QoS-Aware Adaptive Routing in Multi-layer Hierarchical Software Defined Networks: A Reinforcement Learning Approach
Abstract
Software-defined networks (SDNs) have been recognized as the next-generation networking paradigm that decouples the data forwarding from the centralized control. To realize the merits of dedicated QoS provisioning and fast route (re-)configuration services over the decoupled SDNs, various QoS requirements in packet delay, loss, and throughput should be supported by an efficient transportation with respect to each specific application. In this paper, a QoS-aware adaptive routing (QAR) is proposed in the designed multi-layer hierarchical SDNs. Specifically, the distributed hierarchical control plane architecture is employed to minimize signaling delay in large SDNs via three-levels design of controllers, i.e., the super, domain (or master), and slave controllers. Furthermore, QAR algorithm is proposed with the aid of reinforcement learning and QoS-aware reward function, achieving a time-efficient, adaptive, QoS-provisioning packet forwarding. Simulation results confirm that QAR outperforms the existing learning solution and provides fast convergence with QoS provisioning, facilitating the practical implementations in large-scale software service-defined networks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The SARSA-based QAR algorithm is not specific to a multi-layer hierarchical SDN control plane and is meant to run on any controller with global visibility.
“the proposed SARSA-based routing algorithm is not specific to such an architecture, and is meant to run on any controller that has global visibility of the different paths and links in the network.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [276]
QAR is a centralized SARSA with softmax policy selection applied to achieve QoS-aware adaptive routing in SDN.
“a centralized SARSA with a softmax policy selection algorithm has been applied by Lin et al. [276] to achieve QoS-aware adaptive routing (QAR) in SDN.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [276]
QAR achieves faster convergence time (20 episodes less) compared to Q-learning with QoS-awareness.
“Compared to Q-learning with QoS-awareness: • Faster convergence time (20 episodes less)”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [276]
In SDN and WSN, the existence of a central node allows for centralized learning.
“in SDN [276] as well as WSN, the existence of a central node-the controller in SDN and the sink in WSN, respectively-allows for centralized learning.”
From A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities (2018) · cites this paper as [276]
Cites
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083 · see citing works
Reinforcement Learning: An Introduction
Johnson, J. D., Li, J., & Chen, Z. (2000) · Neurocomputing · doi:10.1016/s0925-2312(00)00324-6 · Cited by 8,821 · see citing works
McKeown (2008) · doi:10.1145/1355734.1355746 · Cited by 8,513 · see citing works
On-line Q-learning Using Connectionist Systems
Rummery, G. A. (1994) · Cited by 1,475 · see citing works
Onix: a distributed control platform for large-scale production networks
Koponen, T., Casado, M., Gude, N. S., Stribling, J., Poutievski, L., Zhu, M., Ramanathan, R., Iwata, Y., Inoue, H., Hama, T., et al. (2010) · doi:10.5555/1924943.1924968 · Cited by 1,247 · see citing works
Achieving high utilization with software-driven WAN
Hong, C.-Y., Kandula, S., Mahajan, R., Zhang, M., Gill, V., Nanduri, M., & Wattenhofer, R. P. (2013) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/2486001.2486012 · Cited by 1,074 · see citing works
Jain, S., Kumar, A., Mandal, S., Ong, J. S., Poutievski, L., Singh, A., Venkata, S., Wanderer, J., Zhou, J., Zhu, M., et al. (2013) · ACM SIGCOMM Computer Communication Review · doi:10.1145/2534169.2486019 · Cited by 1,007 · see citing works
Computer Networking: A Top-Down Approach
Kurose, J. F., & Ross, K. W. (2012) · Cited by 831 · see citing works
Computer Networking A Top- Down Approach
Kurose, & Ross (2017) · Cited by 780 · see citing works
Yeganeh, S. H., & Ganjali, Y. (2012) · doi:10.1145/2342441.2342446 · Cited by 645 · see citing works
A roadmap for traffic engineering in SDN-OpenFlow networks
Akyildiz, I. F., Lee, A., Wang, P., Luo, M., & Chou, W. (2014) · Computer Networks · doi:10.1016/j.comnet.2014.06.002 · Cited by 536 · see citing works
Self-citationThe Multi-Armed Bandit Problem: Decomposition and Computation
Katehakis, M. N., & Veinott, A. F. (1987) · Mathematics of Operations Research · doi:10.1287/moor.12.2.262 · Cited by 347 · see citing works
SoftAir: A software defined networking architecture for 5G wireless systems
Akyildiz, I. F., Wang, P., & Lin, S. (2015) · Computer Networks · doi:10.1016/j.comnet.2015.05.007 · Cited by 272 · see citing works
Self-citationAkyildiz, I. F., Lin, S.-C., & Wang, P. (2015) · Computer Networks · doi:10.1016/j.comnet.2015.10.013 · Cited by 118 · see citing works
Self-citationControl traffic balancing in software defined networks
Lin, S., Wang, P., & Luo, M. (2015) · Computer Networks · doi:10.1016/j.comnet.2015.08.004 · Cited by 66 · see citing works
Self-citationAn adaptive multi-path computation framework for centrally controlled networks
Luo, M., Zeng, Y., Li, J., & Chou, W. (2015) · Computer Networks · doi:10.1016/j.comnet.2015.02.004 · Cited by 38 · see citing works
Self-citationReinforcement learning for cooperative sensing gain in cognitive radio ad hoc networks
Lo, B. F., & Akyildiz, I. F. (2012) · Wireless Networks · doi:10.1007/s11276-012-0530-4 · Cited by 33 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., & Caicedo, O. M. (2018) · Journal of Internet Services and Applications · doi:10.1186/s13174-018-0087-2 · Cited by 1,036 · see citing works
Xie, J., Yu, F. R., Huang, T., Xie, R., Liu, J., Wang, C., & Liu, Y. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2866942 · Cited by 700 · see citing works
Hybrid SDN evolution: A comprehensive survey of the state-of-the-art
Khorsandroo, S., Sánchez, A. G., Tosun, A. S., Arco, J., & Doriguzzi-Corin, R. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.107981 · Cited by 111 · see citing works
- Authors
- Lin, S.-C., Akyildiz, I. F., Wang, P., & Luo, M.
- Affiliations
- Georgia Institute of Technology (US)
- Wichita State University (US)
- Huawei Technologies (China) (CN)
- Venue
- 2016 IEEE International Conference on Services Computing (SCC)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 25-33
- OpenAlex
- W2512877821
- Cited by
- 255
- References
- 17
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 21 · 2023: 33 · 2022: 24 · 2021: 51 · 2020: 41 · 2019: 38 · 2018: 29 · 2017: 6
- FWCI
- 20.79
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Services Computing (publishedVersion)
- Holmes Museum Of Anthropology (Wichita State University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Optical Network Technologies
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Traffic and Congestion Control
- Keywords
- software-defined networking, reinforcement learning, domain controller, reward function design, packet delay, packet loss, throughput
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
