IEICE TRANSACTIONS on Communications
Open Access
Extendable NFV-Integrated Control Method Using Reinforcement Learning
-
Full Text Views
48
- Cite this
- Free PDF (3.3MB)
Summary :
Network functions virtualization (NFV) enables telecommunications service providers to realize various network services by flexibly combining multiple virtual network functions (VNFs). To provide such services, an NFV control method should optimally allocate such VNFs into physical networks and servers by taking account of the combination(s) of objective functions and constraints for each metric defined for each VNF type, e.g., VNF placements and routes between the VNFs. The NFV control method should also be extendable for adding new metrics or changing the combination of metrics. One approach for NFV control to optimize allocations is to construct an algorithm that simultaneously solves the combined optimization problem. However, this approach is not extendable because the problem needs to be reformulated every time a new metric is added or a combination of metrics is changed. Another approach involves using an extendable network-control architecture that coordinates multiple control algorithms specified for individual metrics. However, to the best of our knowledge, no method has been developed that can optimize allocations through this kind of coordination. In this paper, we propose an extendable NFV-integrated control method by coordinating multiple control algorithms. We also propose an efficient coordination algorithm based on reinforcement learning. Finally, we evaluate the effectiveness of the proposed method through simulations.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E103-B No.8 pp.826-841
- Publication Date
- 2020/08/01
- Publicized
- 2020/01/24
- Online ISSN
- 1745-1345
- DOI
- 10.1587/transcom.2019EBP3114
- Type of Manuscript
- PAPER
- Category
- Network
Authors
Akito SUZUKI
NTT Corporation
Ryoichi KAWAHARA
Toyo University
Masahiro KOBAYASHI
NTT Corporation
Shigeaki HARADA
NTT Corporation
Yousuke TAKAHASHI
NTT Corporation
Keisuke ISHIBASHI
International Christian University
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
Akito SUZUKI, Ryoichi KAWAHARA, Masahiro KOBAYASHI, Shigeaki HARADA, Yousuke TAKAHASHI, Keisuke ISHIBASHI, "Extendable NFV-Integrated Control Method Using Reinforcement Learning" in IEICE TRANSACTIONS on Communications,
vol. E103-B, no. 8, pp. 826-841, August 2020, doi: 10.1587/transcom.2019EBP3114.
Abstract: Network functions virtualization (NFV) enables telecommunications service providers to realize various network services by flexibly combining multiple virtual network functions (VNFs). To provide such services, an NFV control method should optimally allocate such VNFs into physical networks and servers by taking account of the combination(s) of objective functions and constraints for each metric defined for each VNF type, e.g., VNF placements and routes between the VNFs. The NFV control method should also be extendable for adding new metrics or changing the combination of metrics. One approach for NFV control to optimize allocations is to construct an algorithm that simultaneously solves the combined optimization problem. However, this approach is not extendable because the problem needs to be reformulated every time a new metric is added or a combination of metrics is changed. Another approach involves using an extendable network-control architecture that coordinates multiple control algorithms specified for individual metrics. However, to the best of our knowledge, no method has been developed that can optimize allocations through this kind of coordination. In this paper, we propose an extendable NFV-integrated control method by coordinating multiple control algorithms. We also propose an efficient coordination algorithm based on reinforcement learning. Finally, we evaluate the effectiveness of the proposed method through simulations.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2019EBP3114/_p
Copy
@ARTICLE{e103-b_8_826,
author={Akito SUZUKI, Ryoichi KAWAHARA, Masahiro KOBAYASHI, Shigeaki HARADA, Yousuke TAKAHASHI, Keisuke ISHIBASHI, },
journal={IEICE TRANSACTIONS on Communications},
title={Extendable NFV-Integrated Control Method Using Reinforcement Learning},
year={2020},
volume={E103-B},
number={8},
pages={826-841},
abstract={Network functions virtualization (NFV) enables telecommunications service providers to realize various network services by flexibly combining multiple virtual network functions (VNFs). To provide such services, an NFV control method should optimally allocate such VNFs into physical networks and servers by taking account of the combination(s) of objective functions and constraints for each metric defined for each VNF type, e.g., VNF placements and routes between the VNFs. The NFV control method should also be extendable for adding new metrics or changing the combination of metrics. One approach for NFV control to optimize allocations is to construct an algorithm that simultaneously solves the combined optimization problem. However, this approach is not extendable because the problem needs to be reformulated every time a new metric is added or a combination of metrics is changed. Another approach involves using an extendable network-control architecture that coordinates multiple control algorithms specified for individual metrics. However, to the best of our knowledge, no method has been developed that can optimize allocations through this kind of coordination. In this paper, we propose an extendable NFV-integrated control method by coordinating multiple control algorithms. We also propose an efficient coordination algorithm based on reinforcement learning. Finally, we evaluate the effectiveness of the proposed method through simulations.},
keywords={},
doi={10.1587/transcom.2019EBP3114},
ISSN={1745-1345},
month={August},}
Copy
TY - JOUR
TI - Extendable NFV-Integrated Control Method Using Reinforcement Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 826
EP - 841
AU - Akito SUZUKI
AU - Ryoichi KAWAHARA
AU - Masahiro KOBAYASHI
AU - Shigeaki HARADA
AU - Yousuke TAKAHASHI
AU - Keisuke ISHIBASHI
PY - 2020
DO - 10.1587/transcom.2019EBP3114
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E103-B
IS - 8
JA - IEICE TRANSACTIONS on Communications
Y1 - August 2020
AB - Network functions virtualization (NFV) enables telecommunications service providers to realize various network services by flexibly combining multiple virtual network functions (VNFs). To provide such services, an NFV control method should optimally allocate such VNFs into physical networks and servers by taking account of the combination(s) of objective functions and constraints for each metric defined for each VNF type, e.g., VNF placements and routes between the VNFs. The NFV control method should also be extendable for adding new metrics or changing the combination of metrics. One approach for NFV control to optimize allocations is to construct an algorithm that simultaneously solves the combined optimization problem. However, this approach is not extendable because the problem needs to be reformulated every time a new metric is added or a combination of metrics is changed. Another approach involves using an extendable network-control architecture that coordinates multiple control algorithms specified for individual metrics. However, to the best of our knowledge, no method has been developed that can optimize allocations through this kind of coordination. In this paper, we propose an extendable NFV-integrated control method by coordinating multiple control algorithms. We also propose an efficient coordination algorithm based on reinforcement learning. Finally, we evaluate the effectiveness of the proposed method through simulations.
ER -
English
