the monitoring load without considering they own resources needed. This raises a unique challenge: jointly optimising the NFV monitoring systems and minimising their monitoring load at runtime. The objective is to enhance the gain in real-time monitoring metrics at minimum monitoring costs. In this context, we propose a novel NFV monitoring solution, namely, iMon (Monitoring by inferring), that jointly optimises the monitoring process and reduces resource consumption. We formalise the monitoring process into a multitarget regression problem and propose three regression models. These models are implemented by a deep neural network, and an experimental platform is built to prove their availability and effectiveness. Finally, experiments also show that monitoring resource requirements are reduced, and the monitoring load is just 0.6% of that of the monitoring tool cAdvisor on our dataset.
ER -
English
