Abstract
Network traffic is growing with every passing day, making it more critical than ever to deal with the exploding amounts of Internet traffic and reduce delays; thus, self-learning network management systems are a must for efficient network management; such systems are called active queue management systems or AQM. This paper discusses the use of machine learning to auto-tune the parameters of AQM algorithms by training a deep reinforcement learning model to balance the queuing delay and through putto get the maximum possible network score which is also known as the reward system. Deep Q-Network (DQN) is used as the foundation to control and auto-tune the parameters of the RED algorithm. Results from the NS3 simulation suggest that the DQN algorithm has better network reliability and is thus preferable to the RED active queue control algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Athuraliya S, Low S, Li V, Yin Q (2001) REM active queue management. IEEE Netw Mag 15(3)
Kuhn N, Natarajan P, Khademi N, Ros D (2016) Characterization guidelines for active queue management (AQM). In: Internet engineering task force (IETF), RFC 7928. [Online]. Available: https://tools.ietf.org/html/rfc7928
Baker F, Fairhurst G (2015) IETF recommendations regarding active queue management. In: Internet engineering task force (IETF), RFC 7567. [Online]. Available: https://tools.ietf.org/html/rfc7567
Mohammadi M, Al-Fuqaha A, Sorour S, Guizani M (2018) Deep learning for IoT big data and streaming analytics: a survey. IEEE Commun Surv Tutor. [Online early access]. Available: https://doi.org/10.1109/COMST.2018.2844341
Sutton RS, Barto AG (2018) Reinforcement learning: an introduction, 2nd ed. MIT Press
Bouacida N, Shihada B (2018) Practical and dynamic buffer sizing using LearnQueue, IEEE Trans Mob Comput. [Online early access]. Available: https://doi.org/10.1109/TMC.2018.2868670
Bisoy SK, Pandey PK, Pati B (2017) Design of an active queue management technique based on neural networks for congestion control. In: 2017 IEEE international conference on advanced networks and telecommunications systems (ANTS). [Online]. Available: https://doi.org/10.1109/ANTS.2017.8384104
Vucevic N, Perez-Romero J, Sallent O, Agusti R (2007) Reinforcement learning for active queue management in mobile All-IP networks. In: 2007 IEEE 18th international symposium on personal, indoor and mobile radio communications. [Online]. Available: https://doi.org/10.1109/PIMRC.2007.4394713
Chen X, Zhang H, Wu C, Mao S, Ji Y, Bennis M (2018) Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning. IEEE Internet Things J. [Online early access]. Available: https://doi.org/10.1109/JIOT.2018.2876279
Xu Z, Tang J, Meng J, Zhang W, Wang Y, Liu CH, Yang D (2018) Experience driven networking: a deep reinforcement learning based approach. In: IEEE INFOCOM 2018—IEEE conference on computer communications. [Online]. Available: https://doi.org/10.1109/INFOCOM.2018.8485853
Gadicha AB et al (2021) J Phys Conf Ser 1963:012141
Bansal R et al (2021) J Phys Conf Ser 1963:012170
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, vol 9, pp 249–256. [Online]. Available: http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf
Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980v9. [Online]. Available: https://arxiv.org/abs/1412.6980
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Basheer, A., Hassan, H.J., Muttasher, G. (2022). Intelligent Parameter Tuning Using Deep Q-Network for RED Algorithm in Adaptive Queue Management Systems. In: Sharma, D.K., Peng, SL., Sharma, R., Zaitsev, D.A. (eds) Micro-Electronics and Telecommunication Engineering . ICMETE 2021. Lecture Notes in Networks and Systems, vol 373. Springer, Singapore. https://doi.org/10.1007/978-981-16-8721-1_42
Download citation
DOI: https://doi.org/10.1007/978-981-16-8721-1_42
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8720-4
Online ISBN: 978-981-16-8721-1
eBook Packages: EngineeringEngineering (R0)