A reinforcement learning approach for widest path routing in software-defined networks
In this paper, a routing method based on reinforcement learning (RL) under software-defined networks (SDN), namely the Q-learning widest-path routing algorithm (Q-WPRA), is proposed. This algorithm processes the reward function according to the link bandwidth in the execution environment to find the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | ICT Express |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405959522001503 |
| _version_ | 1797653981109944320 |
|---|---|
| author | Chih-Heng Ke Yi-Hao Tu Yi-Wei Ma |
| author_facet | Chih-Heng Ke Yi-Hao Tu Yi-Wei Ma |
| author_sort | Chih-Heng Ke |
| collection | DOAJ |
| description | In this paper, a routing method based on reinforcement learning (RL) under software-defined networks (SDN), namely the Q-learning widest-path routing algorithm (Q-WPRA), is proposed. This algorithm processes the reward function according to the link bandwidth in the execution environment to find the optimal (i.e., widest) transmission path with the maximum bandwidth between the source and the destination through RL. The experimental results reveal that the Q-WPRA is outperformance than Dijkstra’s algorithm and Dijkstra’s widest-path algorithm to find the widest transmission path in SDN environment under different bandwidths, loss rates, and background traffic. |
| first_indexed | 2024-03-11T16:51:44Z |
| format | Article |
| id | doaj.art-ca72846e20e44f38903c65b559cac458 |
| institution | Directory Open Access Journal |
| issn | 2405-9595 |
| language | English |
| last_indexed | 2024-03-11T16:51:44Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | ICT Express |
| spelling | doaj.art-ca72846e20e44f38903c65b559cac4582023-10-21T04:22:58ZengElsevierICT Express2405-95952023-10-0195882889A reinforcement learning approach for widest path routing in software-defined networksChih-Heng Ke0Yi-Hao Tu1Yi-Wei Ma2Department of Computer Science and Information Engineering, National Quemoy University, Kinmen, 892, TaiwanDepartment of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, 106, Taiwan; Corresponding author.Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, 106, TaiwanIn this paper, a routing method based on reinforcement learning (RL) under software-defined networks (SDN), namely the Q-learning widest-path routing algorithm (Q-WPRA), is proposed. This algorithm processes the reward function according to the link bandwidth in the execution environment to find the optimal (i.e., widest) transmission path with the maximum bandwidth between the source and the destination through RL. The experimental results reveal that the Q-WPRA is outperformance than Dijkstra’s algorithm and Dijkstra’s widest-path algorithm to find the widest transmission path in SDN environment under different bandwidths, loss rates, and background traffic.http://www.sciencedirect.com/science/article/pii/S2405959522001503Reinforcement learningSoftware-defined networksReward functionQ-WPRAWidest path |
| spellingShingle | Chih-Heng Ke Yi-Hao Tu Yi-Wei Ma A reinforcement learning approach for widest path routing in software-defined networks ICT Express Reinforcement learning Software-defined networks Reward function Q-WPRA Widest path |
| title | A reinforcement learning approach for widest path routing in software-defined networks |
| title_full | A reinforcement learning approach for widest path routing in software-defined networks |
| title_fullStr | A reinforcement learning approach for widest path routing in software-defined networks |
| title_full_unstemmed | A reinforcement learning approach for widest path routing in software-defined networks |
| title_short | A reinforcement learning approach for widest path routing in software-defined networks |
| title_sort | reinforcement learning approach for widest path routing in software defined networks |
| topic | Reinforcement learning Software-defined networks Reward function Q-WPRA Widest path |
| url | http://www.sciencedirect.com/science/article/pii/S2405959522001503 |
| work_keys_str_mv | AT chihhengke areinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks AT yihaotu areinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks AT yiweima areinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks AT chihhengke reinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks AT yihaotu reinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks AT yiweima reinforcementlearningapproachforwidestpathroutinginsoftwaredefinednetworks |