Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning

Zechuan Guan; Fu Wang; Ze Dong; Zhipei Li; Huan Chang; Ran Gao

doi:10.1109/OECC56963.2023.10209850

Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning

Zechuan Guan, Fu Wang^*, Ze Dong, Zhipei Li, Huan Chang, Ran Gao

^*Corresponding author for this work

School of Information and Electronics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

We propose a spectrum adaptive awareness routing and spectrum allocation (SAA-RSA) scheme based on reinforcement learning in elastic optical networks. This scheme combines spectrum fragment awareness and reinforcement learning to realize adaptive spectrum allocation. Based on the proposed scheme, the action space of RL is optimized, thus improving the performance of network and reducing traffic blocking probability. The simulation results show that when the network load is 300 Erlang, compared with traditional KSP-FF method and reinforcement learning method without considering spectrum fragment, the scheme can reduce blocking probability by 27.56% and 12.15% respectively.

Original language	English
Title of host publication	2023 Opto-Electronics and Communications Conference, OECC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665462136
DOIs	https://doi.org/10.1109/OECC56963.2023.10209850
Publication status	Published - 2023
Event	2023 Opto-Electronics and Communications Conference, OECC 2023 - Shanghai, China Duration: 2 Jul 2023 → 6 Jul 2023

Publication series

Name	2023 Opto-Electronics and Communications Conference, OECC 2023

Conference

Conference	2023 Opto-Electronics and Communications Conference, OECC 2023
Country/Territory	China
City	Shanghai
Period	2/07/23 → 6/07/23

Keywords

Deep Q-network
Elastic optical networks
RSA
Reinforcement learning
Spectrum Slice Degree

Access to Document

10.1109/OECC56963.2023.10209850

Cite this

Guan, Z., Wang, F., Dong, Z., Li, Z., Chang, H., & Gao, R. (2023). Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning. In 2023 Opto-Electronics and Communications Conference, OECC 2023 (2023 Opto-Electronics and Communications Conference, OECC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/OECC56963.2023.10209850

@inproceedings{053ca783f4064ba69587781e09df25ce,

title = "Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning",

abstract = "We propose a spectrum adaptive awareness routing and spectrum allocation (SAA-RSA) scheme based on reinforcement learning in elastic optical networks. This scheme combines spectrum fragment awareness and reinforcement learning to realize adaptive spectrum allocation. Based on the proposed scheme, the action space of RL is optimized, thus improving the performance of network and reducing traffic blocking probability. The simulation results show that when the network load is 300 Erlang, compared with traditional KSP-FF method and reinforcement learning method without considering spectrum fragment, the scheme can reduce blocking probability by 27.56\% and 12.15\% respectively.",

keywords = "Deep Q-network, Elastic optical networks, RSA, Reinforcement learning, Spectrum Slice Degree",

author = "Zechuan Guan and Fu Wang and Ze Dong and Zhipei Li and Huan Chang and Ran Gao",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 Opto-Electronics and Communications Conference, OECC 2023 ; Conference date: 02-07-2023 Through 06-07-2023",

year = "2023",

doi = "10.1109/OECC56963.2023.10209850",

language = "English",

series = "2023 Opto-Electronics and Communications Conference, OECC 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 Opto-Electronics and Communications Conference, OECC 2023",

address = "United States",

}

Guan, Z, Wang, F, Dong, Z , Li, Z , Chang, H & Gao, R 2023, Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning. in 2023 Opto-Electronics and Communications Conference, OECC 2023. 2023 Opto-Electronics and Communications Conference, OECC 2023, Institute of Electrical and Electronics Engineers Inc., 2023 Opto-Electronics and Communications Conference, OECC 2023, Shanghai, China, 2/07/23. https://doi.org/10.1109/OECC56963.2023.10209850

Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning. / Guan, Zechuan; Wang, Fu; Dong, Ze et al.
2023 Opto-Electronics and Communications Conference, OECC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 Opto-Electronics and Communications Conference, OECC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning

AU - Guan, Zechuan

AU - Wang, Fu

AU - Dong, Ze

AU - Li, Zhipei

AU - Chang, Huan

AU - Gao, Ran

PY - 2023

Y1 - 2023

N2 - We propose a spectrum adaptive awareness routing and spectrum allocation (SAA-RSA) scheme based on reinforcement learning in elastic optical networks. This scheme combines spectrum fragment awareness and reinforcement learning to realize adaptive spectrum allocation. Based on the proposed scheme, the action space of RL is optimized, thus improving the performance of network and reducing traffic blocking probability. The simulation results show that when the network load is 300 Erlang, compared with traditional KSP-FF method and reinforcement learning method without considering spectrum fragment, the scheme can reduce blocking probability by 27.56% and 12.15% respectively.

AB - We propose a spectrum adaptive awareness routing and spectrum allocation (SAA-RSA) scheme based on reinforcement learning in elastic optical networks. This scheme combines spectrum fragment awareness and reinforcement learning to realize adaptive spectrum allocation. Based on the proposed scheme, the action space of RL is optimized, thus improving the performance of network and reducing traffic blocking probability. The simulation results show that when the network load is 300 Erlang, compared with traditional KSP-FF method and reinforcement learning method without considering spectrum fragment, the scheme can reduce blocking probability by 27.56% and 12.15% respectively.

KW - Deep Q-network

KW - Elastic optical networks

KW - RSA

KW - Reinforcement learning

KW - Spectrum Slice Degree

UR - https://www.scopus.com/pages/publications/85170206107

U2 - 10.1109/OECC56963.2023.10209850

DO - 10.1109/OECC56963.2023.10209850

M3 - Conference contribution

AN - SCOPUS:85170206107

T3 - 2023 Opto-Electronics and Communications Conference, OECC 2023

BT - 2023 Opto-Electronics and Communications Conference, OECC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 Opto-Electronics and Communications Conference, OECC 2023

Y2 - 2 July 2023 through 6 July 2023

ER -

Spectrum Adaptive Awareness Routing and Spectrum Allocation Based on Reinforcement Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this